@article{abbasi2019MachineLearningApplications,
  title = {Machine Learning Applications in Epilepsy},
  author = {Abbasi, Bardia and Goldenholz, Daniel M.},
  date = {2019-10},
  journaltitle = {Epilepsia},
  shortjournal = {Epilepsia},
  volume = {60},
  number = {10},
  pages = {2037--2047},
  issn = {0013-9580, 1528-1167},
  doi = {10.1111/epi.16333},
  url = {https://onlinelibrary.wiley.com/doi/10.1111/epi.16333},
  urldate = {2022-03-08},
  abstract = {Machine learning leverages statistical and computer science principles to develop algorithms capable of improving performance through interpretation of data rather than through explicit instructions. Alongside widespread use in image recognition, language processing, and data mining, machine learning techniques have received increasing attention in medical applications, ranging from automated imaging analysis to disease forecasting. This review examines the parallel progress made in epilepsy, highlighting applications in automated seizure detection from electroencephalography (EEG), video, and kinetic data, automated imaging analysis and pre‐surgical planning, prediction of medication response, and prediction of medical and surgical outcomes using a wide variety of data sources. A brief overview of commonly used machine learning approaches, as well as challenges in further application of machine learning techniques in epilepsy, is also presented. With increasing computational capabilities, availability of effective machine learning algorithms, and accumulation of larger datasets, clinicians and researchers will increasingly benefit from familiarity with these techniques and the significant progress already made in their application in epilepsy.},
  langid = {english},
  keywords = {read_nonote},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\PLEVBU7M\\Abbasi and Goldenholz - 2019 - Machine learning applications in epilepsy.pdf}
}

@article{acar2007MultiwayAnalysisEpilepsy,
  title = {Multiway Analysis of Epilepsy Tensors},
  author = {Acar, Evrim and Aykut-Bingol, Canan and Bingol, Haluk and Bro, Rasmus and Yener, Bülent},
  date = {2007-07-01},
  journaltitle = {Bioinformatics},
  shortjournal = {Bioinformatics},
  volume = {23},
  number = {13},
  pages = {i10-i18},
  issn = {1367-4803},
  doi = {10.1093/bioinformatics/btm210},
  url = {https://doi.org/10.1093/bioinformatics/btm210},
  urldate = {2022-05-03},
  abstract = {Motivation: The success or failure of an epilepsy surgery depends greatly on the localization of epileptic focus (origin of a seizure). We address the problem of identification of a seizure origin through an analysis of ictal electroencephalogram (EEG), which is proven to be an effective standard in epileptic focus localization.Summary: With a goal of developing an automated and robust way of visual analysis of large amounts of EEG data, we propose a novel approach based on multiway models to study epilepsy seizure structure. Our contributions are 3-fold. First, we construct an Epilepsy Tensor with three modes, i.e. time samples, scales and electrodes, through wavelet analysis of multi-channel ictal EEG. Second, we demonstrate that multiway analysis techniques, in particular parallel factor analysis (PARAFAC), provide promising results in modeling the complex structure of an epilepsy seizure, localizing a seizure origin and extracting artifacts. Third, we introduce an approach for removing artifacts using multilinear subspace analysis and discuss its merits and drawbacks.Results: Ictal EEG analysis of 10 seizures from 7 patients are included in this study. Our results for 8 seizures match with clinical observations in terms of seizure origin and extracted artifacts. On the other hand, for 2 of the seizures, seizure localization is not achieved using an initial trial of PARAFAC modeling. In these cases, first, we apply an artifact removal method and subsequently apply the PARAFAC model on the epilepsy tensor from which potential artifacts have been removed. This method successfully identifies the seizure origin in both cases.Contact:acare@cs.rpi.edu},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Acar et al\\2007\\Acar et al_2007_Multiway analysis of epilepsy tensors.pdf;C\:\\Users\\selinederooij\\surfdrive\\notes\\PhD_Notes\\Reading Notes\\@acar2007MultiwayAnalysisEpilepsy.md;C\:\\Users\\selinederooij\\Zotero\\storage\\AMKG6TNL\\234097.html}
}

@article{acharya2013AutomatedEEGAnalysis,
  title = {Automated {{EEG}} Analysis of Epilepsy: {{A}} Review},
  shorttitle = {Automated {{EEG}} Analysis of Epilepsy},
  author = {Acharya, U. Rajendra and Vinitha Sree, S. and Swapna, G. and Martis, Roshan Joy and Suri, Jasjit S.},
  date = {2013-06-01},
  journaltitle = {Knowledge-Based Systems},
  shortjournal = {Knowledge-Based Systems},
  volume = {45},
  pages = {147--165},
  issn = {0950-7051},
  doi = {10.1016/j.knosys.2013.02.014},
  url = {https://www.sciencedirect.com/science/article/pii/S0950705113000798},
  urldate = {2022-03-17},
  abstract = {Epilepsy is an electrophysiological disorder of the brain, characterized by recurrent seizures. Electroencephalogram (EEG) is a test that measures and records the electrical activity of the brain, and is widely used in the detection and analysis of epileptic seizures. However, it is often difficult to identify subtle but critical changes in the EEG waveform by visual inspection, thus opening up a vast research area for biomedical engineers to develop and implement several intelligent algorithms for the identification of such subtle changes. Moreover, the EEG signals are nonlinear and non-stationary in nature, which contribute to further complexities related to their manual interpretation and detection of normal and abnormal (interictal and ictal) activities. Hence, it is necessary to develop a Computer Aided Diagnostic (CAD) system to automatically identify the normal and abnormal activities using minimum number of highly discriminating features in classifiers. It has been found that nonlinear features are able to capture the complex physiological phenomena such as abrupt transitions and chaotic behavior in the EEG signals. In this review, we discuss various feature extraction methods and the results of different automated epilepsy stage detection techniques in detail. We also briefly present the various open ended challenges that need to be addressed before a CAD based epilepsy detection system can be set-up in a clinical setting.},
  langid = {english},
  keywords = {Classification,EEG,Epilepsy,Fractal dimension,Higher order spectra,Ictal,Interictal,Nonlinear,Recurrence plot},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Acharya et al\\2013\\Acharya et al_2013_Automated EEG analysis of epilepsy.pdf;C\:\\Users\\selinederooij\\Zotero\\storage\\DM9JXGXC\\S0950705113000798.html}
}

@article{acharya2018AutomatedSeizurePrediction,
  title = {Automated Seizure Prediction},
  author = {Acharya, U. Rajendra and Hagiwara, Yuki and Adeli, Hojjat},
  date = {2018-11},
  journaltitle = {Epilepsy \& Behavior},
  shortjournal = {Epilepsy \& Behavior},
  volume = {88},
  pages = {251--261},
  issn = {15255050},
  doi = {10.1016/j.yebeh.2018.09.030},
  url = {https://linkinghub.elsevier.com/retrieve/pii/S1525505018305791},
  urldate = {2022-03-08},
  abstract = {In the past two decades, significant advances have been made on automated electroencephalogram (EEG)-based diagnosis of epilepsy and seizure detection. A number of innovative algorithms have been introduced that can aid in epilepsy diagnosis with a high degree of accuracy. In recent years, the frontiers of computational epilepsy research have moved to seizure prediction, a more challenging problem. While antiepileptic medication can result in complete seizure freedom in many patients with epilepsy, up to one-third of patients living with epilepsy will have medically intractable epilepsy, where medications reduce seizure frequency but do not completely control seizures. If a seizure can be predicted prior to its clinical manifestation, then there is potential for abortive treatment to be given, either self-administered or via an implanted device administering medication or electrical stimulation. This will have a far-reaching impact on the treatment of epilepsy and patient's quality of life. This paper presents a state-of-the-art review of recent efforts and journal articles on seizure prediction. The technologies developed for epilepsy diagnosis and seizure detection are being adapted and extended for seizure prediction. The paper ends with some novel ideas for seizure prediction using the increasingly ubiquitous machine learning technology, particularly deep neural network machine learning.},
  langid = {english},
  keywords = {read_nonote},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\LHDYSKYL\\Acharya et al. - 2018 - Automated seizure prediction.pdf}
}

@article{acharyaApplicationNonlinearWavelet2012a,
  title = {Application of Non-Linear and Wavelet Based Features for the Automated Identification of Epileptic Eeg Signals},
  author = {Acharya, U. Rajendra and Sree, S. Vinitha and Ang, Peng Chuan Alvin and Yanti, Ratna and Suri, Jasjit S.},
  date = {2012-04},
  journaltitle = {International Journal of Neural Systems},
  shortjournal = {Int. J. Neur. Syst.},
  volume = {22},
  number = {02},
  pages = {1250002},
  publisher = {{World Scientific Publishing Co.}},
  issn = {0129-0657},
  doi = {10.1142/S0129065712500025},
  url = {https://www.worldscientific.com/doi/10.1142/S0129065712500025},
  urldate = {2022-03-07},
  abstract = {Epilepsy, a neurological disorder, is characterized by the recurrence of seizures. Electroencephalogram (EEG) signals, which are used to detect the presence of seizures, are non-linear and dynamic in nature. Visual inspection of the EEG signals for detection of normal, interictal, and ictal activities is a strenuous and time-consuming task due to the huge volumes of EEG segments that have to be studied. Therefore, non-linear methods are being widely used to study EEG signals for the automatic monitoring of epileptic activities. The aim of our work is to develop a Computer Aided Diagnostic (CAD) technique with minimal pre-processing steps that can classify all the three classes of EEG segments, namely normal, interictal, and ictal, using a small number of highly discriminating non-linear features in simple classifiers. To evaluate the technique, segments of normal, interictal, and ictal EEG segments (100 segments in each class) were used. Non-linear features based on the Higher Order Spectra (HOS), two entropies, namely the Approximation Entropy (ApEn) and the Sample Entropy (SampEn), and Fractal Dimension and Hurst Exponent were extracted from the segments. Significant features were selected using the ANOVA test. After evaluating the performance of six classifiers (Decision Tree, Fuzzy Sugeno Classifier, Gaussian Mixture Model, K-Nearest Neighbor, Support Vector Machine, and Radial Basis Probabilistic Neural Network) using a combination of the selected features, we found that using a set of all the selected six features in the Fuzzy classifier resulted in 99.7\% classification accuracy. We have demonstrated that our technique is capable of achieving high accuracy using a small number of features that accurately capture the subtle differences in the three different types of EEG (normal, interictal, and ictal) segments. The technique can be easily written as a software application and used by medical professionals without any extensive training and cost. Such software can evolve into an automatic seizure monitoring application in the near future and can aid the doctors in providing better and timely care for the patients suffering from epilepsy.},
  keywords = {electroencephalograms,entropies,Epilepsy,Higher Order Spectra,ictal,interictal,non-linear analysis,unread},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Acharya et al_2012_Application of non-linear and wavelet based features for the automated.pdf}
}

@article{acharyaAutomatedDiagnosisEpileptic2012,
  title = {Automated Diagnosis of Epileptic {{EEG}} Using Entropies},
  author = {Acharya, U.R. and Molinari, F. and Sree, S.V. and Chattopadhyay, S. and Ng, K.-H. and Suri, J.S.},
  date = {2012},
  journaltitle = {Biomedical Signal Processing and Control},
  volume = {7},
  number = {4},
  pages = {401--408},
  issn = {1746-8094},
  doi = {10.1016/j.bspc.2011.07.007},
  abstract = {Epilepsy is a neurological disorder characterized by the presence of recurring seizures. Like many other neurological disorders, epilepsy can be assessed by the electroencephalogram (EEG). The EEG signal is highly non-linear and non-stationary, and hence, it is difficult to characterize and interpret it. However, it is a well-established clinical technique with low associated costs. In this work, we propose a methodology for the automatic detection of normal, pre-ictal, and ictal conditions from recorded EEG signals. Four entropy features namely Approximate Entropy (ApEn), Sample Entropy (SampEn), Phase Entropy 1 (S1), and Phase Entropy 2 (S2) were extracted from the collected EEG signals. These features were fed to seven different classifiers: Fuzzy Sugeno Classifier (FSC), Support Vector Machine (SVM), K-Nearest Neighbour (KNN), Probabilistic Neural Network (PNN), Decision Tree (DT), Gaussian Mixture Model (GMM), and Naive Bayes Classifier (NBC). Our results show that the Fuzzy classifier was able to differentiate the three classes with a high accuracy of 98.1\%. Overall, compared to previous techniques, our proposed strategy is more suitable for diagnosis of epilepsy with higher accuracy. © 2011 Elsevier Ltd. All rights reserved.},
  langid = {english},
  keywords = {Classifiers,EEG,Entropy,Epilepsy,Feature extraction,Preictal,unread},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\AQZJE3BB\\Acharya et al. - 2012 - Automated diagnosis of epileptic EEG using entropi.pdf;C\:\\Users\\selinederooij\\Zotero\\storage\\AIVGQ2LR\\display.html}
}

@incollection{akbani2004ApplyingSupportVector,
  title = {Applying {{Support Vector Machines}} to {{Imbalanced Datasets}}},
  booktitle = {Machine {{Learning}}: {{ECML}} 2004},
  author = {Akbani, Rehan and Kwek, Stephen and Japkowicz, Nathalie},
  editor = {Boulicaut, Jean-François and Esposito, Floriana and Giannotti, Fosca and Pedreschi, Dino},
  date = {2004},
  series = {Lecture {{Notes}} in {{Computer Science}}},
  volume = {3201},
  pages = {39--50},
  publisher = {{Springer Berlin Heidelberg}},
  location = {{Berlin, Heidelberg}},
  doi = {10.1007/978-3-540-30115-8_7},
  url = {http://link.springer.com/10.1007/978-3-540-30115-8_7},
  urldate = {2022-03-08},
  abstract = {Support Vector Machines (SVM) have been extensively studied and have shown remarkable success in many applications. However the success of SVM is very limited when it is applied to the problem of learning from imbalanced datasets in which negative instances heavily outnumber the positive instances (e.g. in gene profiling and detecting credit card fraud). This paper discusses the factors behind this failure and explains why the common strategy of undersampling the training data may not be the best choice for SVM. We then propose an algorithm for overcoming these problems which is based on a variant of the SMOTE algorithm by Chawla et al, combined with Veropoulos et al’s different error costs algorithm. We compare the performance of our algorithm against these two algorithms, along with undersampling and regular SVM and show that our algorithm outperforms all of them.},
  editorb = {Hutchison, David and Kanade, Takeo and Kittler, Josef and Kleinberg, Jon M. and Mattern, Friedemann and Mitchell, John C. and Naor, Moni and Nierstrasz, Oscar and Pandu Rangan, C. and Steffen, Bernhard and Sudan, Madhu and Terzopoulos, Demetri and Tygar, Dough and Vardi, Moshe Y. and Weikum, Gerhard},
  editorbtype = {redactor},
  isbn = {978-3-540-23105-9 978-3-540-30115-8},
  langid = {english},
  keywords = {unread},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\QWKFZ5CU\\Akbani et al. - 2004 - Applying Support Vector Machines to Imbalanced Dat.pdf}
}

@article{alotaiby2015ReviewChannelSelection,
  title = {A Review of Channel Selection Algorithms for {{EEG}} Signal Processing},
  author = {Alotaiby, Turky and Abd El-Samie, Fathi E. and Alshebeili, Saleh A. and Ahmad, Ishtiaq},
  date = {2015-08-01},
  journaltitle = {Eurasip Journal on Advances in Signal Processing},
  shortjournal = {EURASIP J. Adv. Signal Process.},
  pages = {66},
  publisher = {{Springer}},
  location = {{New York}},
  issn = {1687-6180},
  doi = {10.1186/s13634-015-0251-9},
  url = {https://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=DOISource&SrcApp=WOS&KeyAID=10.1186%2Fs13634-015-0251-9&DestApp=DOI&SrcAppSID=5DacMNcAZiO4ZnGIAYT&SrcJTitle=EURASIP+JOURNAL+ON+ADVANCES+IN+SIGNAL+PROCESSING&DestDOIRegistrantName=Springer+%28Biomed+Central+Ltd.%29},
  urldate = {2022-03-17},
  abstract = {Digital processing of electroencephalography (EEG) signals has now been popularly used in a wide variety of applications such as seizure detection/prediction, motor imagery classification, mental task classification, emotion classification, sleep state classification, and drug effects diagnosis. With the large number of EEG channels acquired, it has become apparent that efficient channel selection algorithms are needed with varying importance from one application to another. The main purpose of the channel selection process is threefold: (i) to reduce the computational complexity of any processing task performed on EEG signals by selecting the relevant channels and hence extracting the features of major importance, (ii) to reduce the amount of overfitting that may arise due to the utilization of unnecessary channels, for the purpose of improving the performance, and (iii) to reduce the setup time in some applications. Signal processing tools such as time-domain analysis, power spectral estimation, and wavelet transform have been used for feature extraction and hence for channel selection in most of channel selection algorithms. In addition, different evaluation approaches such as filtering, wrapper, embedded, hybrid, and human-based techniques have been widely used for the evaluation of the selected subset of channels. In this paper, we survey the recent developments in the field of EEG channel selection methods along with their applications and classify these methods according to the evaluation approach.},
  langid = {english},
  keywords = {brain-computer interfaces,Channel selection,classification,communication,components,EEG signals,Emotion classification,Mental task classification,Motor imagery classification,neonatal seizure detection,Seizure detection,Sleep state   classification,unread},
  annotation = {WOS:000358779400001},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Alotaiby et al\\2015\\Alotaiby et al_2015_A review of channel selection algorithms for EEG signal processing.pdf}
}

@article{ansari2019NeonatalSeizureDetection,
  title = {Neonatal {{Seizure Detection Using Deep Convolutional Neural Networks}}},
  author = {Ansari, Amir H. and Cherian, Perumpillichira J. and Caicedo, Alexander and Naulaers, Gunnar and De Vos, Maarten and Van Huffel, Sabine},
  date = {2019-05},
  journaltitle = {International Journal of Neural Systems},
  shortjournal = {Int. J. Neur. Syst.},
  volume = {29},
  number = {04},
  pages = {1850011},
  publisher = {{World Scientific Publishing Co.}},
  issn = {0129-0657},
  doi = {10.1142/S0129065718500119},
  url = {https://www.worldscientific.com/doi/abs/10.1142/S0129065718500119},
  urldate = {2022-04-25},
  abstract = {Identifying a core set of features is one of the most important steps in the development of an automated seizure detector. In most of the published studies describing features and seizure classifiers, the features were hand-engineered, which may not be optimal. The main goal of the present paper is using deep convolutional neural networks (CNNs) and random forest to automatically optimize feature selection and classification. The input of the proposed classifier is raw multi-channel EEG and the output is the class label: seizure/nonseizure. By training this network, the required features are optimized, while fitting a nonlinear classifier on the features. After training the network with EEG recordings of 26 neonates, five end layers performing the classification were replaced with a random forest classifier in order to improve the performance. This resulted in a false alarm rate of 0.9 per hour and seizure detection rate of 77\% using a test set of EEG recordings of 22 neonates that also included dubious seizures. The newly proposed CNN classifier outperformed three data-driven feature-based approaches and performed similar to a previously developed heuristic method.},
  keywords = {convolutional neural network,Deep neural networks,neonatal seizure detection,random forest,unread},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Ansari et al\\2019\\Ansari et al_2019_Neonatal Seizure Detection Using Deep Convolutional Neural Networks.pdf}
}

@misc{baltrusaitis2017MultimodalMachineLearning,
  title = {Multimodal {{Machine Learning}}: {{A Survey}} and {{Taxonomy}}},
  shorttitle = {Multimodal {{Machine Learning}}},
  author = {Baltrušaitis, Tadas and Ahuja, Chaitanya and Morency, Louis-Philippe},
  date = {2017-08-01},
  number = {arXiv:1705.09406},
  eprint = {1705.09406},
  eprinttype = {arxiv},
  primaryclass = {cs},
  publisher = {{arXiv}},
  url = {http://arxiv.org/abs/1705.09406},
  urldate = {2022-06-16},
  abstract = {Our experience of the world is multimodal - we see objects, hear sounds, feel texture, smell odors, and taste flavors. Modality refers to the way in which something happens or is experienced and a research problem is characterized as multimodal when it includes multiple such modalities. In order for Artificial Intelligence to make progress in understanding the world around us, it needs to be able to interpret such multimodal signals together. Multimodal machine learning aims to build models that can process and relate information from multiple modalities. It is a vibrant multi-disciplinary field of increasing importance and with extraordinary potential. Instead of focusing on specific multimodal applications, this paper surveys the recent advances in multimodal machine learning itself and presents them in a common taxonomy. We go beyond the typical early and late fusion categorization and identify broader challenges that are faced by multimodal machine learning, namely: representation, translation, alignment, fusion, and co-learning. This new taxonomy will enable researchers to better understand the state of the field and identify directions for future research.},
  archiveprefix = {arXiv},
  keywords = {Computer Science - Machine Learning},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Baltrušaitis et al\\2017\\Baltrušaitis et al_2017_Multimodal Machine Learning.pdf;C\:\\Users\\selinederooij\\Zotero\\storage\\NTBBPMK4\\1705.html}
}

@article{baud2018MultidayRhythmsModulate,
  title = {Multi-Day Rhythms Modulate Seizure Risk in Epilepsy},
  author = {Baud, Maxime O. and Kleen, Jonathan K. and Mirro, Emily A. and Andrechak, Jason C. and King-Stephens, David and Chang, Edward F. and Rao, Vikram R.},
  date = {2018-12},
  journaltitle = {Nature Communications},
  shortjournal = {Nat Commun},
  volume = {9},
  number = {1},
  pages = {88},
  issn = {2041-1723},
  doi = {10.1038/s41467-017-02577-y},
  url = {http://www.nature.com/articles/s41467-017-02577-y},
  urldate = {2022-03-08},
  langid = {english},
  keywords = {read_nonote},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\P2T76HC5\\Baud et al. - 2018 - Multi-day rhythms modulate seizure risk in epileps.pdf}
}

@article{blankertz2008OptimizingSpatialFilters,
  title = {Optimizing {{Spatial}} Filters for {{Robust EEG Single-Trial Analysis}}},
  author = {Blankertz, Benjamin and Tomioka, Ryota and Lemm, Steven and Kawanabe, Motoaki and Muller, Klaus-robert},
  date = {2008},
  journaltitle = {IEEE Signal Processing Magazine},
  volume = {25},
  number = {1},
  pages = {41--56},
  issn = {1558-0792},
  doi = {10.1109/MSP.2008.4408441},
  abstract = {Due to the volume conduction multichannel electroencephalogram (EEG) recordings give a rather blurred image of brain activity. Therefore spatial filters are extremely useful in single-trial analysis in order to improve the signal-to-noise ratio. There are powerful methods from machine learning and signal processing that permit the optimization of spatio-temporal filters for each subject in a data dependent fashion beyond the fixed filters based on the sensor geometry, e.g., Laplacians. Here we elucidate the theoretical background of the common spatial pattern (CSP) algorithm, a popular method in brain-computer interface (BCD research. Apart from reviewing several variants of the basic algorithm, we reveal tricks of the trade for achieving a powerful CSP performance, briefly elaborate on theoretical aspects of CSP, and demonstrate the application of CSP-type preprocessing in our studies of the Berlin BCI (BBCI) project.},
  eventtitle = {{{IEEE Signal Processing Magazine}}},
  keywords = {Brain,Electroencephalography,Geometry,Machine learning,Optimization methods,Robustness,Signal analysis,Signal processing algorithms,Signal to noise ratio,Spatial filters},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Blankertz et al\\2008\\Blankertz et al_2008_Optimizing Spatial filters for Robust EEG Single-Trial Analysis.pdf;C\:\\Users\\selinederooij\\Zotero\\storage\\NBTE4528\\4408441.html}
}

@inproceedings{boeckx2018LiveDemonstrationSeizeIT,
  title = {Live {{Demonstration}}: {{SeizeIT}} - {{A}} Wearable Multimodal Epileptic Seizure Detection Device},
  shorttitle = {Live {{Demonstration}}},
  booktitle = {2018 {{IEEE Biomedical Circuits}} and {{Systems Conference}} ({{BioCAS}})},
  author = {Boeckx, Steven and van Paesschen, Wim and Bonte, Brecht and Dan, Jonathan},
  options = {useprefix=true},
  date = {2018-10},
  pages = {1--1},
  publisher = {{IEEE}},
  location = {{Cleveland, OH}},
  doi = {10.1109/BIOCAS.2018.8584738},
  url = {https://ieeexplore.ieee.org/document/8584738/},
  urldate = {2022-03-08},
  abstract = {This demonstration presents a small wearable multisensor device for epileptic activity monitoring and seizure detection in the everyday life of a patient. The demonstration setup consists of the wearable medical sensor accompanied by a docking station for wireless charging and data transfer. A software application allows streaming of the physiological signals in real-time, as well as managing, viewing and processing the recorded data.},
  eventtitle = {2018 {{IEEE Biomedical Circuits}} and {{Systems Conference}} ({{BioCAS}})},
  isbn = {978-1-5386-3603-9},
  langid = {english},
  keywords = {read_nonote},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\TEQYX6EE\\Boeckx et al. - 2018 - Live Demonstration SeizeIT - A wearable multimoda.pdf}
}

@article{boonyakitanont2020ReviewFeatureExtraction,
  title = {A Review of Feature Extraction and Performance Evaluation in Epileptic Seizure Detection Using {{EEG}}},
  author = {Boonyakitanont, Poomipat and Lek-uthai, Apiwat and Chomtho, Krisnachai and Songsiri, Jitkomut},
  date = {2020-03-01},
  journaltitle = {Biomedical Signal Processing and Control},
  shortjournal = {Biomedical Signal Processing and Control},
  volume = {57},
  pages = {101702},
  issn = {1746-8094},
  doi = {10.1016/j.bspc.2019.101702},
  url = {https://www.sciencedirect.com/science/article/pii/S1746809419302836},
  urldate = {2022-03-17},
  abstract = {Since the manual detection of electrographic seizures in continuous electroencephalogram (EEG) monitoring is very time-consuming and requires a trained expert, attempts to develop automatic seizure detection are diverse and ongoing. Machine learning approaches are intensely being applied to this problem due to their ability to classify seizure conditions from a large amount of data, and provide pre-screened results for neurologists. Several features, data transformations, and classifiers have been explored to analyze and classify seizures via EEG signals. In the literature, some jointly-applied features used in the classification may have shared similar contributions, making them redundant in the learning process. Therefore, this paper aims to comprehensively summarize feature descriptions and their interpretations in characterizing epileptic seizures using EEG signals, as well as to review classification performance metrics. To provide meaningful information of feature selection, we conducted an experiment to examine the quality of each feature independently. The Bayesian error and non-parametric probability distribution estimation were employed to determine the significance of the individual features. Moreover, a redundancy analysis using a correlation-based feature selection was applied. The results showed that the following features – variance, energy, nonlinear energy, and Shannon entropy computed on a raw EEG signal, as well as variance, energy, kurtosis, and line length calculated on wavelet coefficients – were able to significantly capture the seizures. When compared with a baseline method of classifying all epochs as normal, an improvement of 4.77–13.51\% in the Bayesian error was obtained.},
  langid = {english},
  keywords = {classification,EEG,Feature extraction,read,Seizure detection},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Boonyakitanont et al\\2020\\Boonyakitanont et al_2020_A review of feature extraction and performance evaluation in epileptic seizure.pdf;C\:\\Users\\selinederooij\\surfdrive\\notes\\PhD_Notes\\Reading Notes\\@boonyakitanont2020ReviewFeatureExtraction.md;C\:\\Users\\selinederooij\\Zotero\\storage\\4UYVZTIS\\S1746809419302836.html}
}

@article{bouassi2017AccuratePredictionEpileptic,
  title = {Towards Accurate Prediction of Epileptic Seizures: {{A}} Review},
  shorttitle = {Towards Accurate Prediction of Epileptic Seizures},
  author = {Bou Assi, Elie and Nguyen, Dang K. and Rihana, Sandy and Sawan, Mohamad},
  date = {2017-04-01},
  journaltitle = {Biomedical Signal Processing and Control},
  shortjournal = {Biomedical Signal Processing and Control},
  volume = {34},
  pages = {144--157},
  issn = {1746-8094},
  doi = {10.1016/j.bspc.2017.02.001},
  url = {https://www.sciencedirect.com/science/article/pii/S1746809417300277},
  urldate = {2022-03-17},
  abstract = {Recent research has investigated the possibility of predicting epileptic seizures. Intervention before the onset of seizure manifestations could be envisioned with accurate seizure forecasting. Although efforts for better prediction have been made, the translation of current approaches to clinical applications is still not possible. While early findings have been optimistic, the absence of statistical validation and reproducibility has raised doubts about the existence of a preictal state. Analysis and algorithmic studies are providing evidence that transition to the ictal state is not random, with build-up leading to seizures. We have reviewed the general framework of reliable algorithmic seizure prediction studies, discussing each component of the whole block diagram. We have explored steps along the pathway, from signal acquisition to adequate performance evaluation that should be taken into account in the design of an efficient seizure advisory/intervention system. The present review has established that there is potential for improvement and optimization in the seizure prediction framework. New databases, higher sampling frequencies, adequate preprocessing, electrode selection, and machine-learning considerations are all elements of the prediction scheme that should be assessed to achieve more realistic, better-than-chance performances.},
  langid = {english},
  keywords = {Classification,Epilepsy,Feature extraction,Preictal state,Seizure forecasting,Signal processing,unread},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Bou Assi et al\\2017\\Bou Assi et al_2017_Towards accurate prediction of epileptic seizures.pdf;C\:\\Users\\selinederooij\\Zotero\\storage\\4KGSK8I4\\S1746809417300277.html}
}

@article{bousse2018LinearSystemsCanonical,
  title = {Linear Systems with a Canonical Polyadic Decomposition Constrained Solution: {{Algorithms}} and Applications},
  shorttitle = {Linear Systems with a Canonical Polyadic Decomposition Constrained Solution},
  author = {Boussé, M. and Vervliet, N. and Domanov, I. and Debals, O. and De Lathauwer, L.},
  date = {2018},
  journaltitle = {Numerical Linear Algebra with Applications},
  volume = {25},
  number = {6},
  pages = {e2190},
  issn = {1099-1506},
  doi = {10.1002/nla.2190},
  url = {https://onlinelibrary.wiley.com/doi/abs/10.1002/nla.2190},
  urldate = {2022-03-28},
  abstract = {Real-life data often exhibit some structure and/or sparsity, allowing one to use parsimonious models for compact representation and approximation. When considering matrix and tensor data, low-rank models such as the (multilinear) singular value decomposition, canonical polyadic decomposition (CPD), tensor train, and hierarchical Tucker model are very common. The solution of (large-scale) linear systems is often structured in a similar way, allowing one to use compact matrix and tensor models as well. In this paper, we focus on linear systems with a CPD-constrained solution (LS-CPD). Our main contribution is the development of optimization-based and algebraic methods to solve LS-CPDs. Furthermore, we propose a condition that guarantees generic uniqueness of the obtained solution. We also show that LS-CPDs provide a broad framework for the analysis of multilinear systems of equations. The latter are a higher-order generalization of linear systems, similar to tensor decompositions being a generalization of matrix decompositions. The wide applicability of LS-CPDs in domains such as classification, multilinear algebra, and signal processing is illustrated.},
  langid = {english},
  keywords = {higher-order tensor,linear systems,multilinear algebra,multilinear systems,tensor decompositions},
  annotation = {\_eprint: https://onlinelibrary.wiley.com/doi/pdf/10.1002/nla.2190},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Boussé et al\\2018\\Boussé et al_2018_Linear systems with a canonical polyadic decomposition constrained solution.pdf;C\:\\Users\\selinederooij\\Zotero\\storage\\X67AFXEH\\nla.html}
}

@article{bultheelWaveletsApplicationsSignal,
  title = {Wavelets with Applications in Signal and Image Processing},
  author = {Bultheel, Adhemar and Huybrechs, Daan},
  pages = {194},
  langid = {english},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\BLC2CAA5\\Bultheel and Huybrechs - Wavelets with applications in signal and image pro.pdf}
}

@article{chawla2002SMOTESyntheticMinority,
  title = {{{SMOTE}}: {{Synthetic Minority Over-sampling Technique}}},
  shorttitle = {{{SMOTE}}},
  author = {Chawla, N. V. and Bowyer, K. W. and Hall, L. O. and Kegelmeyer, W. P.},
  date = {2002-06-01},
  journaltitle = {Journal of Artificial Intelligence Research},
  volume = {16},
  pages = {321--357},
  issn = {1076-9757},
  doi = {10.1613/jair.953},
  url = {https://www.jair.org/index.php/jair/article/view/10302},
  urldate = {2022-03-08},
  abstract = {An approach to the construction of classifiers from    imbalanced datasets is described. A dataset is imbalanced if the    classification categories are not approximately equally    represented. Often real-world data sets are predominately composed of    ``normal'' examples with only a small percentage of ``abnormal'' or    ``interesting'' examples. It is also the case that the cost of    misclassifying an abnormal (interesting) example as a normal example    is often much higher than the cost of the reverse    error. Under-sampling of the majority (normal) class has been proposed    as a good means of increasing the sensitivity of a classifier to the    minority class. This paper shows that a combination of our method of    over-sampling the minority (abnormal) class and under-sampling the    majority (normal) class can achieve better classifier performance (in    ROC space) than only under-sampling the majority class.  This paper    also shows that a combination of our method of over-sampling the    minority class and under-sampling the majority class can achieve    better classifier performance (in ROC space) than varying the loss    ratios in Ripper or class priors in Naive Bayes. Our method of    over-sampling the minority class involves creating synthetic minority    class examples.  Experiments are performed using C4.5, Ripper and a    Naive Bayes classifier. The method is evaluated using the area under    the Receiver Operating Characteristic curve (AUC) and the ROC convex    hull strategy.},
  langid = {english},
  keywords = {read},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Chawla et al_2002_SMOTE2.pdf;C\:\\Users\\selinederooij\\surfdrive\\notes\\PhD_Notes\\Literature\\Machine Learning\\@chawla2002SMOTESyntheticMinority.md}
}

@article{chen2022KernelizedSupportTensor,
  title = {Kernelized Support Tensor Train Machines},
  author = {Chen, Cong and Batselier, Kim and Yu, Wenjian and Wong, Ngai},
  date = {2022-02-01},
  journaltitle = {Pattern Recognition},
  shortjournal = {Pattern Recognition},
  volume = {122},
  pages = {108337},
  issn = {0031-3203},
  doi = {10.1016/j.patcog.2021.108337},
  url = {https://www.sciencedirect.com/science/article/pii/S0031320321005173},
  urldate = {2022-03-28},
  abstract = {Tensor, a multi-dimensional data structure, has been exploited recently in the machine learning community. Traditional machine learning approaches are vector- or matrix-based, and cannot handle tensorial data directly. In this paper, we propose a tensor train (TT)-based kernel technique for the first time, and apply it to the conventional support vector machine (SVM) for high-dimensional image classification with very small number of training samples. Specifically, we propose a kernelized support tensor train machine that accepts tensorial input and preserves the intrinsic kernel property. The main contributions are threefold. First, we propose a TT-based feature mapping procedure that maintains the TT structure in the feature space. Second, we demonstrate two ways to construct the TT-based kernel function while considering consistency with the TT inner product and preservation of information. Third, we show that it is possible to apply different kernel functions on different data modes. In principle, our method tensorizes the standard SVM on its input structure and kernel mapping scheme. This reduces the storage and computation complexity of kernel matrix construction from exponential to polynomial. The validity proof and computation complexity of the proposed TT-based kernel functions are provided elaborately. Extensive experiments are performed on high-dimensional fMRI and color images datasets, which demonstrates the superiority of the proposed scheme compared with the state-of-the-art techniques.},
  langid = {english},
  keywords = {Image classification,Support tensor machine,Tensor,unread},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Chen et al\\2022\\Chen et al_2022_Kernelized support tensor train machines.pdf;C\:\\Users\\selinederooij\\Zotero\\storage\\22H2RMZA\\1-s2.0-S0031320321005173-main.pdf;C\:\\Users\\selinederooij\\Zotero\\storage\\MXCKYF46\\S0031320321005173.html}
}

@article{chisci2010RealTimeEpilepticSeizure,
  title = {Real-{{Time Epileptic Seizure Prediction Using AR Models}} and {{Support Vector Machines}}},
  author = {Chisci, Luigi and Mavino, Antonio and Perferi, Guido and Sciandrone, Marco and Anile, Carmelo and Colicchio, Gabriella and Fuggetta, Filomena},
  date = {2010-05},
  journaltitle = {IEEE Transactions on Biomedical Engineering},
  volume = {57},
  number = {5},
  pages = {1124--1132},
  issn = {1558-2531},
  doi = {10.1109/TBME.2009.2038990},
  abstract = {This paper addresses the prediction of epileptic seizures from the online analysis of EEG data. This problem is of paramount importance for the realization of monitoring/control units to be implanted on drug-resistant epileptic patients. The proposed solution relies in a novel way on autoregressive modeling of the EEG time series and combines a least-squares parameter estimator for EEG feature extraction along with a support vector machine (SVM) for binary classification between preictal/ictal and interictal states. This choice is characterized by low computational requirements compatible with a real-time implementation of the overall system. Moreover, experimental results on the Freiburg dataset exhibited correct prediction of all seizures (100 \% sensitivity) and, due to a novel regularization of the SVM classifier based on the Kalman filter, also a low false alarm rate.},
  eventtitle = {{{IEEE Transactions}} on {{Biomedical Engineering}}},
  keywords = {Autoregressive (AR) models,Brain modeling,Data analysis,EEG signals,Electroencephalography,Epilepsy,epileptic seizure prediction,Kalman filtering,Parameter estimation,Patient monitoring,Predictive models,State estimation,Support vector machine classification,Support vector machines,support vector machines (SVMs),unread},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Chisci et al\\2010\\Chisci et al_2010_Real-Time Epileptic Seizure Prediction Using AR Models and Support Vector.pdf;C\:\\Users\\selinederooij\\Zotero\\storage\\U664EXI7\\5415597.html}
}

@article{cichocki2016LowRankTensorNetworks,
  title = {Low-{{Rank Tensor Networks}} for {{Dimensionality Reduction}} and {{Large-Scale Optimization Problems}}: {{Perspectives}} and {{Challenges PART}} 1},
  shorttitle = {Low-{{Rank Tensor Networks}} for {{Dimensionality Reduction}} and {{Large-Scale Optimization Problems}}},
  author = {Cichocki, A. and Lee, N. and Oseledets, I. V. and Phan, A.-H. and Zhao, Q. and Mandic, D.},
  date = {2016},
  journaltitle = {Foundations and Trends® in Machine Learning},
  shortjournal = {FNT in Machine Learning},
  volume = {9},
  number = {4-5},
  eprint = {1609.00893},
  eprinttype = {arxiv},
  primaryclass = {cs},
  pages = {249--429},
  issn = {1935-8237, 1935-8245},
  doi = {10.1561/2200000059},
  url = {http://arxiv.org/abs/1609.00893},
  urldate = {2022-05-23},
  abstract = {Machine learning and data mining algorithms are becoming increasingly important in analyzing large volume, multi-relational and multi--modal datasets, which are often conveniently represented as multiway arrays or tensors. It is therefore timely and valuable for the multidisciplinary research community to review tensor decompositions and tensor networks as emerging tools for large-scale data analysis and data mining. We provide the mathematical and graphical representations and interpretation of tensor networks, with the main focus on the Tucker and Tensor Train (TT) decompositions and their extensions or generalizations. Keywords: Tensor networks, Function-related tensors, CP decomposition, Tucker models, tensor train (TT) decompositions, matrix product states (MPS), matrix product operators (MPO), basic tensor operations, multiway component analysis, multilinear blind source separation, tensor completion, linear/multilinear dimensionality reduction, large-scale optimization problems, symmetric eigenvalue decomposition (EVD), PCA/SVD, huge systems of linear equations, pseudo-inverse of very large matrices, Lasso and Canonical Correlation Analysis (CCA) (This is Part 1)},
  archiveprefix = {arXiv},
  keywords = {Mathematics - Numerical Analysis},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Cichocki et al\\2016\\Cichocki et al_2016_Low-Rank Tensor Networks for Dimensionality Reduction and Large-Scale.pdf;C\:\\Users\\selinederooij\\Zotero\\storage\\4HEC2BWL\\1609.html}
}

@article{cichocki2016TensorNetworksDimensionalitya,
  title = {Tensor {{Networks}} for {{Dimensionality Reduction}} and {{Large-scale Optimization}}: {{Part}} 1 {{Low-Rank Tensor Decompositions}}},
  shorttitle = {Tensor {{Networks}} for {{Dimensionality Reduction}} and {{Large-scale Optimization}}},
  author = {Cichocki, Andrzej and Lee, Namgil and Oseledets, Ivan and Phan, Anh-Huy and Zhao, Qibin and Mandic, Danilo P.},
  date = {2016},
  journaltitle = {Foundations and Trends® in Machine Learning},
  shortjournal = {FNT in Machine Learning},
  volume = {9},
  number = {4-5},
  pages = {249--429},
  issn = {1935-8237, 1935-8245},
  doi = {10.1561/2200000059},
  url = {http://www.nowpublishers.com/article/Details/MAL-059},
  urldate = {2022-07-15},
  langid = {english},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\7USKSGFI\\Cichocki et al. - 2016 - Tensor Networks for Dimensionality Reduction and L.pdf}
}

@article{cichocki2017TensorNetworksDimensionalitya,
  title = {Tensor {{Networks}} for {{Dimensionality Reduction}} and {{Large-scale Optimization}}: {{Part}} 2 {{Applications}} and {{Future Perspectives}}},
  shorttitle = {Tensor {{Networks}} for {{Dimensionality Reduction}} and {{Large-scale Optimization}}},
  author = {Cichocki, Andrzej and Lee, Namgil and Oseledets, Ivan and Phan, Anh-Huy and Zhao, Qibin and Sugiyama, Masashi and Mandic, Danilo P.},
  date = {2017},
  journaltitle = {Foundations and Trends® in Machine Learning},
  shortjournal = {FNT in Machine Learning},
  volume = {9},
  number = {6},
  pages = {249--429},
  issn = {1935-8237, 1935-8245},
  doi = {10.1561/2200000067},
  url = {http://www.nowpublishers.com/article/Details/MAL-067},
  urldate = {2022-03-22},
  langid = {english},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\4TEG4X29\\Cichocki et al. - 2017 - Tensor Networks for Dimensionality Reduction and L.pdf}
}

@online{ClusterbasedOversamplingAlgorithm,
  title = {A Cluster-Based Oversampling Algorithm Combining {{SMOTE}} and k-Means for Imbalanced Medical Data | {{Elsevier Enhanced Reader}}},
  doi = {10.1016/j.ins.2021.02.056},
  url = {https://reader.elsevier.com/reader/sd/pii/S0020025521001985?token=7483BAD1D81B26CC6CA4F35E73AD32413B0D87163F2D5C506E8D91C917EAD91AC48C531C24B6CE7D1E5F9EA0ABD57569&originRegion=eu-west-1&originCreation=20220314145206},
  urldate = {2022-03-14},
  langid = {english},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\VGTJRTWQ\\S0020025521001985.html}
}

@article{comon2014TensorsBriefIntroduction,
  title = {Tensors : {{A}} Brief Introduction},
  shorttitle = {Tensors},
  author = {Comon, Pierre},
  date = {2014-05},
  journaltitle = {IEEE Signal Processing Magazine},
  shortjournal = {IEEE Signal Process. Mag.},
  volume = {31},
  number = {3},
  pages = {44--53},
  issn = {1053-5888},
  doi = {10.1109/MSP.2014.2298533},
  url = {http://ieeexplore.ieee.org/document/6784037/},
  urldate = {2022-03-08},
  abstract = {Tensor decompositions are at the core of many Blind Source Separation (BSS) algorithms, either explicitly or implicitly. In particular, the Canonical Polyadic (CP) tensor decomposition plays a central role in identification of underdetermined mixtures. Despite some similarities, CP and Singular Value Decomposition (SVD) are quite different. More generally, tensors and matrices enjoy different properties, as pointed out in this brief introduction.},
  langid = {english},
  keywords = {read_nonote},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\S5UAVIXM\\Comon - 2014 - Tensors  A brief introduction.pdf}
}

@article{cook2013PredictionSeizureLikelihood,
  title = {Prediction of Seizure Likelihood with a Long-Term, Implanted Seizure Advisory System in Patients with Drug-Resistant Epilepsy: A First-in-Man Study},
  shorttitle = {Prediction of Seizure Likelihood with a Long-Term, Implanted Seizure Advisory System in Patients with Drug-Resistant Epilepsy},
  author = {Cook, Mark J and O'Brien, Terence J and Berkovic, Samuel F and Murphy, Michael and Morokoff, Andrew and Fabinyi, Gavin and D'Souza, Wendyl and Yerra, Raju and Archer, John and Litewka, Lucas and Hosking, Sean and Lightfoot, Paul and Ruedebusch, Vanessa and Sheffield, W Douglas and Snyder, David and Leyde, Kent and Himes, David},
  date = {2013-06},
  journaltitle = {The Lancet Neurology},
  shortjournal = {The Lancet Neurology},
  volume = {12},
  number = {6},
  pages = {563--571},
  issn = {14744422},
  doi = {10.1016/S1474-4422(13)70075-9},
  url = {https://linkinghub.elsevier.com/retrieve/pii/S1474442213700759},
  urldate = {2022-03-08},
  abstract = {Background Seizure prediction would be clinically useful in patients with epilepsy and could improve safety, increase independence, and allow acute treatment. We did a multicentre clinical feasibility study to assess the safety and efficacy of a long-term implanted seizure advisory system designed to predict seizure likelihood and quantify seizures in adults with drug-resistant focal seizures.},
  langid = {english},
  keywords = {unread},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\M42SLEBP\\Cook et al. - 2013 - Prediction of seizure likelihood with a long-term,.pdf}
}

@article{craik2019DeepLearningElectroencephalogram,
  title = {Deep Learning for Electroencephalogram ({{EEG}}) Classification Tasks: A Review},
  shorttitle = {Deep Learning for Electroencephalogram ({{EEG}}) Classification Tasks},
  author = {Craik, Alexander and He, Yongtian and Contreras-Vidal, Jose L.},
  date = {2019-04},
  journaltitle = {Journal of Neural Engineering},
  shortjournal = {J. Neural Eng.},
  volume = {16},
  number = {3},
  pages = {031001},
  publisher = {{IOP Publishing}},
  issn = {1741-2552},
  doi = {10.1088/1741-2552/ab0ab5},
  url = {https://doi.org/10.1088/1741-2552/ab0ab5},
  urldate = {2022-07-05},
  abstract = {Objective. Electroencephalography (EEG) analysis has been an important tool in neuroscience with applications in neuroscience, neural engineering (e.g. Brain–computer interfaces, BCI’s), and even commercial applications. Many of the analytical tools used in EEG studies have used machine learning to uncover relevant information for neural classification and neuroimaging. Recently, the availability of large EEG data sets and advances in machine learning have both led to the deployment of deep learning architectures, especially in the analysis of EEG signals and in understanding the information it may contain for brain functionality. The robust automatic classification of these signals is an important step towards making the use of EEG more practical in many applications and less reliant on trained professionals. Towards this goal, a systematic review of the literature on deep learning applications to EEG classification was performed to address the following critical questions: (1) Which EEG classification tasks have been explored with deep learning? (2) What input formulations have been used for training the deep networks? (3) Are there specific deep learning network structures suitable for specific types of tasks? Approach. A systematic literature review of EEG classification using deep learning was performed on Web of Science and PubMed databases, resulting in 90 identified studies. Those studies were analyzed based on type of task, EEG preprocessing methods, input type, and deep learning architecture. Main results. For EEG classification tasks, convolutional neural networks, recurrent neural networks, deep belief networks outperform stacked auto-encoders and multi-layer perceptron neural networks in classification accuracy. The tasks that used deep learning fell into five general groups: emotion recognition, motor imagery, mental workload, seizure detection, event related potential detection, and sleep scoring. For each type of task, we describe the specific input formulation, major characteristics, and end classifier recommendations found through this review. Significance. This review summarizes the current practices and performance outcomes in the use of deep learning for EEG classification. Practical suggestions on the selection of many hyperparameters are provided in the hope that they will promote or guide the deployment of deep learning to EEG datasets in future research.},
  langid = {english},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Craik et al\\2019\\Craik et al_2019_Deep learning for electroencephalogram (EEG) classification tasks.pdf}
}

@article{currey2019ClassificationContinuousWavelet,
  title = {A Classification of Continuous Wavelet Transforms in Dimension Three},
  author = {Currey, Bradley and Führ, Hartmut and Oussa, Vignon},
  date = {2019-05-01},
  journaltitle = {Applied and Computational Harmonic Analysis},
  shortjournal = {Applied and Computational Harmonic Analysis},
  volume = {46},
  number = {3},
  pages = {500--543},
  issn = {1063-5203},
  doi = {10.1016/j.acha.2017.06.003},
  url = {https://www.sciencedirect.com/science/article/pii/S1063520317300568},
  urldate = {2022-03-16},
  abstract = {This paper presents a full catalogue, up to conjugacy and subgroups of finite index, of all matrix groups H},
  langid = {english},
  keywords = {Atomic decomposition,Continuous wavelet,Coorbit space,Irreducibly admissible matrix group,unread,Wiener amalgam space},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Currey et al\\2019\\Currey et al_2019_A classification of continuous wavelet transforms in dimension three.pdf;C\:\\Users\\selinederooij\\Zotero\\storage\\5Y73ZH82\\S1063520317300568.html}
}

@article{delathauwer2000MultilinearSingularValue,
  title = {A {{Multilinear Singular Value Decomposition}}},
  author = {De Lathauwer, Lieven and De Moor, Bart and Vandewalle, Joos},
  date = {2000-01},
  journaltitle = {SIAM Journal on Matrix Analysis and Applications},
  shortjournal = {SIAM J. Matrix Anal. \& Appl.},
  volume = {21},
  number = {4},
  pages = {1253--1278},
  issn = {0895-4798, 1095-7162},
  doi = {10.1137/S0895479896305696},
  url = {http://epubs.siam.org/doi/10.1137/S0895479896305696},
  urldate = {2022-03-14},
  abstract = {We discuss a multilinear generalization of the singular value decomposition. There is a strong analogy between several properties of the matrix and the higher-order tensor decomposition; uniqueness, link with the matrix eigenvalue decomposition, first-order perturbation effects, etc., are analyzed. We investigate how tensor symmetries affect the decomposition and propose a multilinear generalization of the symmetric eigenvalue decomposition for pair-wise symmetric tensors.},
  langid = {english},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\ZITTSAZK\\De Lathauwer et al. - 2000 - A Multilinear Singular Value Decomposition.pdf}
}

@article{delathauwer2008DecompositionsHigherOrderTensor,
  title = {Decompositions of a {{Higher-Order Tensor}} in {{Block Terms}}—{{Part II}}: {{Definitions}} and {{Uniqueness}}},
  shorttitle = {Decompositions of a {{Higher-Order Tensor}} in {{Block Terms}}—{{Part II}}},
  author = {De Lathauwer, Lieven},
  date = {2008-01},
  journaltitle = {SIAM Journal on Matrix Analysis and Applications},
  shortjournal = {SIAM J. Matrix Anal. \& Appl.},
  volume = {30},
  number = {3},
  pages = {1033--1066},
  issn = {0895-4798, 1095-7162},
  doi = {10.1137/070690729},
  url = {http://epubs.siam.org/doi/10.1137/070690729},
  urldate = {2022-03-08},
  abstract = {In this paper we introduce a new class of tensor decompositions. Intuitively, we decompose a given tensor block into blocks of smaller size, where the size is characterized by a set of mode-n ranks. We study different types of such decompositions. For each type we derive conditions under which essential uniqueness is guaranteed. The parallel factor decomposition and Tucker’s decomposition can be considered as special cases in the new framework. The paper sheds new light on fundamental aspects of tensor algebra.},
  langid = {english},
  keywords = {read_nonote},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\LLUUW4ZA\\De Lathauwer - 2008 - Decompositions of a Higher-Order Tensor in Block T.pdf}
}

@article{douzas2018ImprovingImbalancedLearning,
  title = {Improving Imbalanced Learning through a Heuristic Oversampling Method Based on K-Means and {{SMOTE}}},
  author = {Douzas, Georgios and Bacao, Fernando and Last, Felix},
  date = {2018-10-01},
  journaltitle = {Information Sciences},
  shortjournal = {Information Sciences},
  volume = {465},
  pages = {1--20},
  issn = {0020-0255},
  doi = {10.1016/j.ins.2018.06.056},
  url = {https://www.sciencedirect.com/science/article/pii/S0020025518304997},
  urldate = {2022-03-16},
  abstract = {Learning from class-imbalanced data continues to be a common and challenging problem in supervised learning as standard classification algorithms are designed to handle balanced class distributions. While different strategies exist to tackle this problem, methods which generate artificial data to achieve a balanced class distribution are more versatile than modifications to the classification algorithm. Such techniques, called oversamplers, modify the training data, allowing any classifier to be used with class-imbalanced datasets. Many algorithms have been proposed for this task, but most are complex and tend to generate unnecessary noise. This work presents a simple and effective oversampling method based on k-means clustering and SMOTE (synthetic minority oversampling technique), which avoids the generation of noise and effectively overcomes imbalances between and within classes. Empirical results of extensive experiments with 90 datasets show that training data oversampled with the proposed method improves classification results. Moreover, k-means SMOTE consistently outperforms other popular oversampling methods. An implementation11The implementation of k-means SMOTE can be found at https://github.com/felix-last/kmeans\_smote. is made available in the Python programming language.},
  langid = {english},
  keywords = {Class-imbalanced learning,Classification,Clustering,Oversampling,Supervised learning,Within-class imbalance},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Douzas et al\\2018\\Douzas et al_2018_Improving imbalanced learning through a heuristic oversampling method based on.pdf;C\:\\Users\\selinederooij\\Zotero\\storage\\3R7JFZNI\\S0020025518304997.html}
}

@article{duarte2017EmpiricalComparisonCrossvalidation,
  title = {Empirical Comparison of Cross-Validation and Internal Metrics for Tuning {{SVM}} Hyperparameters},
  author = {Duarte, Edson and Wainer, Jacques},
  date = {2017-03-01},
  journaltitle = {Pattern Recognition Letters},
  shortjournal = {Pattern Recognition Letters},
  volume = {88},
  pages = {6--11},
  issn = {0167-8655},
  doi = {10.1016/j.patrec.2017.01.007},
  url = {https://www.sciencedirect.com/science/article/pii/S0167865517300077},
  urldate = {2022-03-09},
  abstract = {Hyperparameter tuning is a mandatory step for building a support vector machine classifier. In this work, we study some methods based on metrics of the training set itself, and not the performance of the classifier on a different test set - the usual cross-validation approach. We compare cross-validation (5-fold) with Xi-alpha, radius-margin bound, generalized approximate cross validation, maximum discrepancy and distance between two classes on 110 public binary data sets. Cross validation is the method that resulted in the best selection of the hyper-parameters, but it is also the method with one of the highest execution time. Distance between two classes (DBTC) is the fastest and the second best ranked method. We discuss that DBTC is a reasonable alternative to cross validation when training/hyperparameter-selection times are an issue and that the loss in accuracy when using DBTC is reasonably small.},
  langid = {english},
  keywords = {Cross validation,Hyper-parameter tuning,Internal metrics,Model selection,SVM},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Duarte_Wainer\\2017\\Duarte_Wainer_2017_Empirical comparison of cross-validation and internal metrics for tuning SVM.pdf;C\:\\Users\\selinederooij\\Zotero\\storage\\KUEPRXW8\\S0167865517300077.html}
}

@book{eijkhout2022IntroductionHighPerformance,
  title = {Introduction to {{High Performance Scientific Computing}}: {{The Art}} of {{HPC}}},
  author = {Eijkhout, Victor and Chow, Edmond and van de Geijn, Robert},
  date = {2022-07-05},
  edition = {3},
  volume = {1},
  url = {https://bitbucket.org/VictorEijkhout/scientific-computing-public/},
  langid = {english},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\JSQ9VISI\\Eijkhout - 3rd edition 2022, formatted July 5, 2022 Book and .pdf}
}

@article{ephraim2002HiddenMarkovProcesses,
  title = {Hidden {{Markov}} Processes},
  author = {Ephraim, Y. and Merhav, N.},
  date = {2002-06},
  journaltitle = {IEEE Transactions on Information Theory},
  volume = {48},
  number = {6},
  pages = {1518--1569},
  issn = {1557-9654},
  doi = {10.1109/TIT.2002.1003838},
  abstract = {An overview of statistical and information-theoretic aspects of hidden Markov processes (HMPs) is presented. An HMP is a discrete-time finite-state homogeneous Markov chain observed through a discrete-time memoryless invariant channel. In recent years, the work of Baum and Petrie (1966) on finite-state finite-alphabet HMPs was expanded to HMPs with finite as well as continuous state spaces and a general alphabet. In particular, statistical properties and ergodic theorems for relative entropy densities of HMPs were developed. Consistency and asymptotic normality of the maximum-likelihood (ML) parameter estimator were proved under some mild conditions. Similar results were established for switching autoregressive processes. These processes generalize HMPs. New algorithms were developed for estimating the state, parameter, and order of an HMP, for universal coding and classification of HMPs, and for universal decoding of hidden Markov channels. These and other related topics are reviewed.},
  eventtitle = {{{IEEE Transactions}} on {{Information Theory}}},
  keywords = {Autoregressive processes,Decoding,Discrete time systems,Encoding,Entropy,Hidden Markov models,Maximum likelihood estimation,Memoryless systems,Reviews,State estimation,Statistics},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Ephraim_Merhav\\2002\\Ephraim_Merhav_2002_Hidden Markov processes.pdf}
}

@article{faust2018DeepLearningHealthcare,
  title = {Deep Learning for Healthcare Applications Based on Physiological Signals: {{A}} Review},
  shorttitle = {Deep Learning for Healthcare Applications Based on Physiological Signals},
  author = {Faust, Oliver and Hagiwara, Yuki and Hong, Tan Jen and Lih, Oh Shu and Acharya, U Rajendra},
  date = {2018-07},
  journaltitle = {Computer Methods and Programs in Biomedicine},
  shortjournal = {Computer Methods and Programs in Biomedicine},
  volume = {161},
  pages = {1--13},
  issn = {01692607},
  doi = {10.1016/j.cmpb.2018.04.005},
  url = {https://linkinghub.elsevier.com/retrieve/pii/S0169260718301226},
  urldate = {2022-03-08},
  abstract = {Background and objective: We have cast the net into the ocean of knowledge to retrieve the latest scientific research on deep learning methods for physiological signals. We found 53 research papers on this topic, published from 01.01.2008 to 31.12.2017. Methods: An initial bibliometric analysis shows that the reviewed papers focused on Electromyogram(EMG), Electroencephalogram(EEG), Electrocardiogram(ECG), and Electrooculogram(EOG). These four categories were used to structure the subsequent content review. Results: During the content review, we understood that deep learning performs better for big and varied datasets than classic analysis and machine classification methods. Deep learning algorithms try to develop the model by using all the available input. Conclusions: This review paper depicts the application of various deep learning algorithms used till recently, but in future it will be used for more healthcare areas to improve the quality of diagnosis. © 2018 Elsevier B.V. All rights reserved.},
  langid = {english},
  keywords = {unread},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\JL96L4Y3\\Faust et al. - 2018 - Deep learning for healthcare applications based on.pdf}
}

@article{fisher2017OperationalClassificationSeizure,
  title = {Operational Classification of Seizure Types by the {{International League Against Epilepsy}}: {{Position Paper}} of the {{ILAE Commission}} for {{Classification}} and {{Terminology}}},
  shorttitle = {Operational Classification of Seizure Types by the {{International League Against Epilepsy}}},
  author = {Fisher, Robert S. and Cross, J. Helen and French, Jacqueline A. and Higurashi, Norimichi and Hirsch, Edouard and Jansen, Floor E. and Lagae, Lieven and Moshé, Solomon L. and Peltola, Jukka and Roulet Perez, Eliane and Scheffer, Ingrid E. and Zuberi, Sameer M.},
  date = {2017-04},
  journaltitle = {Epilepsia},
  shortjournal = {Epilepsia},
  volume = {58},
  number = {4},
  pages = {522--530},
  issn = {0013-9580, 1528-1167},
  doi = {10.1111/epi.13670},
  url = {https://onlinelibrary.wiley.com/doi/10.1111/epi.13670},
  urldate = {2022-03-08},
  abstract = {The International League Against Epilepsy (ILAE) presents a revised operational classification of seizure types. The purpose of such a revision is to recognize that some seizure types can have either a focal or generalized onset, to allow classification when the onset is unobserved, to include some missing seizure types, and to adopt more transparent names. Because current knowledge is insufficient to form a scientifically based classification, the 2017 Classification is operational (practical) and based on the 1981 Classification, extended in 2010. Changes include the following: (1) “partial” becomes “focal”; (2) awareness is used as a classifier of focal seizures; (3) the terms dyscognitive, simple partial, complex partial, psychic, and secondarily generalized are eliminated; (4) new focal seizure types include automatisms, behavior arrest, hyperkinetic, autonomic, cognitive, and emotional; (5) atonic, clonic, epileptic spasms, myoclonic, and tonic seizures can be of either focal or generalized onset; (6) focal to bilateral tonic–clonic seizure replaces secondarily generalized seizure; (7) new generalized seizure types are absence with eyelid myoclonia, myoclonic absence, myoclonic–atonic, myoclonic–tonic–clonic; and (8) seizures of unknown onset may have features that can still be classified. The new classification does not represent a fundamental change, but allows greater flexibility and transparency in naming seizure types.},
  langid = {english},
  keywords = {read_nonote},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\WSZIZDYG\\Fisher et al. - 2017 - Operational classification of seizure types by the.pdf}
}

@article{freestone2017ForwardlookingReviewSeizure,
  title = {A Forward-Looking Review of Seizure Prediction},
  author = {Freestone, Dean R. and Karoly, Philippa J. and Cook, Mark J.},
  date = {2017-04},
  journaltitle = {Current Opinion in Neurology},
  volume = {30},
  number = {2},
  pages = {167--173},
  issn = {1350-7540, 1473-6551},
  doi = {10.1097/WCO.0000000000000429},
  url = {https://journals.lww.com/00019052-201704000-00009},
  urldate = {2022-03-08},
  abstract = {We conclude the review with an exercise in wishful thinking, which asks what the ideal seizure prediction dataset would look like and how these data should be manipulated to maximize benefits for patients. The motivation for structuring the review in this way is to create a forward-looking, optimistic critique of the existing methodologies.},
  langid = {english},
  keywords = {read_nonote},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\5UIVUT27\\Freestone et al. - 2017 - A forward-looking review of seizure prediction.pdf}
}

@article{galar2012ReviewEnsemblesClass,
  title = {A {{Review}} on {{Ensembles}} for the {{Class Imbalance Problem}}: {{Bagging-}}, {{Boosting-}}, and {{Hybrid-Based Approaches}}},
  shorttitle = {A {{Review}} on {{Ensembles}} for the {{Class Imbalance Problem}}},
  author = {Galar, Mikel and Fernandez, Alberto and Barrenechea, Edurne and Bustince, Humberto and Herrera, Francisco},
  date = {2012-07},
  journaltitle = {IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews)},
  volume = {42},
  number = {4},
  pages = {463--484},
  issn = {1558-2442},
  doi = {10.1109/TSMCC.2011.2161285},
  abstract = {Classifier learning with data-sets that suffer from imbalanced class distributions is a challenging problem in data mining community. This issue occurs when the number of examples that represent one class is much lower than the ones of the other classes. Its presence in many real-world applications has brought along a growth of attention from researchers. In machine learning, the ensemble of classifiers are known to increase the accuracy of single classifiers by combining several of them, but neither of these learning techniques alone solve the class imbalance problem, to deal with this issue the ensemble learning algorithms have to be designed specifically. In this paper, our aim is to review the state of the art on ensemble techniques in the framework of imbalanced data-sets, with focus on two-class problems. We propose a taxonomy for ensemble-based methods to address the class imbalance where each proposal can be categorized depending on the inner ensemble methodology in which it is based. In addition, we develop a thorough empirical comparison by the consideration of the most significant published approaches, within the families of the taxonomy proposed, to show whether any of them makes a difference. This comparison has shown the good behavior of the simplest approaches which combine random undersampling techniques with bagging or boosting ensembles. In addition, the positive synergy between sampling techniques and bagging has stood out. Furthermore, our results show empirically that ensemble-based algorithms are worthwhile since they outperform the mere use of preprocessing techniques before learning the classifier, therefore justifying the increase of complexity by means of a significant enhancement of the results.},
  eventtitle = {{{IEEE Transactions}} on {{Systems}}, {{Man}}, and {{Cybernetics}}, {{Part C}} ({{Applications}} and {{Reviews}})},
  keywords = {Accuracy,Algorithm design and analysis,Bagging,boosting,class distribution,classification,ensembles,imbalanced data-sets,Learning systems,multiple classifier systems,Noise,Proposals,read,Training},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Galar et al\\2012\\Galar et al_2012_A Review on Ensembles for the Class Imbalance Problem.pdf;C\:\\Users\\selinederooij\\surfdrive\\notes\\PhD_Notes\\Literature\\Machine Learning\\@galar2012ReviewEnsemblesClass.md;C\:\\Users\\selinederooij\\Zotero\\storage\\JDVQDT34\\5978225.html}
}

@article{ghosh-dastidarNewSupervisedLearning2009a,
  title = {A New Supervised Learning Algorithm for Multiple Spiking Neural Networks with Application in Epilepsy and Seizure Detection},
  author = {Ghosh-Dastidar, Samanwoy and Adeli, Hojjat},
  date = {2009-12-01},
  journaltitle = {Neural Networks},
  shortjournal = {Neural Networks},
  volume = {22},
  number = {10},
  pages = {1419--1431},
  issn = {0893-6080},
  doi = {10.1016/j.neunet.2009.04.003},
  url = {https://www.sciencedirect.com/science/article/pii/S0893608009000653},
  urldate = {2022-03-07},
  abstract = {A new Multi-Spiking Neural Network (MuSpiNN) model is presented in which information from one neuron is transmitted to the next in the form of multiple spikes via multiple synapses. A new supervised learning algorithm, dubbed Multi-SpikeProp, is developed for training MuSpiNN. The model and learning algorithm employ the heuristic rules and optimum parameter values presented by the authors in a recent paper that improved the efficiency of the original single-spiking Spiking Neural Network (SNN) model by two orders of magnitude. The classification accuracies of MuSpiNN and Multi-SpikeProp are evaluated using three increasingly more complicated problems: the XOR problem, the Fisher iris classification problem, and the epilepsy and seizure detection (EEG classification) problem. It is observed that MuSpiNN learns the XOR problem in twice the number of epochs compared with the single-spiking SNN model but requires only one-fourth the number of synapses. For the iris and EEG classification problems, a modular architecture is employed to reduce each 3-class classification problem to three 2-class classification problems and improve the classification accuracy. For the complicated EEG classification problem a classification accuracy in the range of 90.7\%–94.8\% was achieved, which is significantly higher than the 82\% classification accuracy obtained using the single-spiking SNN with SpikeProp.},
  langid = {english},
  keywords = {EEG classification,Epilepsy,Spiking neural networks,Supervised learning,unread},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Ghosh-Dastidar_Adeli_2009_A new supervised learning algorithm for multiple spiking neural networks with.pdf;C\:\\Users\\selinederooij\\Zotero\\storage\\6U2SR5VF\\S0893608009000653.html}
}

@article{giannakis2018TopologyIdentificationLearning,
  title = {Topology {{Identification}} and {{Learning}} over {{Graphs}}: {{Accounting}} for {{Nonlinearities}} and {{Dynamics}}},
  shorttitle = {Topology {{Identification}} and {{Learning}} over {{Graphs}}},
  author = {Giannakis, Georgios B. and Shen, Yanning and Karanikolas, Georgios Vasileios},
  date = {2018-05},
  journaltitle = {Proceedings of the IEEE},
  volume = {106},
  number = {5},
  pages = {787--807},
  issn = {1558-2256},
  doi = {10.1109/JPROC.2018.2804318},
  abstract = {Identifying graph topologies as well as processes evolving over graphs emerge in various applications involving gene-regulatory, brain, power, and social networks, to name a few. Key graph-aware learning tasks include regression, classification, subspace clustering, anomaly identification, interpolation, extrapolation, and dimensionality reduction. Scalable approaches to deal with such high-dimensional tasks experience a paradigm shift to address the unique modeling and computational challenges associated with data-driven sciences. Albeit simple and tractable, linear time-invariant models are limited since they are incapable of handling generally evolving topologies, as well as nonlinear and dynamic dependencies between nodal processes. To this end, the main goal of this paper is to outline overarching advances, and develop a principled framework to capture nonlinearities through kernels, which are judiciously chosen from a preselected dictionary to optimally fit the data. The framework encompasses and leverages (non) linear counterparts of partial correlation and partial Granger causality, as well as (non)linear structural equations and vector autoregressions, along with attributes such as low rank, sparsity, and smoothness to capture even directional dependencies with abrupt change points, as well as time-evolving processes over possibly time-evolving topologies. The overarching approach inherits the versatility and generality of kernel-based methods, and lends itself to batch and computationally affordable online learning algorithms, which include novel Kalman filters over graphs. Real data experiments highlight the impact of the nonlinear and dynamic models on consumer and financial networks, as well as gene-regulatory and functional connectivity brain networks, where connectivity patterns revealed exhibit discernible differences relative to existing approaches.},
  eventtitle = {Proceedings of the {{IEEE}}},
  keywords = {Brain modeling,Dimensionality reduction,Graph theory,Kernel-based models,Network topology,network topology inference,nonlinear modeling,Principal component analysis,Social network services,Task analysis,time-varying networks,unread},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Giannakis et al\\2018\\Giannakis et al_2018_Topology Identification and Learning over Graphs.pdf;C\:\\Users\\selinederooij\\Zotero\\storage\\44VRW6K2\\8347160.html}
}

@article{gomez2020AutomaticSeizureDetection,
  title = {Automatic Seizure Detection Based on Imaged-{{EEG}} Signals through Fully Convolutional Networks},
  author = {Gómez, Catalina and Arbeláez, Pablo and Navarrete, Miguel and Alvarado-Rojas, Catalina and Le Van Quyen, Michel and Valderrama, Mario},
  date = {2020-12},
  journaltitle = {Scientific Reports},
  shortjournal = {Sci Rep},
  volume = {10},
  number = {1},
  pages = {21833},
  issn = {2045-2322},
  doi = {10.1038/s41598-020-78784-3},
  url = {http://www.nature.com/articles/s41598-020-78784-3},
  urldate = {2022-03-08},
  abstract = {Abstract             Seizure detection is a routine process in epilepsy units requiring manual intervention of well-trained specialists. This process could be extensive, inefficient and time-consuming, especially for long term recordings. We proposed an automatic method to detect epileptic seizures using an imaged-EEG representation of brain signals. To accomplish this, we analyzed EEG signals from two different datasets: the CHB-MIT Scalp EEG database and the EPILEPSIAE project that includes scalp and intracranial recordings. We used fully convolutional neural networks to automatically detect seizures. For our best model, we reached average accuracy and specificity values of 99.3\% and 99.6\%, respectively, for the CHB-MIT dataset, and corresponding values of 98.0\% and 98.3\% for the EPILEPSIAE patients. For these patients, the inclusion of intracranial electrodes together with scalp ones increased the average accuracy and specificity values to 99.6\% and 58.3\%, respectively. Regarding the other metrics, our best model reached average precision of 62.7\%, recall of 58.3\%, F-measure of 59.0\% and AP of 54.5\% on the CHB-MIT recordings, and comparatively lowers performances for the EPILEPSIAE dataset. For both databases, the number of false alarms per hour reached values less than 0.5/h for 92\% of the CHB-MIT patients and less than 1.0/h for 80\% of the EPILEPSIAE patients. Compared to recent studies, our lightweight approach does not need any estimation of pre-selected features and demonstrates high performances with promising possibilities for the introduction of such automatic methods in the clinical practice.},
  langid = {english},
  keywords = {unread},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\ND9H55NZ\\Gómez et al. - 2020 - Automatic seizure detection based on imaged-EEG si.pdf}
}

@unpublished{grasedyck2013LiteratureSurveyLowrank,
  title = {A Literature Survey of Low-Rank Tensor Approximation Techniques},
  author = {Grasedyck, Lars and Kressner, Daniel and Tobler, Christine},
  date = {2013-02-28},
  eprint = {1302.7121},
  eprinttype = {arxiv},
  primaryclass = {quant-ph},
  url = {http://arxiv.org/abs/1302.7121},
  urldate = {2022-03-08},
  abstract = {During the last years, low-rank tensor approximation has been established as a new tool in scientific computing to address large-scale linear and multilinear algebra problems, which would be intractable by classical techniques. This survey attempts to give a literature overview of current developments in this area, with an emphasis on function-related tensors.},
  archiveprefix = {arXiv},
  langid = {english},
  keywords = {15A69 (Primary) 65F10; 65F15 (Secondary),Mathematics - Numerical Analysis,Quantum Physics,read_nonote},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\ZVZAPNBB\\Grasedyck et al. - 2013 - A literature survey of low-rank tensor approximati.pdf}
}

@article{greene2007CombinationEEGECG,
  title = {Combination of {{EEG}} and {{ECG}} for Improved Automatic Neonatal Seizure Detection},
  author = {Greene, Barry R. and Boylan, Geraldine B. and Reilly, Richard B. and de Chazal, Philip and Connolly, Sean},
  options = {useprefix=true},
  date = {2007-06},
  journaltitle = {Clinical Neurophysiology},
  shortjournal = {Clinical Neurophysiology},
  volume = {118},
  number = {6},
  pages = {1348--1359},
  issn = {13882457},
  doi = {10.1016/j.clinph.2007.02.015},
  url = {https://linkinghub.elsevier.com/retrieve/pii/S1388245707000521},
  urldate = {2022-03-08},
  abstract = {Objective: Neonatal seizures are the most common central nervous system disorder in newborn infants. A system that could automatically detect the presence of seizures in neonates would be a significant advance facilitating timely medical intervention. Methods: A novel method is proposed for the robust detection of neonatal seizures through the combination of simultaneously-recorded electroencephalogram (EEG) and electrocardiogram (ECG). A patient-specific and a patient-independent system are considered, employing statistical classifier models. Results: Results for the signals combined are compared to results for each signal individually. For the patient-specific system, 617 of 633 (97.52\%) expert-labelled seizures were correctly detected with a false detection rate of 13.18\%. For the patient-independent system, 516 of 633 (81.44\%) expert-labelled seizures were correctly detected with a false detection rate of 28.57\%. Conclusions: A novel algorithm for neonatal seizure detection is proposed. The combination of an ECG-based classifier system with a novel multi-channel EEG-based classifier system has led to improved seizure detection performance. The algorithm was evaluated using a large data-set containing ECG and multi-channel EEG of realistic duration and quality.},
  langid = {english},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\FGKXLUEI\\Greene et al. - 2007 - Combination of EEG and ECG for improved automatic .pdf}
}

@article{greene2007CombinationEEGECGa,
  title = {Combination of {{EEG}} and {{ECG}} for Improved Automatic Neonatal Seizure Detection},
  author = {Greene, Barry R. and Boylan, Geraldine B. and Reilly, Richard B. and de Chazal, Philip and Connolly, Sean},
  options = {useprefix=true},
  date = {2007-06-01},
  journaltitle = {Clinical Neurophysiology},
  shortjournal = {Clinical Neurophysiology},
  volume = {118},
  number = {6},
  pages = {1348--1359},
  issn = {1388-2457},
  doi = {10.1016/j.clinph.2007.02.015},
  url = {https://www.sciencedirect.com/science/article/pii/S1388245707000521},
  urldate = {2022-05-16},
  abstract = {Objective Neonatal seizures are the most common central nervous system disorder in newborn infants. A system that could automatically detect the presence of seizures in neonates would be a significant advance facilitating timely medical intervention. Methods A novel method is proposed for the robust detection of neonatal seizures through the combination of simultaneously-recorded electroencephalogram (EEG) and electrocardiogram (ECG). A patient-specific and a patient-independent system are considered, employing statistical classifier models. Results Results for the signals combined are compared to results for each signal individually. For the patient-specific system, 617 of 633 (97.52\%) expert-labelled seizures were correctly detected with a false detection rate of 13.18\%. For the patient-independent system, 516 of 633 (81.44\%) expert-labelled seizures were correctly detected with a false detection rate of 28.57\%. Conclusions A novel algorithm for neonatal seizure detection is proposed. The combination of an ECG-based classifier system with a novel multi-channel EEG-based classifier system has led to improved seizure detection performance. The algorithm was evaluated using a large data-set containing ECG and multi-channel EEG of realistic duration and quality. Significance Analysis of simultaneously-recorded EEG and ECG represents a new approach in seizure detection research and the detection performance of the proposed system is a significant improvement on previous reported results for automated neonatal seizure detection.},
  langid = {english},
  keywords = {ECG,EEG,EKG,Neonatal seizure detection,read_nonote},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Greene et al\\2007\\Greene et al_2007_Combination of EEG and ECG for improved automatic neonatal seizure detection.pdf;C\:\\Users\\selinederooij\\surfdrive\\notes\\PhD_Notes\\Reading Notes\\@greene2007CombinationEEGECGa.md;C\:\\Users\\selinederooij\\surfdrive\\notes\\PhD_Notes\\Reading Notes\\@greene2007CombinationEEGECGa.md;C\:\\Users\\selinederooij\\surfdrive\\notes\\PhD_Notes\\Reading Notes\\@greene2007CombinationEEGECGa.md;C\:\\Users\\selinederooij\\Zotero\\storage\\WABJRG9M\\S1388245707000521.html}
}

@article{greene2008ComparisonQuantitativeEEG,
  title = {A Comparison of Quantitative {{EEG}} Features for Neonatal Seizure Detection},
  author = {Greene, B. R. and Faul, S. and Marnane, W. P. and Lightbody, G. and Korotchikova, I. and Boylan, G. B.},
  date = {2008-06-01},
  journaltitle = {Clinical Neurophysiology},
  shortjournal = {Clinical Neurophysiology},
  volume = {119},
  number = {6},
  pages = {1248--1261},
  issn = {1388-2457},
  doi = {10.1016/j.clinph.2008.02.001},
  url = {https://www.sciencedirect.com/science/article/pii/S1388245708001405},
  urldate = {2022-03-17},
  abstract = {Objective This study was undertaken to identify the best performing quantitative EEG features for neonatal seizures detection from a test set of 21. Methods Each feature was evaluated on 1-min, artefact-free segments of seizure and non-seizure neonatal EEG recordings. The potential utility of each feature for neonatal seizure detection was determined using receiver operating characteristic analysis and repeated measures t-tests. A performance estimate of the feature set was obtained using a cross-fold validation and combining all features together into a linear discriminant classifier model. Results Significant differences between seizure and non-seizure segments were found in 19 features for 17 patients. The best performing features for this application were the RMS amplitude, the line length and the number of local maxima and minima. An estimate of the patient independent classifier performance yielded a sensitivity of 81.08\% and specificity of 82.23\%. Conclusions The individual performances of 21 quantitative EEG features in detecting electrographic seizure in the neonate were compared and numerically quantified. Combining all features together into a classifier model led to superior performance than that provided by any individual feature taken alone. Significance The results documented in this study may provide a reference for the optimum quantitative EEG features to use in developing and enhancing neonatal seizure detection algorithms.},
  langid = {english},
  keywords = {EEG,Feature extraction,Neonatal seizure,Quantitative EEG,read},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Greene et al\\2008\\Greene et al_2008_A comparison of quantitative EEG features for neonatal seizure detection.pdf;C\:\\Users\\selinederooij\\surfdrive\\notes\\PhD_Notes\\Reading Notes\\@greene2008ComparisonQuantitativeEEG.md;C\:\\Users\\selinederooij\\Zotero\\storage\\TL73398M\\S1388245708001405.html}
}

@article{guo2016SupportTensorMachines,
  title = {Support {{Tensor Machines}} for {{Classification}} of {{Hyperspectral Remote Sensing Imagery}}},
  author = {Guo, Xian and Huang, Xin and Zhang, Lefei and Zhang, Liangpei and Plaza, Antonio and Benediktsson, Jón Atli},
  date = {2016-06},
  journaltitle = {IEEE Transactions on Geoscience and Remote Sensing},
  volume = {54},
  number = {6},
  pages = {3248--3264},
  issn = {1558-0644},
  doi = {10.1109/TGRS.2016.2514404},
  abstract = {In recent years, the support vector machines (SVMs) have been very successful in remote sensing image classification, particularly when dealing with high-dimensional data and limited training samples. Nevertheless, the vector-based feature alignment of the SVM can lead to an information loss in representation of hyperspectral images, which intrinsically have a tensor-based data structure. In this paper, a new multiclass support tensor machine (STM) is specifically developed for hyperspectral image classification. Our newly proposed STM processes the hyperspectral image as a data cube and then identifies the information classes in tensor space. The multiclass STM is developed from a set of binary STM classifiers using the one-against-one parallel strategy. As a part of our tensor-based processing chain, a multilinear principal component analysis (MPCA) is used for preprocessing, in order to reduce the tensorial data redundancy and, at the same time, preserve the tensorial structure information in sparse and high-order subspaces. As a result, the contributions of this work are twofold: a new multiclass STM model for hyperspectral image classification is developed, and a tensorial image interpretation framework is constructed, which provides a system consisting of tensor-based feature representation, feature extraction, and classification. Experiments with four hyperspectral data sets, covering agricultural and urban areas, are conducted to validate the effectiveness of the proposed framework. Our experimental results show that the proposed STM and MPCA-STM can achieve better results than traditional SVM-based classifiers.},
  eventtitle = {{{IEEE Transactions}} on {{Geoscience}} and {{Remote Sensing}}},
  keywords = {Algebra,Classification,dimensionality reduction,feature extraction,hyperspectral,Hyperspectral imaging,support tensor machine (STM),support vector machine (SVM),Support vector machines,Tensile stress,tensor,Training,unread},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Guo et al\\2016\\Guo et al_2016_Support Tensor Machines for Classification of Hyperspectral Remote Sensing.pdf;C\:\\Users\\selinederooij\\Zotero\\storage\\UA8ZZLX2\\7389377.html}
}

@article{haixiang2017LearningClassimbalancedData,
  title = {Learning from Class-Imbalanced Data: {{Review}} of Methods and Applications},
  shorttitle = {Learning from Class-Imbalanced Data},
  author = {Haixiang, Guo and Yijing, Li and Shang, Jennifer and Mingyun, Gu and Yuanyue, Huang and Bing, Gong},
  date = {2017-05-01},
  journaltitle = {Expert Systems with Applications},
  shortjournal = {Expert Systems with Applications},
  volume = {73},
  pages = {220--239},
  issn = {0957-4174},
  doi = {10.1016/j.eswa.2016.12.035},
  url = {https://www.sciencedirect.com/science/article/pii/S0957417416307175},
  urldate = {2022-03-08},
  abstract = {Rare events, especially those that could potentially negatively impact society, often require humans’ decision-making responses. Detecting rare events can be viewed as a prediction task in data mining and machine learning communities. As these events are rarely observed in daily life, the prediction task suffers from a lack of balanced data. In this paper, we provide an in depth review of rare event detection from an imbalanced learning perspective. Five hundred and seventeen related papers that have been published in the past decade were collected for the study. The initial statistics suggested that rare events detection and imbalanced learning are concerned across a wide range of research areas from management science to engineering. We reviewed all collected papers from both a technical and a practical point of view. Modeling methods discussed include techniques such as data preprocessing, classification algorithms and model evaluation. For applications, we first provide a comprehensive taxonomy of the existing application domains of imbalanced learning, and then we detail the applications for each category. Finally, some suggestions from the reviewed papers are incorporated with our experiences and judgments to offer further research directions for the imbalanced learning and rare event detection fields.},
  langid = {english},
  keywords = {Data mining,Imbalanced data,Machine learning,Rare events,unread},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Haixiang et al\\2017\\Haixiang et al_2017_Learning from class-imbalanced data.pdf;C\:\\Users\\selinederooij\\Zotero\\storage\\RECI4CAY\\S0957417416307175.html}
}

@article{hao2013LinearSupportHigherOrder,
  title = {A {{Linear Support Higher-Order Tensor Machine}} for {{Classification}}},
  author = {Hao, Zhifeng and He, Lifang and Chen, Bingqian and Yang, Xiaowei},
  date = {2013-07},
  journaltitle = {IEEE Transactions on Image Processing},
  volume = {22},
  number = {7},
  pages = {2911--2920},
  issn = {1941-0042},
  doi = {10.1109/TIP.2013.2253485},
  abstract = {There has been growing interest in developing more effective learning machines for tensor classification. At present, most of the existing learning machines, such as support tensor machine (STM), involve nonconvex optimization problems and need to resort to iterative techniques. Obviously, it is very time-consuming and may suffer from local minima. In order to overcome these two shortcomings, in this paper, we present a novel linear support higher-order tensor machine (SHTM) which integrates the merits of linear C-support vector machine (C-SVM) and tensor rank-one decomposition. Theoretically, SHTM is an extension of the linear C-SVM to tensor patterns. When the input patterns are vectors, SHTM degenerates into the standard C-SVM. A set of experiments is conducted on nine second-order face recognition datasets and three third-order gait recognition datasets to illustrate the performance of the proposed SHTM. The statistic test shows that compared with STM and C-SVM with the RBF kernel, SHTM provides significant performance gain in terms of test accuracy and training speed, especially in the case of higher-order tensors.},
  eventtitle = {{{IEEE Transactions}} on {{Image Processing}}},
  keywords = {Computational modeling,Educational institutions,Higher-order tensor,Optimization,printed,support tensor machine (STM),support vector machine (SVM),Support vector machines,Tensile stress,tensor classification,tensor rank-one decomposition,Training,unread,Vectors},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Hao et al\\2013\\Hao et al_2013_A Linear Support Higher-Order Tensor Machine for Classification.pdf;C\:\\Users\\selinederooij\\Zotero\\storage\\BHDLAVIQ\\6482624.html}
}

@book{he2013ImbalancedLearningFoundations,
  title = {Imbalanced {{Learning}}: {{Foundations}}, {{Algorithms}}, and {{Applications}}},
  shorttitle = {Imbalanced {{Learning}}},
  author = {He, Haibo and Ma, Yunqian},
  date = {2013-06-07},
  publisher = {{John Wiley \& Sons}},
  url = {https://ieeexplore-ieee-org.tudelft.idm.oclc.org/book/6542371},
  abstract = {The first book of its kind to review the current status and future direction of the exciting new branch of machine learning/data mining called imbalanced learning Imbalanced learning focuses on how an intelligent system can learn when it is provided with imbalanced data. Solving imbalanced learning problems is critical in numerous data-intensive networked systems, including surveillance, security, Internet, finance, biomedical, defense, and more. Due to the inherent complex characteristics of imbalanced data sets, learning from such data requires new understandings, principles, algorithms, and tools to transform vast amounts of raw data efficiently into information and knowledge representation. The first comprehensive look at this new branch of machine learning, this book offers a critical review of the problem of imbalanced learning, covering the state of the art in techniques, principles, and real-world applications. Featuring contributions from experts in both academia and industry, Imbalanced Learning: Foundations, Algorithms, and Applications provides chapter coverage on:  Foundations of Imbalanced Learning Imbalanced Datasets: From Sampling to Classifiers Ensemble Methods for Class Imbalance Learning Class Imbalance Learning Methods for Support Vector Machines Class Imbalance and Active Learning Nonstationary Stream Data Learning with Imbalanced Class Distribution Assessment Metrics for Imbalanced Learning  Imbalanced Learning: Foundations, Algorithms, and Applications will help scientists and engineers learn how to tackle the problem of learning from imbalanced datasets, and gain insight into current developments in the field as well as future research directions.},
  isbn = {978-1-118-64633-5},
  langid = {english},
  pagetotal = {218},
  keywords = {Technology & Engineering / Electrical,Technology & Engineering / Electronics / General}
}

@article{he2020SupportTensorMachine,
  title = {Support Tensor Machine with Dynamic Penalty Factors and Its Application to the Fault Diagnosis of Rotating Machinery with Unbalanced Data},
  author = {He, Zhiyi and Shao, Haidong and Cheng, Junsheng and Zhao, Xianzhu and Yang, Yu},
  date = {2020-07-01},
  journaltitle = {Mechanical Systems and Signal Processing},
  shortjournal = {Mechanical Systems and Signal Processing},
  volume = {141},
  pages = {106441},
  issn = {0888-3270},
  doi = {10.1016/j.ymssp.2019.106441},
  url = {https://www.sciencedirect.com/science/article/pii/S0888327019306624},
  urldate = {2022-03-09},
  abstract = {The fault diagnosis methods of rotating machinery based on machine learning have been developed in the past years, such as support vector machine (SVM) and convolutional neural networks (CNN). SVM just can be only used for the classification of the vector space in which the feature data extracted from raw signals are input data in vector form, so SVM loses its functions while the input feature data are high order tensors which can contain rich feature information of rotating machinery. Moreover, a large number of data are needed in CNN, but it’s hard to get large numbers of fault samples of rotating machinery under different conditions. Recently, a kind of tensor classifier called support tensor machines (STM) can solve the problems in the above methods. But when the input samples of STM are unbalanced data, the hyper-plane obtained by the training of STM may not be the optimal hyper-plane and it may reduce the overall classification rate. Therefore, in this paper, a novel tensor classifier called support tensor machine with dynamic penalty factors (DC-STM) is proposed and applied to the fault diagnosis of rotating machinery. In this method, for linear separable case, linear support tensor model with dynamic penalty factors (DC-LSTM) is proposed, which does not ignore the impact of rare support vectors of a class with less training samples on the structural risk. Subsequently, for nonlinear separable case, a tensor kernel function is introduced into DC-LSTM, and nonlinear support tensor model with dynamic penalty factors (DC-NSTM) is proposed. In order to verify the performance of DC-STM in unbalanced data classification, it is applied to fault classification of rotating machinery with unbalanced data. The experimental results show that the proposed method can achieve better classification results when the training samples of rotating machinery are unbalanced data.},
  langid = {english},
  keywords = {Dynamic penalty factors,Fault diagnosis,printed,read_nonote,Rotating machinery,Support tensor machine,Unbalanced data},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\He et al\\2020\\He et al_2020_Support tensor machine with dynamic penalty factors and its application to the.pdf;C\:\\Users\\selinederooij\\Zotero\\storage\\WFNZVIAY\\S0888327019306624.html}
}

@article{holtz2012AlternatingLinearScheme,
  title = {The {{Alternating Linear Scheme}} for {{Tensor Optimization}} in the {{Tensor Train Format}}},
  author = {Holtz, Sebastian and Rohwedder, Thorsten and Schneider, Reinhold},
  date = {2012-01},
  journaltitle = {SIAM Journal on Scientific Computing},
  shortjournal = {SIAM J. Sci. Comput.},
  volume = {34},
  number = {2},
  pages = {A683-A713},
  publisher = {{Society for Industrial and Applied Mathematics}},
  issn = {1064-8275},
  doi = {10.1137/100818893},
  url = {https://epubs.siam.org/doi/abs/10.1137/100818893},
  urldate = {2022-07-15},
  abstract = {Recent achievements in the field of tensor product approximation provide promising new formats for the representation of tensors in form of tree tensor networks. In contrast to the canonical r-term representation (CANDECOMP, PARAFAC), these new formats provide stable representations, while the amount of required data is only slightly larger. The tensor train (TT) format [SIAM J. Sci. Comput., 33 (2011), pp. 2295–2317], a simple special case of the hierarchical Tucker format [J. Fourier Anal. Appl., 5 (2009), p. 706], is a useful prototype for practical low-rank tensor representation. In this article, we show how optimization tasks can be treated in the TT format by a generalization of the well-known alternating least squares (ALS) algorithm and by a modified approach (MALS) that enables dynamical rank adaptation. A formulation of the component equations in terms of so-called retraction operators helps to show that many structural properties of the original problems transfer to the micro-iterations, giving what is to our knowledge the first stable generic algorithm for the treatment of optimization tasks in the tensor format. For the examples of linear equations and eigenvalue equations, we derive concrete working equations for the micro-iteration steps; numerical examples confirm the theoretical results concerning the stability of the TT decomposition and of ALS and MALS but also show that in some cases, high TT ranks are required during the iterative approximation of low-rank tensors, showing some potential of improvement.},
  keywords = {15A69,65K10,90C06,alternating least squares,density matrix renormalization group,eigenvalue problem,hierarchical tensors,high-dimensional systems,iterative methods for linear systems,matrix product states,optimization problem,tensor decompositions,tensor product approximation,tensor train,unread},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Holtz et al\\2012\\Holtz et al_2012_The Alternating Linear Scheme for Tensor Optimization in the Tensor Train Format.pdf}
}

@book{hu2019EEGSignalProcessing,
  title = {{{EEG Signal Processing}} and {{Feature Extraction}}},
  editor = {Hu, Li and Zhang, Zhiguo},
  date = {2019},
  publisher = {{Springer Singapore}},
  location = {{Singapore}},
  doi = {10.1007/978-981-13-9113-2},
  url = {http://link.springer.com/10.1007/978-981-13-9113-2},
  urldate = {2022-03-08},
  isbn = {9789811391125 9789811391132},
  langid = {english},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\XVZRHVL6\\Hu and Zhang - 2019 - EEG Signal Processing and Feature Extraction.pdf}
}

@thesis{hunyadiLearningStructuredEEG,
  title = {Learning from Structured {{EEG}} and {{fMRI}} Data Supporting the Diagnosis of Epilepsy},
  author = {Hunyadi, Borbála},
  langid = {english},
  keywords = {read_nonote},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\CTLHFJGC\\Hunyadi - Learning from structured EEG and fMRI data support.pdf}
}

@online{ImbalancedLearningFoundations,
  title = {Imbalanced Learning: Foundations, Algorithms, and Applications | Wiley},
  shorttitle = {Imbalanced Learning},
  url = {https://www.wiley.com/en-nl/Imbalanced+Learning%3A+Foundations%2C+Algorithms%2C+and+Applications-p-9781118646335},
  urldate = {2022-03-16},
  abstract = {The first book of its kind to review the current status and future direction of the exciting new branch of machine learning/data mining called imbalanced learning Imbalanced learning focuses on how an intelligent system can learn when it is provided with imbalanced data. Solving imbalanced learning problems is critical in numerous data-intensive networked systems, including surveillance, security, Internet, finance, biomedical, defense, and more. Due to the inherent complex characteristics of imbalanced data sets, learning from such data requires new understandings, principles, algorithms, and tools to transform vast amounts of raw data efficiently into information and knowledge representation. The first comprehensive look at this new branch of machine learning, this book offers a critical review of the problem of imbalanced learning, covering the state of the art in techniques, principles, and real-world applications. Featuring contributions from experts in both academia and industry, Imbalanced Learning: Foundations, Algorithms, and Applications provides chapter coverage on: Foundations of Imbalanced Learning Imbalanced Datasets: From Sampling to Classifiers Ensemble Methods for Class Imbalance Learning Class Imbalance Learning Methods for Support Vector Machines Class Imbalance and Active Learning Nonstationary Stream Data Learning with Imbalanced Class Distribution Assessment Metrics for Imbalanced Learning Imbalanced Learning: Foundations, Algorithms, and Applications will help scientists and engineers learn how to tackle the problem of learning from imbalanced datasets, and gain insight into current developments in the field as well as future research directions.},
  langid = {en-nl},
  organization = {{Wiley.com}},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\4UV3GAHP\\Imbalanced+Learning+Foundations,+Algorithms,+and+Applications-p-9781118646335.html}
}

@online{InboxTodoist,
  title = {Inbox: {{Todoist}}},
  shorttitle = {Inbox},
  url = {https://todoist.com/app/project/2280342375},
  urldate = {2022-03-16},
  langid = {english},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\C8GXZVIT\\2280342375.html}
}

@article{jackson2014NeurophysiologicalBasesEEG,
  title = {The Neurophysiological Bases of {{EEG}} and {{EEG}} Measurement: {{A}} Review for the Rest of Us},
  shorttitle = {The Neurophysiological Bases of {{EEG}} and {{EEG}} Measurement},
  author = {Jackson, Alice F. and Bolger, Donald J.},
  date = {2014},
  journaltitle = {Psychophysiology},
  volume = {51},
  number = {11},
  pages = {1061--1071},
  issn = {1469-8986},
  doi = {10.1111/psyp.12283},
  url = {https://onlinelibrary.wiley.com/doi/abs/10.1111/psyp.12283},
  urldate = {2022-04-26},
  abstract = {A thorough understanding of the EEG signal and its measurement is necessary to produce high quality data and to draw accurate conclusions from those data. However, publications that discuss relevant topics are written for divergent audiences with specific levels of expertise: explanations are either at an abstract level that leaves readers with a fuzzy understanding of the electrophysiology involved, or are at a technical level that requires mastery of the relevant physics to understand. A clear, comprehensive review of the origin and measurement of EEG that bridges these high and low levels of explanation fills a critical gap in the literature and is necessary for promoting better research practices and peer review. The present paper addresses the neurophysiological source of EEG, propagation of the EEG signal, technical aspects of EEG measurement, and implications for interpretation of EEG data.},
  langid = {english},
  keywords = {EEG/ERP,Methods,Signal propagation,unread},
  annotation = {\_eprint: https://onlinelibrary.wiley.com/doi/pdf/10.1111/psyp.12283},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Jackson_Bolger\\2014\\Jackson_Bolger_2014_The neurophysiological bases of EEG and EEG measurement.pdf;C\:\\Users\\selinederooij\\Zotero\\storage\\V5ZNJHX4\\psyp.html}
}

@article{jiang2017SeizureClassificationEEG,
  title = {Seizure {{Classification From EEG Signals Using Transfer Learning}}, {{Semi-Supervised Learning}} and {{TSK Fuzzy System}}},
  author = {Jiang, Yizhang and Wu, Dongrui and Deng, Zhaohong and Qian, Pengjiang and Wang, Jun and Wang, Guanjin and Chung, Fu-Lai and Choi, Kup-Sze and Wang, Shitong},
  date = {2017-12},
  journaltitle = {IEEE Transactions on Neural Systems and Rehabilitation Engineering},
  shortjournal = {IEEE Trans. Neural Syst. Rehabil. Eng.},
  volume = {25},
  number = {12},
  pages = {2270--2284},
  issn = {1534-4320, 1558-0210},
  doi = {10.1109/TNSRE.2017.2748388},
  url = {https://ieeexplore.ieee.org/document/8024036/},
  urldate = {2022-03-08},
  abstract = {Recognition of epileptic seizures from offline EEG signals is very important in clinical diagnosis of epilepsy. Compared with manual labeling of EEG signals by doctors, machine learning approaches can be faster and more consistent. However, the classification accuracy is usually not satisfactory for two main reasons: the distributions of the data used for training and testing may be different, and the amount of training data may not be enough. In addition, most machine learning approaches generate black-box models that are difficult to interpret. In this paper, we integrate transductive transfer learning, semisupervised learning and TSK fuzzy system to tackle these three problems. More specifically, we use transfer learning to reduce the discrepancy in data distribution between the training and testing data, employ semi-supervised learning to use the unlabeled testing data to remedy the shortage of training data, and adopt TSK fuzzy system to increase model interpretability. Two learning algorithms are proposed to train the system. Our experimental results show that the proposed approaches can achieve better performance than many state-of-the-art seizure classification algorithms.},
  langid = {english},
  keywords = {unread},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\YPMIZPLR\\Jiang et al. - 2017 - Seizure Classification From EEG Signals Using Tran.pdf}
}

@article{johansson2018WearableSensorsClinical,
  title = {Wearable Sensors for Clinical Applications in Epilepsy, {{Parkinson}}’s Disease, and Stroke: A Mixed-Methods Systematic Review},
  shorttitle = {Wearable Sensors for Clinical Applications in Epilepsy, {{Parkinson}}’s Disease, and Stroke},
  author = {Johansson, Dongni and Malmgren, Kristina and Alt Murphy, Margit},
  date = {2018-08},
  journaltitle = {Journal of Neurology},
  shortjournal = {J Neurol},
  volume = {265},
  number = {8},
  pages = {1740--1752},
  issn = {0340-5354, 1432-1459},
  doi = {10.1007/s00415-018-8786-y},
  url = {http://link.springer.com/10.1007/s00415-018-8786-y},
  urldate = {2022-03-08},
  abstract = {Objectives\hspace{0.6em} Wearable technology is increasingly used to monitor neurological disorders. The purpose of this systematic review was to synthesize knowledge from quantitative and qualitative clinical researches using wearable sensors in epilepsy, Parkinson’s disease (PD), and stroke. Methods\hspace{0.6em} A systematic literature search was conducted in PubMed and Scopus spanning from 1995 to January 2017. A synthesis of the main findings, reported adherence to wearables and missing data from quantitative studies, is provided. Clinimetric properties of measures derived from wearables in laboratory, free activities in hospital, and free-living environment were also evaluated. Qualitative thematic synthesis was conducted to explore user experiences and acceptance of wearables. Results\hspace{0.6em} In total, 56 studies (50 reporting quantitative and 6 reporting qualitative data) were included for data extraction and synthesis. Among studies reporting quantitative data, 5 were in epilepsy, 21 PD, and 24 studies in stroke. In epilepsy, wearables are used to detect and differentiate seizures in hospital settings. In PD, the focus is on quantification of cardinal motor symptoms and medication-evoked adverse symptoms in both laboratory and free-living environment. In stroke upper extremity activity, walking and physical activity have been studied in laboratory and during free activities. Three analytic themes emerged from thematic synthesis of studies reporting qualitative data: acceptable integration in daily life, lack of confidence in technology, and the need to consider individualization. Conclusions\hspace{0.6em} Wearables may provide information of clinical features of interest in epilepsy, PD and stroke, but knowledge regarding the clinical utility for supporting clinical decision making remains to be established.},
  langid = {english},
  keywords = {unread},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\XLEDFEJQ\\Johansson et al. - 2018 - Wearable sensors for clinical applications in epil.pdf}
}

@article{karoly2017CircadianProfileEpilepsy,
  title = {The Circadian Profile of Epilepsy Improves Seizure Forecasting},
  author = {Karoly, Philippa J and Ung, Hoameng and Grayden, David B and Kuhlmann, Levin and Leyde, Kent and Cook, Mark J and Freestone, Dean R},
  date = {2017-08-01},
  journaltitle = {Brain},
  volume = {140},
  number = {8},
  pages = {2169--2182},
  issn = {0006-8950, 1460-2156},
  doi = {10.1093/brain/awx173},
  url = {https://academic.oup.com/brain/article/140/8/2169/4032453},
  urldate = {2022-03-08},
  langid = {english},
  keywords = {read_nonote},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\5F9IGUUQ\\Karoly et al. - 2017 - The circadian profile of epilepsy improves seizure.pdf}
}

@article{khan2018FocalOnsetSeizure,
  title = {Focal {{Onset Seizure Prediction Using Convolutional Networks}}},
  author = {Khan, Haidar and Marcuse, Lara and Fields, Madeline and Swann, Kalina and Yener, Bülent},
  date = {2018-09},
  journaltitle = {IEEE Transactions on Biomedical Engineering},
  volume = {65},
  number = {9},
  pages = {2109--2118},
  issn = {1558-2531},
  doi = {10.1109/TBME.2017.2785401},
  abstract = {Objective: This paper investigates the hypothesis that focal seizures can be predicted using scalp electroencephalogram (EEG) data. Our first aim is to learn features that distinguish between the interictal and preictal regions. The second aim is to define a prediction horizon in which the prediction is as accurate and as early as possible, clearly two competing objectives. Methods: Convolutional filters on the wavelet transformation of the EEG signal are used to define and learn quantitative signatures for each period: interictal, preictal, and ictal. The optimal seizure prediction horizon is also learned from the data as opposed to making an a priori assumption. Results: Computational solutions to the optimization problem indicate a 10-min seizure prediction horizon. This result is verified by measuring Kullback-Leibler divergence on the distributions of the automatically extracted features. Conclusion: The results on the EEG database of 204 recordings demonstrate that (i) the preictal phase transition occurs approximately ten minutes before seizure onset, and (ii) the prediction results on the test set are promising, with a sensitivity of 87.8\% and a low false prediction rate of 0.142 FP/h. Our results significantly outperform a random predictor and other seizure prediction algorithms. Significance: We demonstrate that a robust set of features can be learned from scalp EEG that characterize the preictal state of focal seizures.},
  eventtitle = {{{IEEE Transactions}} on {{Biomedical Engineering}}},
  keywords = {Automatic feature extraction,Brain modeling,Convolution,convolutional neural networks,deep learning,Electroencephalography,Feature extraction,focal seizures,preictal period,printed,read_nonote,Scalp,scalp EEG,seizure prediction,Tensile stress,Wavelet transforms},
  annotation = {124 citations (Semantic Scholar/DOI) [2022-04-25]},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Khan et al\\2018\\Khan et al_2018_Focal Onset Seizure Prediction Using Convolutional Networks.pdf;C\:\\Users\\selinederooij\\Zotero\\storage\\AYML69JF\\8239676.html}
}

@inproceedings{kotsia2012HigherRankSupport,
  title = {Higher {{Rank Support Tensor Machines}}},
  booktitle = {Advances in {{Visual Computing}}},
  author = {Kotsia, Irene and Guo, Weiwei and Patras, Ioannis},
  editor = {Bebis, George and Boyle, Richard and Parvin, Bahram and Koracin, Darko and Fowlkes, Charless and Wang, Sen and Choi, Min-Hyung and Mantler, Stephan and Schulze, Jürgen and Acevedo, Daniel and Mueller, Klaus and Papka, Michael},
  date = {2012},
  series = {Lecture {{Notes}} in {{Computer Science}}},
  pages = {31--40},
  publisher = {{Springer}},
  location = {{Berlin, Heidelberg}},
  doi = {10.1007/978-3-642-33191-6_4},
  abstract = {This work addresses the two class classification problem within the tensor-based large margin classification paradigm. To this end, we formulate the higher rank Support Tensor Machines (STMs), in which the parameters defining the separating hyperplane form a tensor (tensorplane) that is constrained to be the sum of rank one tensors. The corresponding optimization problem is solved in an iterative manner utilizing the CANDECOMP/PARAFAC (CP) decomposition, where at each iteration the parameters corresponding to the projections along a single tensor mode are estimated by solving a typical Support Vector Machine (SVM)-type optimization problem. The efficiency of the proposed method is illustrated on the problems of gait and action recognition where we report results that improve, in some cases considerably, the state of the art.},
  isbn = {978-3-642-33191-6},
  langid = {english},
  keywords = {Action Recognition,Gait Recognition,Human Action Recognition,Machine Intelligence,Recognition Accuracy},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Kotsia et al\\2012\\Kotsia et al_2012_Higher Rank Support Tensor Machines.pdf}
}

@article{krawczyk2016LearningImbalancedData,
  title = {Learning from Imbalanced Data: Open Challenges and Future Directions},
  shorttitle = {Learning from Imbalanced Data},
  author = {Krawczyk, Bartosz},
  date = {2016-11-01},
  journaltitle = {Progress in Artificial Intelligence},
  shortjournal = {Prog Artif Intell},
  volume = {5},
  number = {4},
  pages = {221--232},
  issn = {2192-6360},
  doi = {10.1007/s13748-016-0094-0},
  url = {https://doi.org/10.1007/s13748-016-0094-0},
  urldate = {2022-03-08},
  abstract = {Despite more than two decades of continuous development learning from imbalanced data is still a focus of intense research. Starting as a problem of skewed distributions of binary tasks, this topic evolved way beyond this conception. With the expansion of machine learning and data mining, combined with the arrival of big data era, we have gained a deeper insight into the nature of imbalanced learning, while at the same time facing new emerging challenges. Data-level and algorithm-level methods are constantly being improved and hybrid approaches gain increasing popularity. Recent trends focus on analyzing not only the disproportion between classes, but also other difficulties embedded in the nature of data. New real-life problems motivate researchers to focus on computationally efficient, adaptive and real-time methods. This paper aims at discussing open issues and challenges that need to be addressed to further develop the field of imbalanced learning. Seven vital areas of research in this topic are identified, covering the full spectrum of learning from imbalanced data: classification, regression, clustering, data streams, big data analytics and applications, e.g., in social media and computer vision. This paper provides a discussion and suggestions concerning lines of future research for each of them.},
  langid = {english},
  keywords = {unread},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Krawczyk\\2016\\Krawczyk_2016_Learning from imbalanced data.pdf}
}

@inproceedings{kuhlmann2008CorrelationAnalysisSeizure,
  title = {Correlation Analysis of Seizure Detection Features},
  booktitle = {2008 {{International Conference}} on {{Intelligent Sensors}}, {{Sensor Networks}} and {{Information Processing}}},
  author = {Kuhlmann, L. and Cook, M. J. and Fuller, K. and Grayden, D. B. and Burkitt, A. N. and Mareels, I.M.Y.},
  date = {2008-12},
  pages = {309--314},
  publisher = {{IEEE}},
  location = {{Sydney, NSW, Australia}},
  doi = {10.1109/ISSNIP.2008.4762005},
  url = {https://ieeexplore.ieee.org/document/4762005/},
  urldate = {2022-05-24},
  abstract = {Automated seizure detection is important for speeding up epilepsy diagnosis or for controlling an implantable brain stimulator to avert seizures. Various features calculated from the electroencephalogram (EEG) can be used to detect seizures, and combining features can give superior detection performance. This paper investigates the correlation between seizure detection features in order to determine which ones should be combined for the purposes of seizure detection. Combinations of three features involving relative average amplitude, relative scale energy, coefficient of variation of amplitude, relative power, relative gradient and bounded variation tended to show the lowest correlations.},
  eventtitle = {2008 {{International Conference}} on {{Intelligent Sensors}}, {{Sensor Networks}} and {{Information Processing}}},
  isbn = {978-1-4244-3822-8},
  langid = {english},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\N8HDJHQF\\Kuhlmann et al. - 2008 - Correlation analysis of seizure detection features.pdf}
}

@article{kuhlmann2009SeizureDetectionUsinga,
  title = {Seizure {{Detection Using Seizure Probability Estimation}}: {{Comparison}} of {{Features Used}} to {{Detect Seizures}}},
  shorttitle = {Seizure {{Detection Using Seizure Probability Estimation}}},
  author = {Kuhlmann, Levin and Burkitt, Anthony N. and Cook, Mark J. and Fuller, Karen and Grayden, David B. and Seiderer, Linda and Mareels, Iven M. Y.},
  date = {2009-10-01},
  journaltitle = {Annals of Biomedical Engineering},
  shortjournal = {Ann Biomed Eng},
  volume = {37},
  number = {10},
  pages = {2129--2145},
  issn = {1573-9686},
  doi = {10.1007/s10439-009-9755-5},
  url = {https://doi.org/10.1007/s10439-009-9755-5},
  urldate = {2022-05-24},
  abstract = {This paper analyses seizure detection features and their combinations using a probability-based scalp EEG seizure detection framework developed by Marc Saab and Jean Gotman. Our method was evaluated on 525~h of data, including 88 seizures in 21 patients. The individual performances of the three features used by Saab and Gotman were compared to six alternative features, and combinations of these nine features were analyzed in order to find a superior detector. On a testing set with the combination of their three features, Saab and Gotman reported a sensitivity of 0.78, a false positive rate of 0.86/h, and a median detection delay of 9.8~s. Based on 10-fold cross-validation the testing performance of our implementation of their method achieved a sensitivity of 0.79, a false positive rate of 0.62/h, and a median detection delay of 21.3~s. A detector based on an alternative combination of features achieved sensitivity of 0.81, a false positive rate of 0.60/h, and a median detection delay of 16.9~s. By including filtering techniques, it was possible to achieve performance levels similar to Saab and Gotman using our implementation of their method, although this involved increases in detection delays. Of the seizure detection measures investigated, relative average amplitude, relative power, relative derivative, and coefficent of variation of amplitude provided the best performing combinations. These better-performing features can be employed together to make robust and reliable seizure detectors.},
  langid = {english},
  keywords = {EEG,Epilepsy,Seizure detection,Seizure onset},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Kuhlmann et al\\2009\\Kuhlmann et al_2009_Seizure Detection Using Seizure Probability Estimation.pdf}
}

@article{lemm2005SpatiospectralFiltersImproving,
  title = {Spatio-Spectral Filters for Improving the Classification of Single Trial {{EEG}}},
  author = {Lemm, S. and Blankertz, B. and Curio, G. and Muller, K.-R.},
  date = {2005-09},
  journaltitle = {IEEE Transactions on Biomedical Engineering},
  volume = {52},
  number = {9},
  pages = {1541--1548},
  issn = {1558-2531},
  doi = {10.1109/TBME.2005.851521},
  abstract = {Data recorded in electroencephalogram (EEG)-based brain-computer interface experiments is generally very noisy, nonstationary, and contaminated with artifacts that can deteriorate discrimination/classification methods. In this paper, we extend the common spatial pattern (CSP) algorithm with the aim to alleviate these adverse effects. In particular, we suggest an extension of CSP to the state space, which utilizes the method of time delay embedding. As we will show, this allows for individually tuned frequency filters at each electrode position and, thus, yields an improved and more robust machine learning procedure. The advantages of the proposed method over the original CSP method are verified in terms of an improved information transfer rate (bits per trial) on a set of EEG-recordings from experiments of imagined limb movements.},
  eventtitle = {{{IEEE Transactions}} on {{Biomedical Engineering}}},
  keywords = {BCI,Brain computer interfaces,classification,CSP,Data analysis,Electroencephalography,feature extraction,Feature extraction,Filters,Machine learning,Nonlinear distortion,Robustness,Signal processing algorithms,State-space methods},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Lemm et al\\2005\\Lemm et al_2005_Spatio-spectral filters for improving the classification of single trial EEG.pdf;C\:\\Users\\selinederooij\\Zotero\\storage\\NRS93F79\\1495698.html}
}

@article{liu2013ParameterEstimationControl,
  title = {Parameter Estimation and Control for a Neural Mass Model Based on the Unscented {{Kalman}} Filter},
  author = {Liu, Xian and Gao, Qing},
  date = {2013-10-10},
  journaltitle = {Physical Review E},
  shortjournal = {Phys. Rev. E},
  volume = {88},
  number = {4},
  pages = {042905},
  publisher = {{American Physical Society}},
  doi = {10.1103/PhysRevE.88.042905},
  url = {https://link.aps.org/doi/10.1103/PhysRevE.88.042905},
  urldate = {2022-03-21},
  abstract = {Recent progress in Kalman filters to estimate states and parameters in nonlinear systems has provided the possibility of applying such approaches to neural systems. We here apply the nonlinear method of unscented Kalman filters (UKFs) to observe states and estimate parameters in a neural mass model that can simulate distinct rhythms in electroencephalography (EEG) including dynamical evolution during epilepsy seizures. We demonstrate the efficiency of the UKF in estimating states and parameters. We also develop an UKF-based control strategy to modulate the dynamics of the neural mass model. In this strategy the UKF plays the role of observing states, and the control law is constructed via the estimated states. We demonstrate the feasibility of using such a strategy to suppress epileptiform spikes in the neural mass model.},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Liu_Gao\\2013\\Liu_Gao_2013_Parameter estimation and control for a neural mass model based on the unscented.pdf;C\:\\Users\\selinederooij\\Zotero\\storage\\YRTIN6WY\\PhysRevE.88.html}
}

@book{liu2022TensorsDataProcessing,
  title = {Tensors for Data Processing: Theory, Methods and Applications},
  shorttitle = {Tensors for Data Processing},
  author = {Liu, Yipeng},
  date = {2022},
  isbn = {978-0-12-824447-0},
  langid = {english},
  annotation = {OCLC: 1245656712},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\6IPY4KE8\\Liu - 2022 - Tensors for data processing theory, methods and a.pdf}
}

@article{logesparan2012OptimalFeaturesOnline,
  title = {Optimal Features for Online Seizure Detection},
  author = {Logesparan, Lojini and Casson, Alexander J. and Rodriguez-Villegas, Esther},
  date = {2012-07-01},
  journaltitle = {Medical \& Biological Engineering \& Computing},
  shortjournal = {Med Biol Eng Comput},
  volume = {50},
  number = {7},
  pages = {659--669},
  issn = {1741-0444},
  doi = {10.1007/s11517-012-0904-x},
  url = {https://doi.org/10.1007/s11517-012-0904-x},
  urldate = {2022-05-24},
  abstract = {This study identifies characteristic features in scalp EEG that simultaneously give the best discrimination between epileptic seizures and background EEG in minimally pre-processed scalp data; and have minimal computational complexity to be suitable for online, real-time analysis. The discriminative performance of 65 previously reported features has been evaluated in terms of sensitivity, specificity, area under the sensitivity–specificity curve (AUC), and relative computational complexity, on 47 seizures (split in 2,698 2~s sections) in over 172~h of scalp EEG from 24 adults. The best performing features are line length and relative power in the 12.5–25~Hz band. Relative power has a better seizure detection performance (AUC~=~0.83; line length AUC~=~0.77), but is calculated after the discrete wavelet transform and is thus more computationally complex. Hence, relative power achieves the best performance for offline detection, whilst line length would be preferable for online low complexity detection. These results, from the largest systematic study of seizure detection features, aid future researchers in selecting an optimal set of features when designing algorithms for both standard offline detection and new online low computational complexity detectors.},
  langid = {english},
  keywords = {EEG,Epilepsy,Feature,Online,Seizure detection,unread},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Logesparan et al\\2012\\Logesparan et al_2012_Optimal features for online seizure detection.pdf}
}

@online{LongShortTermMemory,
  title = {A {{Long Short-Term Memory}} Deep Learning Network for the Prediction of Epileptic Seizures Using {{EEG}} Signals | {{Elsevier Enhanced Reader}}},
  doi = {10.1016/j.compbiomed.2018.05.019},
  url = {https://reader.elsevier.com/reader/sd/pii/S001048251830132X?token=63EDE1AE0B85B15FE250BB4DB7342088DE6128BFEAF19017BFF883D81B9F23314FF81074B578FA5D7D1AB2191E9F5C71&originRegion=eu-west-1&originCreation=20220516144701},
  urldate = {2022-05-16},
  langid = {english},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\undefined\\undefined\\A Long Short-Term Memory deep learning network for the prediction of epileptic.pdf;C\:\\Users\\selinederooij\\Zotero\\storage\\QT7I5EYE\\S001048251830132X.html}
}

@article{lotteReviewClassificationAlgorithms2018,
  title = {A Review of Classification Algorithms for {{EEG-based}} Brain-Computer Interfaces: A 10 Year Update},
  shorttitle = {A Review of Classification Algorithms for {{EEG-based}} Brain-Computer Interfaces},
  author = {Lotte, F. and Bougrain, L. and Cichocki, A. and Clerc, M. and Congedo, M. and Rakotomamonjy, A. and Yger, F.},
  date = {2018-06},
  journaltitle = {Journal of Neural Engineering},
  shortjournal = {J Neural Eng},
  volume = {15},
  number = {3},
  eprint = {29488902},
  eprinttype = {pmid},
  pages = {031005},
  issn = {1741-2552},
  doi = {10.1088/1741-2552/aab2f2},
  abstract = {OBJECTIVE: Most current electroencephalography (EEG)-based brain-computer interfaces (BCIs) are based on machine learning algorithms. There is a large diversity of classifier types that are used in this field, as described in our 2007 review paper. Now, approximately ten years after this review publication, many new algorithms have been developed and tested to classify EEG signals in BCIs. The time is therefore ripe for an updated review of EEG classification algorithms for BCIs. APPROACH: We surveyed the BCI and machine learning literature from 2007 to 2017 to identify the new classification approaches that have been investigated to design BCIs. We synthesize these studies in order to present such algorithms, to report how they were used for BCIs, what were the outcomes, and to identify their pros and cons. MAIN RESULTS: We found that the recently designed classification algorithms for EEG-based BCIs can be divided into four main categories: adaptive classifiers, matrix and tensor classifiers, transfer learning and deep learning, plus a few other miscellaneous classifiers. Among these, adaptive classifiers were demonstrated to be generally superior to static ones, even with unsupervised adaptation. Transfer learning can also prove useful although the benefits of transfer learning remain unpredictable. Riemannian geometry-based methods have reached state-of-the-art performances on multiple BCI problems and deserve to be explored more thoroughly, along with tensor-based methods. Shrinkage linear discriminant analysis and random forests also appear particularly useful for small training samples settings. On the other hand, deep learning methods have not yet shown convincing improvement over state-of-the-art BCI methods. SIGNIFICANCE: This paper provides a comprehensive overview of the modern classification algorithms used in EEG-based BCIs, presents the principles of these methods and guidelines on when and how to use them. It also identifies a number of challenges to further advance EEG classification in BCI.},
  langid = {english},
  keywords = {1,Algorithms,Animals,Brain,Brain-Computer Interfaces,Deep Learning,Electroencephalography,Humans,read,Signal Processing; Computer-Assisted,Time Factors},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Lotte et al_2018_A review of classification algorithms for EEG-based brain-computer interfaces.pdf;C\:\\Users\\selinederooij\\surfdrive\\notes\\PhD_Notes\\Literature\\EEG classification (general)\\@lotteReviewClassificationAlgorithms2018.md}
}

@misc{lucassen2021TensorNetworkKalman,
  title = {Tensor {{Network Kalman Filtering}} for {{Large-Scale LS-SVMs}}},
  author = {Lucassen, Maximilian and Suykens, Johan A. K. and Batselier, Kim},
  date = {2021-10-26},
  number = {arXiv:2110.13501},
  eprint = {2110.13501},
  eprinttype = {arxiv},
  primaryclass = {cs, eess},
  publisher = {{arXiv}},
  doi = {10.48550/arXiv.2110.13501},
  url = {http://arxiv.org/abs/2110.13501},
  urldate = {2022-07-25},
  abstract = {Least squares support vector machines are a commonly used supervised learning method for nonlinear regression and classification. They can be implemented in either their primal or dual form. The latter requires solving a linear system, which can be advantageous as an explicit mapping of the data to a possibly infinite-dimensional feature space is avoided. However, for large-scale applications, current low-rank approximation methods can perform inadequately. For example, current methods are probabilistic due to their sampling procedures, and/or suffer from a poor trade-off between the ranks and approximation power. In this paper, a recursive Bayesian filtering framework based on tensor networks and the Kalman filter is presented to alleviate the demanding memory and computational complexities associated with solving large-scale dual problems. The proposed method is iterative, does not require explicit storage of the kernel matrix, and allows the formulation of early stopping conditions. Additionally, the framework yields confidence estimates of obtained models, unlike alternative methods. The performance is tested on two regression and three classification experiments, and compared to the Nystr\textbackslash "om and fixed size LS-SVM methods. Results show that our method can achieve high performance and is particularly useful when alternative methods are computationally infeasible due to a slowly decaying kernel matrix spectrum.},
  archiveprefix = {arXiv},
  keywords = {Computer Science - Machine Learning,Electrical Engineering and Systems Science - Systems and Control},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Lucassen et al\\2021\\Lucassen et al_2021_Tensor Network Kalman Filtering for Large-Scale LS-SVMs.pdf;C\:\\Users\\selinederooij\\Zotero\\storage\\USSG38CM\\2110.html}
}

@article{ma2021AutomaticDetectionSeizure,
  title = {The {{Automatic Detection}} of {{Seizure Based}} on {{Tensor Distance And Bayesian Linear Discriminant Analysis}}},
  author = {Ma, Delu and Yuan, Shasha and Shang, Junliang and Liu, Jinxing and Dai, Lingyun and Kong, Xiangzhen and Xu, Fangzhou},
  date = {2021-05},
  journaltitle = {International Journal of Neural Systems},
  shortjournal = {Int. J. Neur. Syst.},
  volume = {31},
  number = {05},
  pages = {2150006},
  publisher = {{World Scientific Publishing Co.}},
  issn = {0129-0657},
  doi = {10.1142/S0129065721500064},
  url = {https://www.worldscientific.com/doi/abs/10.1142/S0129065721500064},
  urldate = {2022-04-25},
  abstract = {Electroencephalogram (EEG) plays an important role in recording brain activity to diagnose epilepsy. However, it is not only laborious, but also not very cost effective for medical experts to manually identify the features on EEG. Therefore, automatic seizure detection in accordance with the EEG recordings is significant for the diagnosis and treatment of epilepsy. Here, a new method for detecting seizures using tensor distance (TD) is proposed. First, the time–frequency characteristics of EEG signals are obtained by wavelet transformation, and the tensor representation of EEG signals is then obtained. Tucker decomposition is used to obtain the principal components of the EEG tensor. After, the distances between different categories of EEG tensors are calculated as the EEG features. Finally, the TD features are classified through the Bayesian Linear Discriminant Analysis (Bayesian LDA) classifier. The performance of this method is measured by the sensitivity, specificity, and recognition accuracy. Results indicate 95.12\% sensitivity, 97.60\% specificity, 97.60\% recognition accuracy, and a false detection rate of 0.76 per hour in the invasive EEG dataset, which included 566.57 h of EEG recording data from 21 patients. Taken together, the results show that TD has a good detection effect for seizure classification and that this method has high computational speed and great potential for real-time diagnosis.},
  keywords = {Bayesian Linear Discriminant Analysis,Electroencephalogram,seizure detection,tensor distance,Tucker decomposition,unread},
  annotation = {3 citations (Semantic Scholar/DOI) [2022-04-25]},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Ma et al\\2021\\Ma et al_2021_The Automatic Detection of Seizure Based on Tensor Distance And Bayesian Linear.pdf}
}

@article{maturana2020CriticalSlowingBiomarker,
  title = {Critical Slowing down as a Biomarker for Seizure Susceptibility},
  author = {Maturana, Matias I. and Meisel, Christian and Dell, Katrina and Karoly, Philippa J. and D’Souza, Wendyl and Grayden, David B. and Burkitt, Anthony N. and Jiruska, Premysl and Kudlacek, Jan and Hlinka, Jaroslav and Cook, Mark J. and Kuhlmann, Levin and Freestone, Dean R.},
  date = {2020-12},
  journaltitle = {Nature Communications},
  shortjournal = {Nat Commun},
  volume = {11},
  number = {1},
  pages = {2172},
  issn = {2041-1723},
  doi = {10.1038/s41467-020-15908-3},
  url = {http://www.nature.com/articles/s41467-020-15908-3},
  urldate = {2022-03-08},
  abstract = {Abstract             The human brain has the capacity to rapidly change state, and in epilepsy these state changes can be catastrophic, resulting in loss of consciousness, injury and even death. Theoretical interpretations considering the brain as a dynamical system suggest that prior to a seizure, recorded brain signals may exhibit critical slowing down, a warning signal preceding many critical transitions in dynamical systems. Using long-term intracranial electroencephalography (iEEG) recordings from fourteen patients with focal epilepsy, we monitored key signatures of critical slowing down prior to seizures. The metrics used to detect critical slowing down fluctuated over temporally long scales (hours to days), longer than would be detectable in standard clinical evaluation settings. Seizure risk was associated with a combination of these signals together with epileptiform discharges. These results provide strong validation of theoretical models and demonstrate that critical slowing down is a reliable indicator that could be used in seizure forecasting algorithms.},
  langid = {english},
  keywords = {read_nonote},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\IUD7F3RF\\Maturana et al. - 2020 - Critical slowing down as a biomarker for seizure s.pdf}
}

@article{mohriFoundationsMachineLearning,
  title = {Foundations of {{Machine Learning}} (Second Edition)},
  author = {Mohri, Mehryar and Rostamizadeh, Afshin and Talwalkar, Ameet},
  pages = {505},
  langid = {english},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\M9AJKZV2\\Mohri et al. - Foundations of Machine Learning (second edition).pdf}
}

@article{nguyen2017HOKFHighOrder,
  title = {{{HOKF}}: {{High Order Kalman Filter}} for {{Epilepsy Forecasting Modeling}}},
  shorttitle = {{{HOKF}}},
  author = {Nguyen, Ngoc Anh Thi and Yang, Hyung-Jeong and Kim, Sunhee},
  date = {2017-08-01},
  journaltitle = {Biosystems},
  shortjournal = {Biosystems},
  volume = {158},
  pages = {57--67},
  issn = {0303-2647},
  doi = {10.1016/j.biosystems.2017.02.004},
  url = {https://www.sciencedirect.com/science/article/pii/S0303264716301678},
  urldate = {2022-03-21},
  abstract = {Epilepsy forecasting has been extensively studied using high-order time series obtained from scalp-recorded electroencephalography (EEG). An accurate seizure prediction system would not only help significantly improve patients’ quality of life, but would also facilitate new therapeutic strategies to manage epilepsy. This paper thus proposes an improved Kalman Filter (KF) algorithm to mine seizure forecasts from neural activity by modeling three properties in the high-order EEG time series: noise, temporal smoothness, and tensor structure. The proposed High-Order Kalman Filter (HOKF) is an extension of the standard Kalman filter, for which higher-order modeling is limited. The efficient dynamic of HOKF system preserves the tensor structure of the observations and latent states. As such, the proposed method offers two main advantages: (i) effectiveness with HOKF results in hidden variables that capture major evolving trends suitable to predict neural activity, even in the presence of missing values; and (ii) scalability in that the wall clock time of the HOKF is linear with respect to the number of time-slices of the sequence. The HOKF algorithm is examined in terms of its effectiveness and scalability by conducting forecasting and scalability experiments with a real epilepsy EEG dataset. The results of the simulation demonstrate the superiority of the proposed method over the original Kalman Filter and other existing methods.},
  langid = {english},
  keywords = {Electroencephalogram (EEG),Epilepsy forecasting,Expectation-maximization,Kalman filter,Multi-way arrays,Tucker tensor decomposition,unread},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Nguyen et al\\2017\\Nguyen et al_2017_HOKF.pdf;C\:\\Users\\selinederooij\\Zotero\\storage\\N2LF8DZL\\S0303264716301678.html}
}

@article{niknazar2020PerformanceAnalysisEEG,
  title = {Performance Analysis of {{EEG}} Seizure Detection Features},
  author = {Niknazar, Hamid and Mousavi, Seyed Reza and Niknazar, Mohammad and Mardanlou, Vahid and Coelho, Brett Nelson},
  date = {2020-11},
  journaltitle = {Epilepsy Research},
  shortjournal = {Epilepsy Res.},
  volume = {167},
  pages = {106483},
  publisher = {{Elsevier}},
  location = {{Amsterdam}},
  issn = {0920-1211},
  doi = {10.1016/j.eplepsyres.2020.106483},
  url = {https://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=DynamicDOIArticle&SrcApp=WOS&KeyAID=10.1016%2Fj.eplepsyres.2020.106483&DestApp=DOI&SrcAppSID=5DacMNcAZiO4ZnGIAYT&SrcJTitle=EPILEPSY+RESEARCH&DestDOIRegistrantName=Elsevier},
  urldate = {2022-03-17},
  abstract = {Automatic detection of epileptic seizures can serve as a valuable clinical tool which involves a more objective and computationally efficient method for the analysis of EEG data in order to generate increasingly accurate and reliable results. Automatic seizure detection is also an important component of closed-loop responsive cortical stimulation systems. The goal of this study is to evaluate EEG-based features recently proposed for seizure detection to discover the optimum ones for a reliable seizure detection system. We extracted seizure detection features from intracranial EEG signals that were recorded during invasive pre-surgical epilepsy monitoring of people with drug resistant focal epilepsy at the Epilepsy Center of the University Hospital of Freiburg. Features from time, frequency and phase space domains as well as similarity/dissimilarity features were considered. The performance of each feature was investigated using the statistical test ANOVA. Performance analysis was conducted separately on the recordings from the channels within the seizure-onset zone (SOZ-in) and the recordings from the channels outside the seizure-onset zone (SOZ-out). Similarity/dissimilarity features that measure dynamic properties of the EEG signal and the evolving phenomena of the seizures could significantly separate ictal (during seizure) states from pre-ictal (before seizure) states (p {$<$} 0.01). Among them, our proposed feature, Bhattacharyya-based dissimilarity index (BBDI), successfully passed Tukey's post-hoc test as well suggesting that it can distinguish both pre-ictal and post-ictal (after seizure) periods from ictal period. BBDI was further applied to detect epileptic seizures and achieved area under the curve of the receiver-operator characteristic (ROC) equal to 0.96 and 0.94 for SOZ-in and SOZ-out channels, respectively. No significant difference (p = 0.59) was observed in the performance of features between SOZ-in recordings and SOZ-out recordings. The discriminative value of EEG seizure detection features was determined by statistical tests. As a result, the best features to be selected for a reliable seizure detection system designed for people with drug-resistant focal epilepsy were suggested, which include similarity/dissimilarity indices.},
  langid = {english},
  keywords = {Drug resistant,EEG seizure detection features,epileptic seizures,Focal epilepsy,fractal dimension,identification,Intracranial EEG,Performance analysis,prediction,rats,read_nonote,surgery},
  annotation = {WOS:000587830900041},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Niknazar et al\\2020\\Niknazar et al_2020_Performance analysis of EEG seizure detection features.pdf}
}

@article{obeid2016TempleUniversityHospital,
  title = {The {{Temple University Hospital EEG Data Corpus}}},
  author = {Obeid, Iyad and Picone, Joseph},
  date = {2016-05-13},
  journaltitle = {Frontiers in Neuroscience},
  shortjournal = {Front. Neurosci.},
  volume = {10},
  issn = {1662-453X},
  doi = {10.3389/fnins.2016.00196},
  url = {http://journal.frontiersin.org/Article/10.3389/fnins.2016.00196/abstract},
  urldate = {2022-03-08},
  langid = {english},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\2XFXT6M7\\Obeid and Picone - 2016 - The Temple University Hospital EEG Data Corpus.pdf}
}

@book{obeid2021BiomedicalSignalProcessing,
  title = {Biomedical Signal Processing: Innovation and Applications},
  shorttitle = {Biomedical Signal Processing},
  author = {Obeid, Iyad and Selesnick, Ivan and Picone, Joseph},
  date = {2021},
  isbn = {978-3-030-67494-6},
  langid = {english},
  annotation = {OCLC: 1256409985},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\A3ICKL6A\\Obeid et al. - 2021 - Biomedical signal processing innovation and appli.pdf}
}

@article{oseledets2011DMRGApproachFast,
  title = {{{DMRG Approach}} to {{Fast Linear Algebra}} in the {{TT-Format}}},
  author = {Oseledets, Ivan},
  date = {2011-01-01},
  journaltitle = {Computational Methods in Applied Mathematics},
  volume = {11},
  number = {3},
  pages = {382--393},
  publisher = {{De Gruyter}},
  issn = {1609-9389},
  doi = {10.2478/cmam-2011-0021},
  url = {https://www.degruyter.com/document/doi/10.2478/cmam-2011-0021/html},
  urldate = {2022-07-19},
  abstract = {In this paper, the concept of the DMRG minimization scheme is extended to several important operations in the TT-format, like the matrix-by-vector product and the conversion from the canonical format to the TT-format. Fast algorithms are implemented and a stabilization scheme based on randomization is proposed. The comparison with the direct method is performed on a sequence of matrices and vectors coming as approximate solutions of linear systems in the TT-format. A generated example is provided to show that randomization is really needed in some cases. The matrices and vectors used are available from the author or at http://spring.inm.ras.ru/osel},
  langid = {english},
  keywords = {high-dimensional problem,SVD,Tensors,TT-format},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Oseledets\\2011\\Oseledets_2011_DMRG Approach to Fast Linear Algebra in the TT-Format.pdf}
}

@article{oseledets2011TensorTrainDecomposition,
  title = {Tensor-{{Train Decomposition}}},
  author = {Oseledets, I. V.},
  date = {2011-01},
  journaltitle = {SIAM Journal on Scientific Computing},
  shortjournal = {SIAM J. Sci. Comput.},
  volume = {33},
  number = {5},
  pages = {2295--2317},
  publisher = {{Society for Industrial and Applied Mathematics}},
  issn = {1064-8275},
  doi = {10.1137/090752286},
  url = {https://epubs.siam.org/doi/10.1137/090752286},
  urldate = {2022-05-06},
  abstract = {A simple nonrecursive form of the tensor decomposition in d dimensions is presented. It does not inherently suffer from the curse of dimensionality, it has asymptotically the same number of parameters as the canonical decomposition, but it is stable and its computation is based on low-rank approximation of auxiliary unfolding matrices. The new form gives a clear and convenient way to implement all basic operations efficiently. A fast rounding procedure is presented, as well as basic linear algebra operations. Examples showing the benefits of the decomposition are given, and the efficiency is demonstrated by the computation of the smallest eigenvalue of a 19-dimensional operator.},
  keywords = {15A23,15A69,65F99,high-dimensional problems,SVD,tensors,TT-format},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Oseledets\\2011\\Oseledets_2011_Tensor-Train Decomposition.pdf}
}

@article{osorio1998RealTimeAutomatedDetection,
  title = {Real-{{Time Automated Detection}} and {{Quantitative Analysis}} of {{Seizures}} and {{Short-Term Prediction}} of {{Clinical Onset}}},
  author = {Osorio, Ivan and Frei, Mark G. and Wilkinson, Steven B.},
  date = {1998},
  journaltitle = {Epilepsia},
  volume = {39},
  number = {6},
  pages = {615--627},
  issn = {1528-1167},
  doi = {10.1111/j.1528-1157.1998.tb01430.x},
  url = {https://onlinelibrary.wiley.com/doi/abs/10.1111/j.1528-1157.1998.tb01430.x},
  urldate = {2022-05-24},
  abstract = {Summary: Purpose: We describe an algorithm for rapid realtime detection, quantitation, localization of seizures, and prediction of their clinical onset. Methods: Advanced digital signal processing techniques used in time-frequency localization, image processing, and identification of time-varying stochastic systems were used to develop the algorithm, which operates in generic or adaptable “modes.” The “generic mode” was tested on (a) 125 partial seizures (each contained in a 10-min segment) involving the mesial temporal regions and recorded using depth electrodes from 16 subjects, and (b) 205 ten-minute segments of randomly selected interictal (nonseizure) data. The performance of the algorithm was compared with expert visual analysis, the current “gold standard.” Results: The generic algorithm achieved perfect sensitivity and specificity (no false-positive and no false-negative detections) over the entire data set. Seizure intensity, a novel measure that seems clinically relevant, ranged between 35.7 and 6129. Detection was sufficiently rapid to allow prediction of clinical onset in 92\% of seizures by a mean of 15.5 s. Conclusions: This algorithm, which was implemented with a personal computer, represents a definitive step toward rapid and accurate detection and prediction of seizures. It may also enable development of intelligent devices for automated seizure warning and treatment and stimulate new study of the dynamics of seizures and of the epileptic brain.},
  langid = {english},
  keywords = {Detection,Epilepsy,Prediction,Real time,Seizure},
  annotation = {\_eprint: https://onlinelibrary.wiley.com/doi/pdf/10.1111/j.1528-1157.1998.tb01430.x},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Osorio et al\\1998\\Osorio et al_1998_Real-Time Automated Detection and Quantitative Analysis of Seizures and.pdf;C\:\\Users\\selinederooij\\Zotero\\storage\\HJHDVS57\\j.1528-1157.1998.tb01430.html}
}

@article{papalexakis2017TensorsDataMining,
  title = {Tensors for {{Data Mining}} and {{Data Fusion}}: {{Models}}, {{Applications}}, and {{Scalable Algorithms}}},
  shorttitle = {Tensors for {{Data Mining}} and {{Data Fusion}}},
  author = {Papalexakis, Evangelos E. and Faloutsos, Christos and Sidiropoulos, Nicholas D.},
  date = {2017-01-18},
  journaltitle = {ACM Transactions on Intelligent Systems and Technology},
  shortjournal = {ACM Trans. Intell. Syst. Technol.},
  volume = {8},
  number = {2},
  pages = {1--44},
  issn = {2157-6904, 2157-6912},
  doi = {10.1145/2915921},
  url = {https://dl.acm.org/doi/10.1145/2915921},
  urldate = {2022-03-08},
  abstract = {Tensors and tensor decompositions are very powerful and versatile tools that can model a wide variety of heterogeneous, multiaspect data. As a result, tensor decompositions, which extract useful latent information out of multiaspect data tensors, have witnessed increasing popularity and adoption by the data mining community. In this survey, we present some of the most widely used tensor decompositions, providing the key insights behind them, and summarizing them from a practitioner’s point of view. We then provide an overview of a very broad spectrum of applications where tensors have been instrumental in achieving state-of-the-art performance, ranging from social network analysis to brain data analysis, and from web mining to healthcare. Subsequently, we present recent algorithmic advances in scaling tensor decompositions up to today’s big data, outlining the existing systems and summarizing the key ideas behind them. Finally, we conclude with a list of challenges and open problems that outline exciting future research directions.},
  langid = {english},
  keywords = {read_nonote},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\CEDABP2B\\Papalexakis et al. - 2017 - Tensors for Data Mining and Data Fusion Models, A.pdf}
}

@article{park2011SeizurePredictionSpectral,
  title = {Seizure Prediction with Spectral Power of {{EEG}} Using Cost-Sensitive Support Vector Machines},
  author = {Park, Yun and Luo, Lan and Parhi, Keshab K. and Netoff, Theoden},
  date = {2011},
  journaltitle = {Epilepsia},
  volume = {52},
  number = {10},
  pages = {1761--1770},
  issn = {1528-1167},
  doi = {10.1111/j.1528-1167.2011.03138.x},
  url = {https://onlinelibrary.wiley.com/doi/abs/10.1111/j.1528-1167.2011.03138.x},
  urldate = {2022-03-21},
  abstract = {Purpose: We propose a patient-specific algorithm for seizure prediction using multiple features of spectral power from electroencephalogram (EEG) and support vector machine (SVM) classification. Methods: The proposed patient-specific algorithm consists of preprocessing, feature extraction, SVM classification, and postprocessing. Preprocessing removes artifacts of intracranial EEG recordings and they are further preprocessed in bipolar and/or time-differential methods. Features of spectral power of raw, or bipolar and/or time-differential intracranial EEG (iEEG) recordings in nine bands are extracted from a sliding 20-s–long and half-overlapped window. Nine bands are selected based on standard EEG frequency bands, but the wide gamma bands are split into four. Cost-sensitive SVMs are used for classification of preictal and interictal samples, and double cross-validation is used to achieve in-sample optimization and out-of-sample testing. We postprocess SVM classification outputs using the Kalman Filter and it removes sporadic and isolated false alarms. The algorithm has been tested on iEEG of 18 patients of 20 available in the Freiburg EEG database who had three or more seizure events. To investigate the discriminability of the features between preictal and interictal, we use the Kernel Fisher Discriminant analysis. Key findings: The proposed patient-specific algorithm for seizure prediction has achieved high sensitivity of 97.5\% with total 80 seizure events and a low false alarm rate of 0.27 per hour and total false prediction times of 13.0\% over a total of 433.2 interictal hours by bipolar preprocessing (92.5\% sensitivity, a false positive rate of 0.20 per hour, and false prediction times of 9.5\% by time-differential preprocessing). This high prediction rate demonstrates that seizures can be predicted by the patient-specific approach using linear features of spectral power and nonlinear classifiers. Bipolar and/or time-differential preprocessing significantly improves sensitivity and specificity. Spectral powers in high gamma bands are the most discriminating features between preictal and interictal. Significance: High sensitivity and specificity are achieved by nonlinear classification of linear features of spectral power. Power changes in certain frequency bands already demonstrated their possibilities for seizure prediction indicators, but we have demonstrated that combining those spectral power features and classifying them in a multivariate approach led to much higher prediction rates. Employing only linear features is advantageous, especially when it comes to an implantable device, because they can be computed rapidly with low power consumption.},
  langid = {english},
  keywords = {Detection,Electroencephalogram,Epilepsy,Prediction,Seizure,unread},
  annotation = {\_eprint: https://onlinelibrary.wiley.com/doi/pdf/10.1111/j.1528-1167.2011.03138.x},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Park et al\\2011\\Park et al_2011_Seizure prediction with spectral power of EEG using cost-sensitive support.pdf}
}

@inproceedings{pernice2020SynergisticRedundantBrainHeart,
  title = {Synergistic and {{Redundant Brain-Heart Information}} in {{Patients}} with {{Focal Epilepsy}}},
  booktitle = {2020 11th {{Conference}} of the {{European Study Group}} on {{Cardiovascular Oscillations}} ({{ESGCO}})},
  author = {Pernice, Riccardo and Kotiuchyi, Ivan and Popov, Anton and Kharytonov, Volodymyr and Busacca, Alessandro and Marinazzo, Daniele and Faes, Luca},
  date = {2020-07},
  pages = {1--2},
  publisher = {{IEEE}},
  location = {{Pisa, Italy}},
  doi = {10.1109/ESGCO49734.2020.9158196},
  url = {https://ieeexplore.ieee.org/document/9158196/},
  urldate = {2022-03-08},
  abstract = {In this work, partial information decomposition (PID) was applied to the time series of heart rate and EEG amplitude variability to investigate the dynamical interactions in brain-heart coupling before and after epileptic seizures. From ECG and EEG signals collected on 23 children suffering from focal epilepsy, the RR intervals and the EEG variance at ipsilateral and contralateral temporal electrodes were computed in four different time windows before and after the seizures. Static PID was used to obtain redundant, unique and synergistic components of the total information shared between the series of RR and EEG variance. Results highlight, in the progression from preictal to postictal states, a statistically significant change of mutual information at the ipsilateral electrode and of the synergy between brain locations.},
  eventtitle = {2020 11th {{Conference}} of the {{European Study Group}} on {{Cardiovascular Oscillations}} ({{ESGCO}})},
  isbn = {978-1-72815-751-1},
  langid = {english},
  keywords = {unread},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\QWBMSLS9\\Pernice et al. - 2020 - Synergistic and Redundant Brain-Heart Information .pdf}
}

@article{phan2010TensorDecompositionsFeature,
  title = {Tensor Decompositions for Feature Extraction and Classification of High Dimensional Datasets},
  author = {Phan, Anh Huy and Cichocki, Andrzej},
  date = {2010},
  journaltitle = {Nonlinear Theory and Its Applications, IEICE},
  shortjournal = {NOLTA},
  volume = {1},
  number = {1},
  pages = {37--68},
  issn = {2185-4106},
  doi = {10.1587/nolta.1.37},
  url = {https://www.jstage.jst.go.jp/article/nolta/1/1/1_1_37/_article},
  urldate = {2022-03-08},
  abstract = {Feature extraction and selection are key factors in model reduction, classification and pattern recognition problems. This is especially important for input data with large dimensions such as brain recording or multiview images, where appropriate feature extraction is a prerequisite to classification. To ensure that the reduced dataset contains maximum information about input data we propose algorithms for feature extraction and classification. This is achieved based on orthogonal or nonnegative tensor (multi-array) decompositions, and higher order (multilinear) discriminant analysis (HODA), whereby input data are considered as tensors instead of more conventional vector or matrix representations. The developed algorithms are verified on benchmark datasets, using constraints imposed on tensors and/or factor matrices such as orthogonality and nonnegativity.},
  langid = {english},
  keywords = {printed,read_nonote},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\XNWNGSPA\\Phan and Cichocki - 2010 - Tensor decompositions for feature extraction and c.pdf}
}

@article{priyaprathaban2021DynamicLearningFramework,
  title = {Dynamic Learning Framework for Epileptic Seizure Prediction Using Sparsity Based {{EEG Reconstruction}} with {{Optimized CNN}} Classifier},
  author = {Priya Prathaban, Banu and Balasubramanian, Ramachandran},
  date = {2021-05-15},
  journaltitle = {Expert Systems with Applications},
  shortjournal = {Expert Systems with Applications},
  volume = {170},
  pages = {114533},
  issn = {0957-4174},
  doi = {10.1016/j.eswa.2020.114533},
  url = {https://www.sciencedirect.com/science/article/pii/S0957417420311775},
  urldate = {2022-04-28},
  abstract = {The World Health Organization (WHO) recently stated that epilepsy affects nearly 65 million people of the world population. Early forecast of the oncoming seizures is of paramount importance in saving the life of epileptic patients. This paper demonstrates a phase transition-based seizure prediction approach from multi-channel scalp electroencephalogram (EEG) recordings. The primary focus of this work is to discriminate the seizure and seizure-free EEG signals by learning the dynamics of preictal, interictal and ictal period. We propose an adaptive optimization approach using non-linear conjugate gradient technique in conjunction with Sparsity based EEG Reconstruction (SER) and three-dimensional Optimized Convolutional Neural Network (3D OCNN) classifier, based on Fletcher Reeves (FR) algorithm. Sparsity based artifact removal approach along with a 3D OCNN classifier, classifies the various states of seizures. FR algorithm is deployed with the deep neural network architecture to accelerate the convergence rate and to reduce the complexity of the proposed non-linear model. The Principle Component Analysis (PCA) algorithm replacing the Singular Value Decomposition (SVD) in the K-SVD algorithm, further reduces the time and complexity of the pre-processing stage. We further propose a Phase Transition based Kullback-Leibler divergence (PTB-KL) predictor for obtaining the Optimal Seizure Prediction Horizon (OSPH). The proposed model is evaluated using three diverse databases such as CHB-MIT, NINC and SRM respectively. Empirical results on the three EEG databases of 300 recordings outperforms the state-of-art approaches with an accuracy score of 0.98, sensitivity score of 0.99 and False Prediction Rate (FPR) of 0.07 FP/h. Statistical assessment of the proposed predictor gains an OSPH of about 1.1~h prior to the seizure onset. Experimental results prove that the phase transition-based seizure prediction approach is a promising one for accurate real-time prediction of epilepsy using scalp EEG data.},
  langid = {english},
  keywords = {Fletcher Reeves,K-SVD,Kullback-Leibler divergence,Optimal Seizure Prediction Horizon,Optimized Convolutional Neural Network,Principle Component Analysis},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Priya Prathaban_Balasubramanian\\2021\\Priya Prathaban_Balasubramanian_2021_Dynamic learning framework for epileptic seizure prediction using sparsity.pdf;C\:\\Users\\selinederooij\\Zotero\\storage\\GZGDQGLA\\S0957417420311775.html}
}

@article{proix2021ForecastingSeizureRisk,
  title = {Forecasting Seizure Risk in Adults with Focal Epilepsy: A Development and Validation Study},
  shorttitle = {Forecasting Seizure Risk in Adults with Focal Epilepsy},
  author = {Proix, Timothée and Truccolo, Wilson and Leguia, Marc G and Tcheng, Thomas K and King-Stephens, David and Rao, Vikram R and Baud, Maxime O},
  date = {2021-02},
  journaltitle = {The Lancet Neurology},
  shortjournal = {The Lancet Neurology},
  volume = {20},
  number = {2},
  pages = {127--135},
  issn = {14744422},
  doi = {10.1016/S1474-4422(20)30396-3},
  url = {https://linkinghub.elsevier.com/retrieve/pii/S1474442220303963},
  urldate = {2022-03-08},
  abstract = {Background People with epilepsy are burdened with the apparent unpredictability of seizures. In the past decade, converging evidence from studies using chronic EEG (cEEG) revealed that epileptic brain activity shows robust cycles, operating over hours (circadian) and days (multidien). We hypothesised that these cycles can be leveraged to estimate future seizure probability, and we tested the feasibility of forecasting seizures days in advance.},
  langid = {english},
  keywords = {unread},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\24PDK9RY\\Proix et al. - 2021 - Forecasting seizure risk in adults with focal epil.pdf}
}

@article{rabiner1989TutorialHiddenMarkov,
  title = {A Tutorial on Hidden {{Markov}} Models and Selected Applications in Speech Recognition},
  author = {Rabiner, L.R.},
  date = {1989-02},
  journaltitle = {Proceedings of the IEEE},
  volume = {77},
  number = {2},
  pages = {257--286},
  issn = {1558-2256},
  doi = {10.1109/5.18626},
  abstract = {This tutorial provides an overview of the basic theory of hidden Markov models (HMMs) as originated by L.E. Baum and T. Petrie (1966) and gives practical details on methods of implementation of the theory along with a description of selected applications of the theory to distinct problems in speech recognition. Results from a number of original sources are combined to provide a single source of acquiring the background required to pursue further this area of research. The author first reviews the theory of discrete Markov chains and shows how the concept of hidden states, where the observation is a probabilistic function of the state, can be used effectively. The theory is illustrated with two simple examples, namely coin-tossing, and the classic balls-in-urns system. Three fundamental problems of HMMs are noted and several practical techniques for solving these problems are given. The various types of HMMs that have been studied, including ergodic as well as left-right models, are described.{$<>$}},
  eventtitle = {Proceedings of the {{IEEE}}},
  keywords = {Hidden Markov models,Speech recognition,Tutorial},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Rabiner\\1989\\Rabiner_1989_A tutorial on hidden Markov models and selected applications in speech.pdf;C\:\\Users\\selinederooij\\Zotero\\storage\\PWRISW2H\\18626.html}
}

@article{ramgopal2014SeizureDetectionSeizure,
  title = {Seizure Detection, Seizure Prediction, and Closed-Loop Warning Systems in Epilepsy},
  author = {Ramgopal, Sriram and Thome-Souza, Sigride and Jackson, Michele and Kadish, Navah Ester and Sánchez Fernández, Iván and Klehm, Jacquelyn and Bosl, William and Reinsberger, Claus and Schachter, Steven and Loddenkemper, Tobias},
  date = {2014-08},
  journaltitle = {Epilepsy \& Behavior},
  shortjournal = {Epilepsy \& Behavior},
  volume = {37},
  pages = {291--307},
  issn = {15255050},
  doi = {10.1016/j.yebeh.2014.06.023},
  url = {https://linkinghub.elsevier.com/retrieve/pii/S1525505014002297},
  urldate = {2022-03-08},
  abstract = {Nearly one-third of patients with epilepsy continue to have seizures despite optimal medication management. Systems employed to detect seizures may have the potential to improve outcomes in these patients by allowing more tailored therapies and might, additionally, have a role in accident and SUDEP prevention. Automated seizure detection and prediction require algorithms which employ feature computation and subsequent classification. Over the last few decades, methods have been developed to detect seizures utilizing scalp and intracranial EEG, electrocardiography, accelerometry and motion sensors, electrodermal activity, and audio/video captures. To date, it is unclear which combination of detection technologies yields the best results, and approaches may ultimately need to be individualized. This review presents an overview of seizure detection and related prediction methods and discusses their potential uses in closed-loop warning systems in epilepsy.},
  langid = {english},
  keywords = {read_nonote},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\YDVQQ3VX\\Ramgopal et al. - 2014 - Seizure detection, seizure prediction, and closed-.pdf}
}

@article{ramgopal2014SeizureDetectionSeizurea,
  title = {Seizure Detection, Seizure Prediction, and Closed-Loop Warning Systems in Epilepsy},
  author = {Ramgopal, Sriram and Thome-Souza, Sigride and Jackson, Michele and Kadish, Navah Ester and Sánchez Fernández, Iván and Klehm, Jacquelyn and Bosl, William and Reinsberger, Claus and Schachter, Steven and Loddenkemper, Tobias},
  date = {2014-08-01},
  journaltitle = {Epilepsy \& Behavior},
  shortjournal = {Epilepsy \& Behavior},
  volume = {37},
  pages = {291--307},
  issn = {1525-5050},
  doi = {10.1016/j.yebeh.2014.06.023},
  url = {https://www.sciencedirect.com/science/article/pii/S1525505014002297},
  urldate = {2022-03-17},
  abstract = {Nearly one-third of patients with epilepsy continue to have seizures despite optimal medication management. Systems employed to detect seizures may have the potential to improve outcomes in these patients by allowing more tailored therapies and might, additionally, have a role in accident and SUDEP prevention. Automated seizure detection and prediction require algorithms which employ feature computation and subsequent classification. Over the last few decades, methods have been developed to detect seizures utilizing scalp and intracranial EEG, electrocardiography, accelerometry and motion sensors, electrodermal activity, and audio/video captures. To date, it is unclear which combination of detection technologies yields the best results, and approaches may ultimately need to be individualized. This review presents an overview of seizure detection and related prediction methods and discusses their potential uses in closed-loop warning systems in epilepsy.},
  langid = {english},
  keywords = {Accelerometry,Artificial neural network,Automated seizure detection,Closed-loop methods,ECG-based seizure detection,EEG-based seizure detection,Fourier,Higher-order spectra,Markov modeling,Support vector machine,unread},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Ramgopal et al\\2014\\Ramgopal et al_2014_Seizure detection, seizure prediction, and closed-loop warning systems in.pdf;C\:\\Users\\selinederooij\\Zotero\\storage\\N8JYAPG3\\S1525505014002297.html}
}

@article{rangapuramDeepStateSpace,
  title = {Deep {{State Space Models}} for {{Time Series Forecasting}}},
  author = {Rangapuram, Syama Sundar and Seeger, Matthias and Gasthaus, Jan and Stella, Lorenzo and Wang, Yuyang and Januschowski, Tim},
  pages = {10},
  abstract = {We present a novel approach to probabilistic time series forecasting that combines state space models with deep learning. By parametrizing a per-time-series linear state space model with a jointly-learned recurrent neural network, our method retains desired properties of state space models such as data efficiency and interpretability, while making use of the ability to learn complex patterns from raw data offered by deep learning approaches. Our method scales gracefully from regimes where little training data is available to regimes where data from large collection of time series can be leveraged to learn accurate models. We provide qualitative as well as quantitative results with the proposed method, showing that it compares favorably to the state-of-the-art.},
  langid = {english},
  keywords = {unread},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\C4H2CVB9\\Rangapuram et al. - Deep State Space Models for Time Series Forecastin.pdf}
}

@article{rosas-romero2019PredictionEpilepticSeizures,
  title = {Prediction of Epileptic Seizures with Convolutional Neural Networks and Functional Near-Infrared Spectroscopy Signals},
  author = {Rosas-Romero, Roberto and Guevara, Edgar and Peng, Ke and Nguyen, Dang Khoa and Lesage, Frédéric and Pouliot, Philippe and Lima-Saad, Wassim-Enrique},
  date = {2019-08-01},
  journaltitle = {Computers in Biology and Medicine},
  shortjournal = {Computers in Biology and Medicine},
  volume = {111},
  pages = {103355},
  issn = {0010-4825},
  doi = {10.1016/j.compbiomed.2019.103355},
  url = {https://www.sciencedirect.com/science/article/pii/S001048251930232X},
  urldate = {2022-04-25},
  abstract = {There have been different efforts to predict epileptic seizures and most of them are based on the analysis of electroencephalography (EEG) signals; however, recent publications have suggested that functional Near-Infrared Spectroscopy (fNIRS), a relatively new technique, could be used to predict seizures. The objectives of this research are to show that the application of fNIRS to epileptic seizure detection yields results that are superior to those based on EEG and to demonstrate that the application of deep learning to this problem is suitable given the nature of fNIRS recordings. A Convolutional Neural Network (CNN) is applied to the prediction of epileptic seizures from fNIRS signals, an optical modality for recording brain waves. The implementation of the proposed method is presented in this work. Application of CNN to fNIRS recordings showed an accuracy ranging between 96.9\% and 100\%, sensitivity between 95.24\% and 100\%, specificity between 98.57\% and 100\%, a positive predictive value between 98.52\% and 100\%, and a negative predictive value between 95.39\% and 100\%. The most important aspect of this research is the combination of fNIRS signals with the particular CNN algorithm. The fNIRS modality has not been used in epileptic seizure prediction. A CNN is suitable for this application because fNIRS recordings are high dimensional data and they can be modeled as three-dimensional tensors for classification.},
  langid = {english},
  keywords = {Convolutional neural network (CNN),Epileptic seizure prediction,Functional near-infrared spectroscopy (fNIRS),Gradient descent method,tensor,unread},
  annotation = {35 citations (Semantic Scholar/DOI) [2022-04-25]},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Rosas-Romero et al\\2019\\Rosas-Romero et al_2019_Prediction of epileptic seizures with convolutional neural networks and.pdf;C\:\\Users\\selinederooij\\Zotero\\storage\\T43ANRWT\\S001048251930232X.html}
}

@article{sabor2022BHINetBrainHeartInteractionBased,
  title = {{{BHI-Net}}: {{Brain-Heart Interaction-Based Deep Architectures}} for {{Epileptic Seizures}} and {{Firing Location Detection}}},
  shorttitle = {{{BHI-Net}}},
  author = {Sabor, Nabil and Mohammed, Hazem and Li, Zhe and Wang, Guoxing},
  date = {2022},
  journaltitle = {IEEE Transactions on Neural Systems and Rehabilitation Engineering},
  volume = {30},
  pages = {1576--1588},
  issn = {1558-0210},
  doi = {10.1109/TNSRE.2022.3181151},
  abstract = {Automatic detection of epileptic seizures is still a challenging problem due to the intolerance of EEG. Introducing ECG can help with EEG for detecting seizures. However, the existing methods depended on fusing either the extracted features or the classification results of EEG-only and ECG-only with ignoring the interaction between them, so the detection rate did not improve much. Also, all EEG channels were considered in a complex manner. Moreover, the detection of epilepsy firing location, which is an important issue for diagnosing epilepsy, is not considered before. Therefore, we propose a new method based on the brain-heart interaction (BHI) for detecting the seizure onset and its firing location in the brain with lower complexity and better performance. BHI allows us to study the nonlinear coupling and variation of phase-synchronization between brain regions and heart activity, which are effective for distinguishing seizures. In our method, the EEG channels are mapped into two surrogate channels to reduce the computational complexity. Moreover, the firing location detector is triggered only once the seizure is detected to save the system’s power. Evaluation using different proposed classification networks based on the TUSZ, the largest available EEG/ECG dataset with 315 subjects and 7 seizure types, showed that our BHI method improves the sensitivity by 48\% with only 4 false alarms/24h compared to using only EEG. Moreover, it outperforms the performance of the average human detector based on the quantitative EEG tools by achieving a sensitivity of 68.2\% with 11.9 false alarms/ 24h and a latency of 11.94 sec.},
  eventtitle = {{{IEEE Transactions}} on {{Neural Systems}} and {{Rehabilitation Engineering}}},
  keywords = {and wavelet bi-spectrum,Brain-heart Interaction,deep network,ECG,EEG,Electrocardiography,Electroencephalography,Epilepsy,Feature extraction,Firing,printed,read,Recording,support vector machine,Support vector machines},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Sabor et al\\2022\\Sabor et al_2022_BHI-Net.pdf;C\:\\Users\\selinederooij\\surfdrive\\notes\\PhD_Notes\\Reading Notes\\@sabor2022BHINetBrainHeartInteractionBased.md;C\:\\Users\\selinederooij\\Zotero\\storage\\W2XVRXY9\\authors.html}
}

@article{saneiEEGSignalProcessing,
  title = {{{EEG Signal Processing}}},
  author = {Sanei, Saeid and Chambers, Jonathan},
  pages = {149},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\WVCSNCIB\\Sanei and Chambers - EEG Signal Processing.pdf}
}

@book{sarkka2013BayesianFilteringSmoothing,
  title = {Bayesian {{Filtering}} and {{Smoothing}}},
  author = {Sarkka, Simo},
  date = {2013},
  publisher = {{Cambridge University Press}},
  location = {{Cambridge}},
  doi = {10.1017/CBO9781139344203},
  url = {http://ebooks.cambridge.org/ref/id/CBO9781139344203},
  urldate = {2022-03-18},
  isbn = {978-1-139-34420-3},
  langid = {english},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\UVL92JSF\\Sarkka - 2013 - Bayesian Filtering and Smoothing.pdf}
}

@article{scheffer2017ILAEClassificationEpilepsies,
  title = {{{{\textsc{ILAE}}}} Classification of the Epilepsies: {{Position}} Paper of the {{{\textsc{ILAE}}}} {{Commission}} for {{Classification}} and {{Terminology}}},
  author = {Scheffer, Ingrid E. and Berkovic, Samuel and Capovilla, Giuseppe and Connolly, Mary B. and French, Jacqueline and Guilhoto, Laura and Hirsch, Edouard and Jain, Satish and Mathern, Gary W. and Moshé, Solomon L. and Nordli, Douglas R. and Perucca, Emilio and Tomson, Torbjörn and Wiebe, Samuel and Zhang, Yue‐Hua and Zuberi, Sameer M.},
  date = {2017-04},
  journaltitle = {Epilepsia},
  shortjournal = {Epilepsia},
  volume = {58},
  number = {4},
  pages = {512--521},
  issn = {0013-9580, 1528-1167},
  doi = {10.1111/epi.13709},
  url = {https://onlinelibrary.wiley.com/doi/10.1111/epi.13709},
  urldate = {2022-03-08},
  langid = {english},
  keywords = {read_nonote},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\24ILJFZV\\Scheffer et al. - 2017 - ILAE.pdf}
}

@inproceedings{schiff2009KalmanMeetsNeuron,
  title = {Kalman {{Meets Neuron}}: {{The Emerging Intersection}} of {{Control Theory}} with {{Neuroscience}}},
  shorttitle = {Kalman {{Meets Neuron}}},
  booktitle = {2009 {{Annual International Conference}} of the {{Ieee Engineering}} in {{Medicine}} and {{Biology Society}}, {{Vols}} 1-20},
  author = {Schiff, Steven J.},
  date = {2009},
  pages = {3318--3321},
  publisher = {{Ieee}},
  location = {{New York}},
  issn = {1557-170X},
  doi = {10.1109/IEMBS.2009.5333752},
  url = {https://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=DynamicDOIConfProc&SrcApp=WOS&KeyAID=10.1109%2FIEMBS.2009.5333752&DestApp=DOI&SrcAppSID=F575yPO42JH3DUXrkTD&SrcJTitle=2009+ANNUAL+INTERNATIONAL+CONFERENCE+OF+THE+IEEE+ENGINEERING+IN+MEDICINE+AND+BIOLOGY+SOCIETY%2C+VOLS+1-20&DestDOIRegistrantName=Institute+of+Electrical+and+Electronics+Engineers},
  urldate = {2022-03-21},
  abstract = {Since the 1950s, we have developed mature theories of modem control theory and computational neuroscience with almost no interaction between these disciplines. With the advent of computationally efficient nonlinear Kalman filtering techniques, along with improved neuroscience models that provide increasingly accurate reconstruction of dynamics in a variety of important normal and disease states in the brain, the prospects for a synergistic interaction between these fields are now strong. I show recent examples of the use of nonlinear control theory for the assimilation and control of single neuron dynamics, the modulation of oscillatory wave dynamics in brain cortex, a control framework for Parkinsonian dynamics and seizures, and the use of optimized parameter model networks to assimilate complex network data - the 'consensus set'.},
  isbn = {978-1-4244-3295-0},
  langid = {english},
  keywords = {data assimilation,dynamics,filter,model,waves},
  annotation = {WOS:000280543602195},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Schiff\\2009\\Schiff_2009_Kalman Meets Neuron.pdf}
}

@inproceedings{schiff2009KalmanMeetsNeurona,
  title = {Kalman Meets Neuron: {{The}} Emerging Intersection of Control Theory with Neuroscience},
  shorttitle = {Kalman Meets Neuron},
  booktitle = {2009 {{Annual International Conference}} of the {{IEEE Engineering}} in {{Medicine}} and {{Biology Society}}},
  author = {Schiff, Steven J.},
  date = {2009-09},
  pages = {3318--3321},
  issn = {1558-4615},
  doi = {10.1109/IEMBS.2009.5333752},
  abstract = {Since the 1950s, we have developed mature theories of modern control theory and computational neuroscience with almost no interaction between these disciplines. With the advent of computationally efficient nonlinear Kalman filtering techniques, along with improved neuroscience models that provide increasingly accurate reconstruction of dynamics in a variety of important normal and disease states in the brain, the prospects for a synergistic interaction between these fields are now strong. I show recent examples of the use of nonlinear control theory for the assimilation and control of single neuron dynamics, the modulation of oscillatory wave dynamics in brain cortex, a control framework for Parkinsonian dynamics and seizures, and the use of optimized parameter model networks to assimilate complex network data - the `consensus set'.},
  eventtitle = {2009 {{Annual International Conference}} of the {{IEEE Engineering}} in {{Medicine}} and {{Biology Society}}},
  keywords = {Brain modeling,Control systems,Control theory,Filtering,Kalman filters,Neurons,Neuroscience,Nonlinear dynamical systems,Power system modeling,Predictive models},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Schiff\\2009\\Schiff_2009_Kalman meets neuron2.pdf;C\:\\Users\\selinederooij\\Zotero\\storage\\G6GZST6H\\5333752.html}
}

@book{scholkopf2002LearningKernelsSupport,
  title = {Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond},
  shorttitle = {Learning with Kernels},
  author = {Schölkopf, Bernhard and Smola, Alexander J.},
  date = {2002},
  series = {Adaptive Computation and Machine Learning},
  publisher = {{MIT Press}},
  location = {{Cambridge, Mass}},
  isbn = {978-0-262-19475-4},
  langid = {english},
  pagetotal = {626},
  keywords = {Kernel functions,Support vector machines},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\3A9JYI5F\\Schölkopf and Smola - 2002 - Learning with kernels support vector machines, re.pdf}
}

@article{schollwock2011DensitymatrixRenormalizationGroup,
  title = {The Density-Matrix Renormalization Group in the Age of Matrix Product States},
  author = {Schollwöck, Ulrich},
  date = {2011-01},
  journaltitle = {Annals of Physics},
  shortjournal = {Annals of Physics},
  volume = {326},
  number = {1},
  pages = {96--192},
  issn = {00034916},
  doi = {10.1016/j.aop.2010.09.012},
  url = {https://linkinghub.elsevier.com/retrieve/pii/S0003491610001752},
  urldate = {2022-07-19},
  abstract = {The density-matrix renormalization group method (DMRG) has established itself over the last decade as the leading method for the simulation of the statics and dynamics of one-dimensional strongly correlated quantum lattice systems. In the further development of the method, the realization that DMRG operates on a highly interesting class of quantum states, so-called matrix product states (MPS), has allowed a much deeper understanding of the inner structure of the DMRG method, its further potential and its limitations. In this paper, I want to give a detailed exposition of current DMRG thinking in the MPS language in order to make the advisable implementation of the family of DMRG algorithms in exclusively MPS terms transparent. I then move on to discuss some directions of potentially fruitful further algorithmic development: while DMRG is a very mature method by now, I still see potential for further improvements, as exemplified by a number of recently introduced algorithms.},
  langid = {english},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\I7AD9YF4\\Schollwöck - 2011 - The density-matrix renormalization group in the ag.pdf}
}

@article{seeck2017StandardizedEEGElectrode,
  title = {The Standardized {{EEG}} Electrode Array of the {{IFCN}}},
  author = {Seeck, Margitta and Koessler, Laurent and Bast, Thomas and Leijten, Frans and Michel, Christoph and Baumgartner, Christoph and He, Bin and Beniczky, Sándor},
  date = {2017-10},
  journaltitle = {Clinical Neurophysiology},
  shortjournal = {Clinical Neurophysiology},
  volume = {128},
  number = {10},
  pages = {2070--2077},
  issn = {13882457},
  doi = {10.1016/j.clinph.2017.06.254},
  url = {https://linkinghub.elsevier.com/retrieve/pii/S1388245717304832},
  urldate = {2022-03-08},
  abstract = {Standardized EEG electrode positions are essential for both clinical applications and research. The aim of this guideline is to update and expand the unifying nomenclature and standardized positioning for EEG scalp electrodes. Electrode positions were based on 20\% and 10\% of standardized measurements from anatomical landmarks on the skull. However, standard recordings do not cover the anterior and basal temporal lobes, which is the most frequent source of epileptogenic activity. Here, we propose a basic array of 25 electrodes including the inferior temporal chain, which should be used for all standard clinical recordings. The nomenclature in the basic array is consistent with the 10–10-system. High-density scalp EEG arrays (64–256 electrodes) allow source imaging with even sub-lobar precision. This supplementary exam should be requested whenever necessary, e.g. search for epileptogenic activity in negative standard EEG or for presurgical evaluation. In the near future, nomenclature for high density electrodes arrays beyond the 10–10 system needs to be defined, to allow comparison and standardized recordings across centers. Contrary to the established belief that smaller heads needs less electrodes, in young children at least as many electrodes as in adults should be applied due to smaller skull thickness and the risk of spatial aliasing. Ó 2017 International Federation of Clinical Neurophysiology. Published by Elsevier Ireland Ltd. All rights reserved.},
  langid = {english},
  keywords = {read_nonote},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\INV3IGUD\\Seeck et al. - 2017 - The standardized EEG electrode array of the IFCN.pdf}
}

@incollection{shah2021ObjectiveEvaluationMetrics,
  title = {Objective {{Evaluation Metrics}} for {{Automatic Classification}} of {{EEG Events}}},
  booktitle = {Biomedical {{Signal Processing}}},
  author = {Shah, Vinit and Golmohammadi, Meysam and Obeid, Iyad and Picone, Joseph},
  editor = {Obeid, Iyad and Selesnick, Ivan and Picone, Joseph},
  date = {2021},
  pages = {223--255},
  publisher = {{Springer International Publishing}},
  location = {{Cham}},
  doi = {10.1007/978-3-030-67494-6_8},
  url = {https://link.springer.com/10.1007/978-3-030-67494-6_8},
  urldate = {2022-06-07},
  abstract = {Significance: The metrics proposed in the study, ATWV and TAES can be the means for standardizing scoring across the industry. We also demonstrate that state-of-the-art technology based on deep learning, though impressive in its performance, still needs significant improvement.},
  isbn = {978-3-030-67493-9 978-3-030-67494-6},
  langid = {english},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\TFNXQIU9\\Shah et al. - 2021 - Objective Evaluation Metrics for Automatic Classif.pdf}
}

@article{shawe-taylorKernelMethodsPattern,
  title = {Kernel {{Methods}} for {{Pattern Analysis}}},
  author = {Shawe-Taylor, John and Cristianini, Nello},
  pages = {478},
  langid = {english},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\Z2Q5YXPZ\\Shawe-Taylor and Cristianini - Kernel Methods for Pattern Analysis.pdf}
}

@article{siddiqui2020ReviewEpilepticSeizure,
  title = {A Review of Epileptic Seizure Detection Using Machine Learning Classifiers},
  author = {Siddiqui, Mohammad Khubeb and Morales-Menendez, Ruben and Huang, Xiaodi and Hussain, Nasir},
  date = {2020-12},
  journaltitle = {Brain Informatics},
  shortjournal = {Brain Inf.},
  volume = {7},
  number = {1},
  pages = {5},
  issn = {2198-4018, 2198-4026},
  doi = {10.1186/s40708-020-00105-1},
  url = {https://braininformatics.springeropen.com/articles/10.1186/s40708-020-00105-1},
  urldate = {2022-03-08},
  abstract = {Epilepsy is a serious chronic neurological disorder, can be detected by analyzing the brain signals produced by brain neurons. Neurons are connected to each other in a complex way to communicate with human organs and generate signals. The monitoring of these brain signals is commonly done using Electroencephalogram (EEG) and Electrocor‑ticography (ECoG) media. These signals are complex, noisy, non-linear, non-stationary and produce a high volume of data. Hence, the detection of seizures and discovery of the brain-related knowledge is a challenging task. Machine learning classifiers are able to classify EEG data and detect seizures along with revealing relevant sensible patterns without compromising performance. As such, various researchers have developed number of approaches to seizure detection using machine learning classifiers and statistical features. The main challenges are selecting appropriate classifiers and features. The aim of this paper is to present an overview of the wide varieties of these techniques over the last few years based on the taxonomy of statistical features and machine learning classifiers—‘black-box’ and ‘non-black-box’. The presented state-of-the-art methods and ideas will give a detailed understanding about seizure detection and classification, and research directions in the future.},
  langid = {english},
  keywords = {read_nonote},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\EK3Q3WBC\\Siddiqui et al. - 2020 - A review of epileptic seizure detection using mach.pdf}
}

@article{siddiqui2020ReviewEpilepticSeizurea,
  title = {A Review of Epileptic Seizure Detection Using Machine Learning Classifiers},
  author = {Siddiqui, Mohammad Khubeb and Morales-Menendez, Ruben and Huang, Xiaodi and Hussain, Nasir},
  date = {2020-05-25},
  journaltitle = {Brain Informatics},
  shortjournal = {Brain Informatics},
  volume = {7},
  number = {1},
  pages = {5},
  issn = {2198-4026},
  doi = {10.1186/s40708-020-00105-1},
  url = {https://doi.org/10.1186/s40708-020-00105-1},
  urldate = {2022-05-24},
  abstract = {Epilepsy is a serious chronic neurological disorder, can be detected by analyzing the brain signals produced by brain neurons. Neurons are connected to each other in a complex way to communicate with human organs and generate signals. The monitoring of these brain signals is commonly done using Electroencephalogram (EEG) and Electrocorticography (ECoG) media. These signals are complex, noisy, non-linear, non-stationary and produce a high volume of data. Hence, the detection of seizures and discovery of the brain-related knowledge is a challenging task. Machine learning classifiers are able to classify EEG data and detect seizures along with revealing relevant sensible patterns without compromising performance. As such, various researchers have developed number of approaches to seizure detection using machine learning classifiers and statistical features. The main challenges are selecting appropriate classifiers and features. The aim of this paper is to present an overview of the wide varieties of these techniques over the last few years based on the taxonomy of statistical features and machine learning classifiers—‘black-box’ and ‘non-black-box’. The presented state-of-the-art methods and ideas will give a detailed understanding about seizure detection and classification, and research directions in the future.},
  keywords = {Applications of machine learning on epilepsy,Black-box and non-black-box classifiers,EEG signals,Epilepsy,Seizure detection,Seizure localization,Statistical features},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\MKHMPCTM\\Siddiqui et al. - 2020 - A review of epileptic seizure detection using mach.pdf;C\:\\Users\\selinederooij\\Zotero\\storage\\XCJRX2FF\\s40708-020-00105-1.html}
}

@article{sidiropoulos2017TensorDecompositionSignal,
  title = {Tensor {{Decomposition}} for {{Signal Processing}} and {{Machine Learning}}},
  author = {Sidiropoulos, Nicholas D. and De Lathauwer, Lieven and Fu, Xiao and Huang, Kejun and Papalexakis, Evangelos E. and Faloutsos, Christos},
  date = {2017-07-01},
  journaltitle = {IEEE Transactions on Signal Processing},
  shortjournal = {IEEE Trans. Signal Process.},
  volume = {65},
  number = {13},
  pages = {3551--3582},
  issn = {1053-587X, 1941-0476},
  doi = {10.1109/TSP.2017.2690524},
  url = {http://ieeexplore.ieee.org/document/7891546/},
  urldate = {2022-03-08},
  abstract = {Tensors or multiway arrays are functions of three or more indices (i, j, k, . . . )—similar to matrices (two-way arrays), which are functions of two indices (r, c) for (row, column). Tensors have a rich history, stretching over almost a century, and touching upon numerous disciplines; but they have only recently become ubiquitous in signal and data analytics at the confluence of signal processing, statistics, data mining, and machine learning. This overview article aims to provide a good starting point for researchers and practitioners interested in learning about and working with tensors. As such, it focuses on fundamentals and motivation (using various application examples), aiming to strike an appropriate balance of breadth and depth that will enable someone having taken first graduate courses in matrix algebra and probability to get started doing research and/or developing tensor algorithms and software. Some background in applied optimization is useful but not strictly required. The material covered includes tensor rank and rank decomposition; basic tensor factorization models and their relationships and properties (including fairly good coverage of identifiability); broad coverage of algorithms ranging from alternating optimization to stochastic gradient; statistical performance analysis; and applications ranging from source separation to collaborative filtering, mixture and topic modeling, classification, and multilinear subspace learning.},
  langid = {english},
  keywords = {read_nonote},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\PJJYWNJG\\Sidiropoulos et al. - 2017 - Tensor Decomposition for Signal Processing and Mac.pdf}
}

@article{sidiropoulos2017TensorDecompositionSignala,
  title = {Tensor {{Decomposition}} for {{Signal Processing}} and {{Machine Learning}}},
  author = {Sidiropoulos, Nicholas D. and De Lathauwer, Lieven and Fu, Xiao and Huang, Kejun and Papalexakis, Evangelos E. and Faloutsos, Christos},
  date = {2017-07-01},
  journaltitle = {IEEE Transactions on Signal Processing},
  shortjournal = {IEEE Trans. Signal Process.},
  volume = {65},
  number = {13},
  pages = {3551--3582},
  issn = {1053-587X, 1941-0476},
  doi = {10.1109/TSP.2017.2690524},
  url = {http://ieeexplore.ieee.org/document/7891546/},
  urldate = {2022-03-08},
  abstract = {Tensors or multiway arrays are functions of three or more indices (i, j, k, . . . )—similar to matrices (two-way arrays), which are functions of two indices (r, c) for (row, column). Tensors have a rich history, stretching over almost a century, and touching upon numerous disciplines; but they have only recently become ubiquitous in signal and data analytics at the confluence of signal processing, statistics, data mining, and machine learning. This overview article aims to provide a good starting point for researchers and practitioners interested in learning about and working with tensors. As such, it focuses on fundamentals and motivation (using various application examples), aiming to strike an appropriate balance of breadth and depth that will enable someone having taken first graduate courses in matrix algebra and probability to get started doing research and/or developing tensor algorithms and software. Some background in applied optimization is useful but not strictly required. The material covered includes tensor rank and rank decomposition; basic tensor factorization models and their relationships and properties (including fairly good coverage of identifiability); broad coverage of algorithms ranging from alternating optimization to stochastic gradient; statistical performance analysis; and applications ranging from source separation to collaborative filtering, mixture and topic modeling, classification, and multilinear subspace learning.},
  langid = {english},
  keywords = {read_nonote},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\NSVEXQ3C\\Sidiropoulos et al. - 2017 - Tensor Decomposition for Signal Processing and Mac.pdf}
}

@article{signorettoKernelbasedFrameworkTensorial2011,
  title = {A Kernel-Based Framework to Tensorial Data Analysis},
  author = {Signoretto, Marco and De Lathauwer, Lieven and Suykens, Johan A. K.},
  date = {2011-10-01},
  journaltitle = {Neural Networks},
  shortjournal = {Neural Networks},
  series = {Artificial {{Neural Networks}}: {{Selected Papers}} from {{ICANN}} 2010},
  volume = {24},
  number = {8},
  pages = {861--874},
  issn = {0893-6080},
  doi = {10.1016/j.neunet.2011.05.011},
  url = {https://www.sciencedirect.com/science/article/pii/S0893608011001535},
  urldate = {2022-03-07},
  abstract = {Tensor-based techniques for learning allow one to exploit the structure of carefully chosen representations of data. This is a desirable feature in particular when the number of training patterns is small which is often the case in areas such as biosignal processing and chemometrics. However, the class of tensor-based models is somewhat restricted and might suffer from limited discriminative power. On a different track, kernel methods lead to flexible nonlinear models that have been proven successful in many different contexts. Nonetheless, a naïve application of kernel methods does not exploit structural properties possessed by the given tensorial representations. The goal of this work is to go beyond this limitation by introducing non-parametric tensor-based models. The proposed framework aims at improving the discriminative power of supervised tensor-based models while still exploiting the structural information embodied in the data. We begin by introducing a feature space formed by multilinear functionals. The latter can be considered as the infinite dimensional analogue of tensors. Successively we show how to implicitly map input patterns in such a feature space by means of kernels that exploit the algebraic structure of data tensors. The proposed tensorial kernel links to the MLSVD and features an interesting invariance property; the approach leads to convex optimization and fits into the same primal–dual framework underlying SVM-like algorithms.},
  langid = {english},
  keywords = {Multilinear algebra,Reproducing kernel Hilbert spaces,Subspace angles,Tensorial kernels,unread},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Signoretto et al_2011_A kernel-based framework to tensorial data analysis.pdf;C\:\\Users\\selinederooij\\Zotero\\storage\\REWQAMCB\\S0893608011001535.html}
}

@incollection{sornmo2005AppendixReviewImportant,
  title = {Appendix {{A}} - {{Review}} of {{Important Concepts}}},
  booktitle = {Bioelectrical {{Signal Processing}} in {{Cardiac}} and {{Neurological Applications}}},
  editor = {Sörnmo, Leif and Laguna, Pablo},
  date = {2005-01-01},
  series = {Biomedical {{Engineering}}},
  pages = {633--648},
  publisher = {{Academic Press}},
  location = {{Burlington}},
  doi = {10.1016/B978-012437552-9/50009-X},
  url = {https://www.sciencedirect.com/science/article/pii/B978012437552950009X},
  urldate = {2022-04-28},
  isbn = {978-0-12-437552-9},
  langid = {english}
}

@incollection{sornmo2005AppendixSymbolsAbbreviations,
  title = {Appendix {{B}} - {{Symbols}} and {{Abbreviations}}},
  booktitle = {Bioelectrical {{Signal Processing}} in {{Cardiac}} and {{Neurological Applications}}},
  editor = {Sörnmo, Leif and Laguna, Pablo},
  date = {2005-01-01},
  series = {Biomedical {{Engineering}}},
  pages = {649--660},
  publisher = {{Academic Press}},
  location = {{Burlington}},
  doi = {10.1016/B978-012437552-9/50010-6},
  url = {https://www.sciencedirect.com/science/article/pii/B9780124375529500106},
  urldate = {2022-04-28},
  isbn = {978-0-12-437552-9},
  langid = {english}
}

@incollection{sornmo2005BackCover,
  title = {Inside {{Back Cover}}},
  booktitle = {Bioelectrical {{Signal Processing}} in {{Cardiac}} and {{Neurological Applications}}},
  editor = {Sörnmo, Leif and Laguna, Pablo},
  date = {2005-01-01},
  series = {Biomedical {{Engineering}}},
  pages = {669},
  publisher = {{Academic Press}},
  location = {{Burlington}},
  doi = {10.1016/B978-0-12-437552-9.50014-3},
  url = {https://www.sciencedirect.com/science/article/pii/B9780124375529500143},
  urldate = {2022-04-28},
  isbn = {978-0-12-437552-9},
  langid = {english}
}

@incollection{sornmo2005ChapterECGSignal,
  title = {Chapter 7 - {{ECG Signal Processing}}},
  booktitle = {Bioelectrical {{Signal Processing}} in {{Cardiac}} and {{Neurological Applications}}},
  author = {Sörnmo, Leif and Laguna, Pablo},
  editor = {Sörnmo, Leif and Laguna, Pablo},
  date = {2005-01-01},
  series = {Biomedical {{Engineering}}},
  pages = {453--566},
  publisher = {{Academic Press}},
  location = {{Burlington}},
  doi = {10.1016/B978-012437552-9/50007-6},
  url = {https://www.sciencedirect.com/science/article/pii/B9780124375529500076},
  urldate = {2022-04-28},
  isbn = {978-0-12-437552-9},
  langid = {english}
}

@incollection{sornmo2005ChapterECGSignala,
  title = {Chapter 8 - {{ECG Signal Processing}}: {{Heart Rate Variability}}},
  shorttitle = {Chapter 8 - {{ECG Signal Processing}}},
  booktitle = {Bioelectrical {{Signal Processing}} in {{Cardiac}} and {{Neurological Applications}}},
  author = {Sörnmo, Leif and Laguna, Pablo},
  editor = {Sörnmo, Leif and Laguna, Pablo},
  date = {2005-01-01},
  series = {Biomedical {{Engineering}}},
  pages = {567--631},
  publisher = {{Academic Press}},
  location = {{Burlington}},
  doi = {10.1016/B978-012437552-9/50008-8},
  url = {https://www.sciencedirect.com/science/article/pii/B9780124375529500088},
  urldate = {2022-04-28},
  isbn = {978-0-12-437552-9},
  langid = {english}
}

@incollection{sornmo2005ChapterEEGSignal,
  title = {Chapter 3 - {{EEG Signal Processing}}},
  booktitle = {Bioelectrical {{Signal Processing}} in {{Cardiac}} and {{Neurological Applications}}},
  author = {Sörnmo, Leif and Laguna, Pablo},
  editor = {Sörnmo, Leif and Laguna, Pablo},
  date = {2005-01-01},
  series = {Biomedical {{Engineering}}},
  pages = {55--179},
  publisher = {{Academic Press}},
  location = {{Burlington}},
  doi = {10.1016/B978-012437552-9/50003-9},
  url = {https://www.sciencedirect.com/science/article/pii/B9780124375529500039},
  urldate = {2022-04-28},
  isbn = {978-0-12-437552-9},
  langid = {english},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Sörnmo_Laguna\\2005\\Sörnmo_Laguna_2005_Chapter 3 - EEG Signal Processing.pdf;C\:\\Users\\selinederooij\\Zotero\\storage\\8ARMQT4E\\B9780124375529500039.html}
}

@incollection{sornmo2005ChapterElectrocardiogramBrief,
  title = {Chapter 6 - {{The Electrocardiogram}}—{{A Brief Background}}},
  booktitle = {Bioelectrical {{Signal Processing}} in {{Cardiac}} and {{Neurological Applications}}},
  author = {Sörnmo, Leif and Laguna, Pablo},
  editor = {Sörnmo, Leif and Laguna, Pablo},
  date = {2005-01-01},
  series = {Biomedical {{Engineering}}},
  pages = {411--452},
  publisher = {{Academic Press}},
  location = {{Burlington}},
  doi = {10.1016/B978-012437552-9/50006-4},
  url = {https://www.sciencedirect.com/science/article/pii/B9780124375529500064},
  urldate = {2022-04-28},
  isbn = {978-0-12-437552-9},
  langid = {english},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Sörnmo_Laguna\\2005\\Sörnmo_Laguna_2005_Chapter 6 - The Electrocardiogram—A Brief Background.pdf;C\:\\Users\\selinederooij\\Zotero\\storage\\6U7J9KP4\\B9780124375529500064.html}
}

@incollection{sornmo2005ChapterElectroencephalogramBrief,
  title = {Chapter 2 - {{The Electroencephalogram}}—{{A Brief Background}}},
  booktitle = {Bioelectrical {{Signal Processing}} in {{Cardiac}} and {{Neurological Applications}}},
  author = {Sörnmo, Leif and Laguna, Pablo},
  editor = {Sörnmo, Leif and Laguna, Pablo},
  date = {2005-01-01},
  series = {Biomedical {{Engineering}}},
  pages = {25--53},
  publisher = {{Academic Press}},
  location = {{Burlington}},
  doi = {10.1016/B978-012437552-9/50002-7},
  url = {https://www.sciencedirect.com/science/article/pii/B9780124375529500027},
  urldate = {2022-04-28},
  isbn = {978-0-12-437552-9},
  langid = {english},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Sörnmo_Laguna\\2005\\Sörnmo_Laguna_2005_Chapter 2 - The Electroencephalogram—A Brief Background.pdf;C\:\\Users\\selinederooij\\Zotero\\storage\\KFAD5JGI\\B9780124375529500027.html}
}

@incollection{sornmo2005ChapterElectromyogram,
  title = {Chapter 5 - {{The Electromyogram}}},
  booktitle = {Bioelectrical {{Signal Processing}} in {{Cardiac}} and {{Neurological Applications}}},
  author = {Sörnmo, Leif and Laguna, Pablo},
  editor = {Sörnmo, Leif and Laguna, Pablo},
  date = {2005-01-01},
  series = {Biomedical {{Engineering}}},
  pages = {337--410},
  publisher = {{Academic Press}},
  location = {{Burlington}},
  doi = {10.1016/B978-012437552-9/50005-2},
  url = {https://www.sciencedirect.com/science/article/pii/B9780124375529500052},
  urldate = {2022-04-28},
  isbn = {978-0-12-437552-9},
  langid = {english},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Sörnmo_Laguna\\2005\\Sörnmo_Laguna_2005_Chapter 5 - The Electromyogram.pdf;C\:\\Users\\selinederooij\\Zotero\\storage\\CQGTDXCB\\B9780124375529500052.html}
}

@incollection{sornmo2005ChapterEvokedPotentials,
  title = {Chapter 4 - {{Evoked Potentials}}},
  booktitle = {Bioelectrical {{Signal Processing}} in {{Cardiac}} and {{Neurological Applications}}},
  author = {Sörnmo, Leif and Laguna, Pablo},
  editor = {Sörnmo, Leif and Laguna, Pablo},
  date = {2005-01-01},
  series = {Biomedical {{Engineering}}},
  pages = {181--336},
  publisher = {{Academic Press}},
  location = {{Burlington}},
  doi = {10.1016/B978-012437552-9/50004-0},
  url = {https://www.sciencedirect.com/science/article/pii/B9780124375529500040},
  urldate = {2022-04-28},
  isbn = {978-0-12-437552-9},
  langid = {english},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Sörnmo_Laguna\\2005\\Sörnmo_Laguna_2005_Chapter 4 - Evoked Potentials.pdf;C\:\\Users\\selinederooij\\Zotero\\storage\\Y3SK49WY\\B9780124375529500040.html}
}

@incollection{sornmo2005ChapterIntroduction,
  title = {Chapter 1 - {{Introduction}}},
  booktitle = {Bioelectrical {{Signal Processing}} in {{Cardiac}} and {{Neurological Applications}}},
  author = {Sörnmo, Leif and Laguna, Pablo},
  editor = {Sörnmo, Leif and Laguna, Pablo},
  date = {2005-01-01},
  series = {Biomedical {{Engineering}}},
  pages = {1--24},
  publisher = {{Academic Press}},
  location = {{Burlington}},
  doi = {10.1016/B978-012437552-9/50001-5},
  url = {https://www.sciencedirect.com/science/article/pii/B9780124375529500015},
  urldate = {2022-04-28},
  isbn = {978-0-12-437552-9},
  langid = {english},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Sörnmo_Laguna\\2005\\Sörnmo_Laguna_2005_Chapter 1 - Introduction.pdf;C\:\\Users\\selinederooij\\Zotero\\storage\\RBEL5YFA\\B9780124375529500015.html}
}

@incollection{sornmo2005Copyright,
  title = {Copyright},
  booktitle = {Bioelectrical {{Signal Processing}} in {{Cardiac}} and {{Neurological Applications}}},
  editor = {Sörnmo, Leif and Laguna, Pablo},
  date = {2005-01-01},
  series = {Biomedical {{Engineering}}},
  pages = {iv},
  publisher = {{Academic Press}},
  location = {{Burlington}},
  doi = {10.1016/B978-0-12-437552-9.50013-1},
  url = {https://www.sciencedirect.com/science/article/pii/B9780124375529500131},
  urldate = {2022-04-28},
  isbn = {978-0-12-437552-9},
  langid = {english},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\undefined\\2005\\2005_Copyright.pdf;C\:\\Users\\selinederooij\\Zotero\\storage\\NJ3QEHSI\\B9780124375529500131.html}
}

@incollection{sornmo2005FrontMatter,
  title = {Front {{Matter}}},
  booktitle = {Bioelectrical {{Signal Processing}} in {{Cardiac}} and {{Neurological Applications}}},
  editor = {Sörnmo, Leif and Laguna, Pablo},
  date = {2005-01-01},
  series = {Biomedical {{Engineering}}},
  pages = {iii},
  publisher = {{Academic Press}},
  location = {{Burlington}},
  doi = {10.1016/B978-0-12-437552-9.50012-X},
  url = {https://www.sciencedirect.com/science/article/pii/B978012437552950012X},
  urldate = {2022-04-28},
  isbn = {978-0-12-437552-9},
  langid = {english},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\NWCPHFBJ\\B978012437552950012X.html}
}

@incollection{sornmo2005Index,
  title = {Index},
  booktitle = {Bioelectrical {{Signal Processing}} in {{Cardiac}} and {{Neurological Applications}}},
  editor = {Sörnmo, Leif and Laguna, Pablo},
  date = {2005-01-01},
  series = {Biomedical {{Engineering}}},
  pages = {661--668},
  publisher = {{Academic Press}},
  location = {{Burlington}},
  doi = {10.1016/B978-012437552-9/50011-8},
  url = {https://www.sciencedirect.com/science/article/pii/B9780124375529500118},
  urldate = {2022-04-28},
  isbn = {978-0-12-437552-9},
  langid = {english}
}

@incollection{sornmo2005Preface,
  title = {Preface},
  booktitle = {Bioelectrical {{Signal Processing}} in {{Cardiac}} and {{Neurological Applications}}},
  author = {Sörnmo, Leif and Laguna, Pablo},
  editor = {Sörnmo, Leif and Laguna, Pablo},
  date = {2005-01-01},
  series = {Biomedical {{Engineering}}},
  pages = {vii-xiii},
  publisher = {{Academic Press}},
  location = {{Burlington}},
  doi = {10.1016/B978-012437552-9/50000-3},
  url = {https://www.sciencedirect.com/science/article/pii/B9780124375529500003},
  urldate = {2022-04-28},
  isbn = {978-0-12-437552-9},
  langid = {english},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Sörnmo_Laguna\\2005\\Sörnmo_Laguna_2005_Preface.pdf;C\:\\Users\\selinederooij\\Zotero\\storage\\HN9TM7QT\\B9780124375529500003.html}
}

@article{steele2021MixedFilteringApproach,
  title = {A {{Mixed Filtering Approach}} for {{Real-Time Seizure State Tracking Using Multi-Channel Electroencephalography Data}}},
  author = {Steele, Alexander G. and Parekh, Sankalp and Azgomi, Hamid Fekri and Ahmadi, Mohammad Badri and Craik, Alexander and Pati, Sandipan and Francis, Joseph T. and Contreras-Vidal, Jose L. and Faghih, Rose T.},
  date = {2021},
  journaltitle = {IEEE Transactions on Neural Systems and Rehabilitation Engineering},
  volume = {29},
  pages = {2037--2045},
  issn = {1558-0210},
  doi = {10.1109/TNSRE.2021.3113888},
  abstract = {Real-time continuous tracking of seizure state is necessary to develop feedback neuromodulation therapy that can prevent or terminate a seizure early. Due to its high temporal resolution, high scalp coverage, and non-invasive applicability, electroencephalography (EEG) is a good candidate for seizure tracking. In this research, we make multiple seizure state estimations using a mixed-filter and multiple channels found over the entire sensor space; then by applying a Kalman filter, we produce a single seizure state estimation made up of these individual estimations. Using a modified wrapper feature selection, we determine two optimal features of mixed data type, one continuous and one binary analyzing all available channels. These features are used in a state-space framework to model the continuous hidden seizure state. Expectation maximization is performed offline on the training and validation data sets to estimate unknown parameters. The seizure state estimation process is performed for multiple channels, and the seizure state estimation is derived using a square-root Kalman filter. A second expectation maximization step is utilized to estimate the unknown square-root Kalman filter parameters. This method is tested in a real-time applicable way for seizure state estimation. Applying this approach, we obtain a single seizure state estimation with quantitative information about the likelihood of a seizure occurring, which we call seizure probability. Our results on the experimental data (CHB-MIT EEG database) validate the proposed estimation method and we achieve an average accuracy, sensitivity, and specificity of 92.7\%, 92.8\%, and 93.4\%, respectively. The potential applications of this seizure estimation model are for closed-loop neuromodulation and long-term quantitative analysis of seizure treatment efficacy.},
  eventtitle = {{{IEEE Transactions}} on {{Neural Systems}} and {{Rehabilitation Engineering}}},
  keywords = {Brain modeling,Electroencephalography,Electroencephalography (EEG),epilepsy,Estimation,Feature extraction,Kalman filter,Kalman filters,neurofeedback,real-time detection,Real-time systems,state estimation,State estimation,state-space methods,unread},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Steele et al\\2021\\Steele et al_2021_A Mixed Filtering Approach for Real-Time Seizure State Tracking Using.pdf;C\:\\Users\\selinederooij\\Zotero\\storage\\B6TL792T\\9541179.html}
}

@inproceedings{stoudenmireSupervisedLearningTensor2016,
  title = {Supervised {{Learning}} with {{Tensor Networks}}},
  booktitle = {Advances in {{Neural Information Processing Systems}}},
  author = {Stoudenmire, Edwin and Schwab, David J},
  date = {2016},
  volume = {29},
  publisher = {{Curran Associates, Inc.}},
  url = {https://papers.nips.cc/paper/2016/hash/5314b9674c86e3f9d1ba25ef9bb32895-Abstract.html},
  urldate = {2022-03-07},
  keywords = {unread},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Stoudenmire_Schwab_2016_Supervised Learning with Tensor Networks.pdf}
}

@article{subasi2007EEGSignalClassification,
  title = {{{EEG}} Signal Classification Using Wavelet Feature Extraction and a Mixture of Expert Model},
  author = {Subasi, Abdulhamit},
  date = {2007-05-01},
  journaltitle = {Expert Systems with Applications},
  shortjournal = {Expert Systems with Applications},
  volume = {32},
  number = {4},
  pages = {1084--1093},
  issn = {0957-4174},
  doi = {10.1016/j.eswa.2006.02.005},
  url = {https://www.sciencedirect.com/science/article/pii/S0957417406000844},
  urldate = {2022-03-17},
  abstract = {Mixture of experts (ME) is modular neural network architecture for supervised learning. A double-loop Expectation-Maximization (EM) algorithm has been introduced to the ME network structure for detection of epileptic seizure. The detection of epileptiform discharges in the EEG is an important component in the diagnosis of epilepsy. EEG signals were decomposed into the frequency sub-bands using discrete wavelet transform (DWT). Then these sub-band frequencies were used as an input to a ME network with two discrete outputs: normal and epileptic. In order to improve accuracy, the outputs of expert networks were combined according to a set of local weights called the “gating function”. The invariant transformations of the ME probability density functions include the permutations of the expert labels and the translations of the parameters in the gating functions. The performance of the proposed model was evaluated in terms of classification accuracies and the results confirmed that the proposed ME network structure has some potential in detecting epileptic seizures. The ME network structure achieved accuracy rates which were higher than that of the stand-alone neural network model.},
  langid = {english},
  keywords = {Discrete wavelet transform (DWT),Electroencephalogram (EEG),Epileptic seizure,Expectation-Maximization (EM) algorithm,Mixture of experts,unread},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Subasi\\2007\\Subasi_2007_EEG signal classification using wavelet feature extraction and a mixture of.pdf}
}

@article{subasi2010EEGSignalClassification,
  title = {{{EEG}} Signal Classification Using {{PCA}}, {{ICA}}, {{LDA}} and Support Vector Machines},
  author = {Subasi, Abdulhamit and Ismail Gursoy, M.},
  date = {2010-12-01},
  journaltitle = {Expert Systems with Applications},
  shortjournal = {Expert Systems with Applications},
  volume = {37},
  number = {12},
  pages = {8659--8666},
  issn = {0957-4174},
  doi = {10.1016/j.eswa.2010.06.065},
  url = {https://www.sciencedirect.com/science/article/pii/S0957417410005695},
  urldate = {2022-03-17},
  abstract = {In this work, we proposed a versatile signal processing and analysis framework for Electroencephalogram (EEG). Within this framework the signals were decomposed into the frequency sub-bands using DWT and a set of statistical features was extracted from the sub-bands to represent the distribution of wavelet coefficients. Principal components analysis (PCA), independent components analysis (ICA) and linear discriminant analysis (LDA) is used to reduce the dimension of data. Then these features were used as an input to a support vector machine (SVM) with two discrete outputs: epileptic seizure or not. The performance of classification process due to different methods is presented and compared to show the excellent of classification process. These findings are presented as an example of a method for training, and testing a seizure prediction method on data from individual petit mal epileptic patients. Given the heterogeneity of epilepsy, it is likely that methods of this type will be required to configure intelligent devices for treating epilepsy to each individual’s neurophysiology prior to clinical operation.},
  langid = {english},
  keywords = {Discrete wavelet transform (DWT),Electroencephalogram (EEG),Epileptic seizure,Independent component analysis (ICA),Linear discriminant analysis (LDA),Principal component analysis (PCA),read_nonote,Support vector machines (SVM)},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Subasi_Ismail Gursoy\\2010\\Subasi_Ismail Gursoy_2010_EEG signal classification using PCA, ICA, LDA and support vector machines.pdf;C\:\\Users\\selinederooij\\Zotero\\storage\\B2UL796C\\S0957417410005695.html}
}

@article{suykens1999LeastSquaresSupport,
  title = {Least {{Squares Support Vector Machine Classifiers}}},
  author = {Suykens, J.A.K. and Vandewalle, J.},
  date = {1999-06-01},
  journaltitle = {Neural Processing Letters},
  shortjournal = {Neural Processing Letters},
  volume = {9},
  number = {3},
  pages = {293--300},
  issn = {1573-773X},
  doi = {10.1023/A:1018628609742},
  url = {https://doi.org/10.1023/A:1018628609742},
  urldate = {2022-08-04},
  abstract = {In this letter we discuss a least squares version for support vector machine (SVM) classifiers. Due to equality type constraints in the formulation, the solution follows from solving a set of linear equations, instead of quadratic programming for classical SVM's. The approach is illustrated on a two-spiral benchmark classification problem.},
  langid = {english},
  keywords = {classification,linear least squares,radial basis function kernel,support vector machines},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Suykens_Vandewalle\\1999\\Suykens_Vandewalle_1999_Least Squares Support Vector Machine Classifiers.pdf}
}

@article{tao2007SupervisedTensorLearning,
  title = {Supervised Tensor Learning},
  author = {Tao, Dacheng and Li, Xuelong and Wu, Xindong and Hu, Weiming and Maybank, Stephen J.},
  date = {2007-09},
  journaltitle = {Knowledge and Information Systems},
  shortjournal = {Knowl Inf Syst},
  volume = {13},
  number = {1},
  pages = {1--42},
  issn = {0219-1377, 0219-3116},
  doi = {10.1007/s10115-006-0050-6},
  url = {http://link.springer.com/10.1007/s10115-006-0050-6},
  urldate = {2022-03-29},
  abstract = {Tensor representation is helpful to reduce the small sample size problem in discriminative subspace selection. As pointed by this paper, this is mainly because the structure information of objects in computer vision research is a reasonable constraint to reduce the number of unknown parameters used to represent a learning model. Therefore, we apply this information to the vector-based learning and generalize the vector-based learning to the tensor-based learning as the supervised tensor learning (STL) framework, which accepts tensors as input. To obtain the solution of STL, the alternating projection optimization procedure is developed. The STL framework is a combination of the convex optimization and the operations in multilinear algebra. The tensor representation helps reduce the overfitting problem in vector-based learning. Based on STL and its alternating projection optimization procedure, we generalize support vector machines, minimax probability machine, Fisher discriminant analysis, and distance metric learning, to support tensor machines, tensor minimax probability machine, tensor Fisher discriminant analysis, and the multiple distance metrics learning, respectively. We also study the iterative procedure for feature extraction within STL. To examine the effectiveness of STL, we implement the tensor minimax probability machine for image classification. By comparing with minimax probability machine, the tensor version reduces the overfitting problem.},
  langid = {english},
  keywords = {unread},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\4GVSRDCR\\Tao et al. - 2007 - Supervised tensor learning.pdf}
}

@book{theodoridis2020MachineLearningBayesian,
  title = {Machine Learning: A {{Bayesian}} and Optimization Perspective},
  shorttitle = {Machine Learning},
  author = {Theodoridis, Sergios},
  date = {2020},
  edition = {2nd edition},
  publisher = {{Elsevier, Academic Press}},
  location = {{London}},
  isbn = {978-0-12-818803-3},
  langid = {english},
  pagetotal = {1131},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\PHAQQQWA\\Theodoridis - 2020 - Machine learning a Bayesian and optimization pers.pdf}
}

@article{thijs2019EpilepsyAdults,
  title = {Epilepsy in Adults},
  author = {Thijs, Roland D and Surges, Rainer and O'Brien, Terence J and Sander, Josemir W},
  date = {2019-02},
  journaltitle = {The Lancet},
  shortjournal = {The Lancet},
  volume = {393},
  number = {10172},
  pages = {689--701},
  issn = {01406736},
  doi = {10.1016/S0140-6736(18)32596-0},
  url = {https://linkinghub.elsevier.com/retrieve/pii/S0140673618325960},
  urldate = {2022-03-08},
  langid = {english},
  keywords = {read_nonote},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\BZGX47Q9\\Thijs et al. - 2019 - Epilepsy in adults.pdf}
}

@article{trinka2015DefinitionClassificationStatus,
  title = {A Definition and Classification of Status Epilepticus – {{Report}} of the {{ILAE Task Force}} on {{Classification}} of {{Status Epilepticus}}},
  author = {Trinka, Eugen and Cock, Hannah and Hesdorffer, Dale and Rossetti, Andrea O. and Scheffer, Ingrid E. and Shinnar, Shlomo and Shorvon, Simon and Lowenstein, Daniel H.},
  date = {2015},
  journaltitle = {Epilepsia},
  volume = {56},
  number = {10},
  pages = {1515--1523},
  issn = {1528-1167},
  doi = {10.1111/epi.13121},
  url = {https://onlinelibrary.wiley.com/doi/abs/10.1111/epi.13121},
  urldate = {2022-03-17},
  abstract = {The Commission on Classification and Terminology and the Commission on Epidemiology of the International League Against Epilepsy (ILAE) have charged a Task Force to revise concepts, definition, and classification of status epilepticus (SE). The proposed new definition of SE is as follows: Status epilepticus is a condition resulting either from the failure of the mechanisms responsible for seizure termination or from the initiation of mechanisms, which lead to abnormally, prolonged seizures (after time point t1). It is a condition, which can have long-term consequences (after time point t2), including neuronal death, neuronal injury, and alteration of neuronal networks, depending on the type and duration of seizures. This definition is conceptual, with two operational dimensions: the first is the length of the seizure and the time point (t1) beyond which the seizure should be regarded as “continuous seizure activity.” The second time point (t2) is the time of ongoing seizure activity after which there is a risk of long-term consequences. In the case of convulsive (tonic–clonic) SE, both time points (t1 at 5 min and t2 at 30 min) are based on animal experiments and clinical research. This evidence is incomplete, and there is furthermore considerable variation, so these time points should be considered as the best estimates currently available. Data are not yet available for other forms of SE, but as knowledge and understanding increase, time points can be defined for specific forms of SE based on scientific evidence and incorporated into the definition, without changing the underlying concepts. A new diagnostic classification system of SE is proposed, which will provide a framework for clinical diagnosis, investigation, and therapeutic approaches for each patient. There are four axes: (1) semiology; (2) etiology; (3) electroencephalography (EEG) correlates; and (4) age. Axis 1 (semiology) lists different forms of SE divided into those with prominent motor systems, those without prominent motor systems, and currently indeterminate conditions (such as acute confusional states with epileptiform EEG patterns). Axis 2 (etiology) is divided into subcategories of known and unknown causes. Axis 3 (EEG correlates) adopts the latest recommendations by consensus panels to use the following descriptors for the EEG: name of pattern, morphology, location, time-related features, modulation, and effect of intervention. Finally, axis 4 divides age groups into neonatal, infancy, childhood, adolescent and adulthood, and elderly.},
  langid = {english},
  keywords = {Classification,Definition,read_nonote,Seizure,Seizure duration,Status epilepticus},
  annotation = {\_eprint: https://onlinelibrary.wiley.com/doi/pdf/10.1111/epi.13121},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Trinka et al\\2015\\Trinka et al_2015_A definition and classification of status epilepticus – Report of the ILAE Task.pdf;C\:\\Users\\selinederooij\\Zotero\\storage\\3LLZ2R6X\\epi.html}
}

@article{tsiouris2018LongShortTermMemory,
  title = {A {{Long Short-Term Memory}} Deep Learning Network for the Prediction of Epileptic Seizures Using {{EEG}} Signals},
  author = {Tsiouris, Κostas Μ. and Pezoulas, Vasileios C. and Zervakis, Michalis and Konitsiotis, Spiros and Koutsouris, Dimitrios D. and Fotiadis, Dimitrios I.},
  date = {2018-08-01},
  journaltitle = {Computers in Biology and Medicine},
  shortjournal = {Computers in Biology and Medicine},
  volume = {99},
  pages = {24--37},
  issn = {0010-4825},
  doi = {10.1016/j.compbiomed.2018.05.019},
  url = {https://www.sciencedirect.com/science/article/pii/S001048251830132X},
  urldate = {2022-05-16},
  abstract = {The electroencephalogram (EEG) is the most prominent means to study epilepsy and capture changes in electrical brain activity that could declare an imminent seizure. In this work, Long Short-Term Memory (LSTM) networks are introduced in epileptic seizure prediction using EEG signals, expanding the use of deep learning algorithms with convolutional neural networks (CNN). A pre-analysis is initially performed to find the optimal architecture of the LSTM network by testing several modules and layers of memory units. Based on these results, a two-layer LSTM network is selected to evaluate seizure prediction performance using four different lengths of preictal windows, ranging from 15\,min to 2\,h. The LSTM model exploits a wide range of features extracted prior to classification, including time and frequency domain features, between EEG channels cross-correlation and graph theoretic features. The evaluation is performed using long-term EEG recordings from the open CHB-MIT Scalp EEG database, suggest that the proposed methodology is able to predict all 185 seizures, providing high rates of seizure prediction sensitivity and low false prediction rates (FPR) of 0.11–0.02 false alarms per hour, depending on the duration of the preictal window. The proposed LSTM-based methodology delivers a significant increase in seizure prediction performance compared to both traditional machine learning techniques and convolutional neural networks that have been previously evaluated in the literature.},
  langid = {english},
  keywords = {Deep learning,EEG,Epilepsy,LSTM model,Seizure prediction,unread},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Tsiouris et al\\2018\\Tsiouris et al_2018_A Long Short-Term Memory deep learning network for the prediction of epileptic.pdf;C\:\\Users\\selinederooij\\Zotero\\storage\\PLHQ3DKZ\\S001048251830132X.html}
}

@article{ullah2010AssimilatingSeizureDynamics,
  title = {Assimilating {{Seizure Dynamics}}},
  author = {Ullah, Ghanim and Schiff, Steven J.},
  date = {2010-05-06},
  journaltitle = {PLOS Computational Biology},
  shortjournal = {PLOS Computational Biology},
  volume = {6},
  number = {5},
  pages = {e1000776},
  publisher = {{Public Library of Science}},
  issn = {1553-7358},
  doi = {10.1371/journal.pcbi.1000776},
  url = {https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1000776},
  urldate = {2022-03-21},
  abstract = {Observability of a dynamical system requires an understanding of its state—the collective values of its variables. However, existing techniques are too limited to measure all but a small fraction of the physical variables and parameters of neuronal networks. We constructed models of the biophysical properties of neuronal membrane, synaptic, and microenvironment dynamics, and incorporated them into a model-based predictor-controller framework from modern control theory. We demonstrate that it is now possible to meaningfully estimate the dynamics of small neuronal networks using as few as a single measured variable. Specifically, we assimilate noisy membrane potential measurements from individual hippocampal neurons to reconstruct the dynamics of networks of these cells, their extracellular microenvironment, and the activities of different neuronal types during seizures. We use reconstruction to account for unmeasured parts of the neuronal system, relating micro-domain metabolic processes to cellular excitability, and validate the reconstruction of cellular dynamical interactions against actual measurements. Data assimilation, the fusing of measurement with computational models, has significant potential to improve the way we observe and understand brain dynamics.},
  langid = {english},
  keywords = {Dynamical systems,Hippocampus,Interneurons,Kalman filter,Membrane potential,Neural networks,Neurons,Pyramidal cells},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Ullah_Schiff\\2010\\Ullah_Schiff_2010_Assimilating Seizure Dynamics.pdf;C\:\\Users\\selinederooij\\Zotero\\storage\\WC347JBT\\article.html}
}

@article{vandecasteele2020VisualSeizureAnnotation,
  title = {Visual Seizure Annotation and Automated Seizure Detection Using Behind‐the‐ear Electroencephalographic Channels},
  author = {Vandecasteele, Kaat and De Cooman, Thomas and Dan, Jonathan and Cleeren, Evy and Van Huffel, Sabine and Hunyadi, Borbála and Van Paesschen, Wim},
  date = {2020-04},
  journaltitle = {Epilepsia},
  shortjournal = {Epilepsia},
  volume = {61},
  number = {4},
  pages = {766--775},
  issn = {0013-9580, 1528-1167},
  doi = {10.1111/epi.16470},
  url = {https://onlinelibrary.wiley.com/doi/10.1111/epi.16470},
  urldate = {2022-03-08},
  abstract = {Objective: Seizure diaries kept by patients are unreliable. Automated electroencephalography (EEG)-based seizure detection systems are a useful support tool to objectively detect and register seizures during long-term video-EEG recording. However, this standard full scalp-EEG recording setup is of limited use outside the hospital, and a discreet, wearable device is needed for capturing seizures in the home setting. We are developing a wearable device that records EEG with behind-the-ear electrodes. In this study, we determined whether the recognition of ictal patterns using only behind-the-ear EEG channels is possible. Second, an automated seizure detection algorithm was developed using only those behind-the-ear EEG channels.},
  langid = {english},
  keywords = {read_nonote},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\49MXYWRT\\Vandecasteele et al. - 2020 - Visual seizure annotation and automated seizure de.pdf}
}

@article{vandecasteele2020VisualSeizureAnnotationb,
  title = {Visual Seizure Annotation and Automated Seizure Detection Using Behind‐the‐ear Electroencephalographic Channels},
  author = {Vandecasteele, Kaat and De Cooman, Thomas and Dan, Jonathan and Cleeren, Evy and Van Huffel, Sabine and Hunyadi, Borbála and Van Paesschen, Wim},
  date = {2020-04},
  journaltitle = {Epilepsia},
  shortjournal = {Epilepsia},
  volume = {61},
  number = {4},
  pages = {766--775},
  issn = {0013-9580, 1528-1167},
  doi = {10.1111/epi.16470},
  url = {https://onlinelibrary.wiley.com/doi/10.1111/epi.16470},
  urldate = {2022-03-08},
  abstract = {Objective: Seizure diaries kept by patients are unreliable. Automated electroencephalography (EEG)-based seizure detection systems are a useful support tool to objectively detect and register seizures during long-term video-EEG recording. However, this standard full scalp-EEG recording setup is of limited use outside the hospital, and a discreet, wearable device is needed for capturing seizures in the home setting. We are developing a wearable device that records EEG with behind-the-ear electrodes. In this study, we determined whether the recognition of ictal patterns using only behind-the-ear EEG channels is possible. Second, an automated seizure detection algorithm was developed using only those behind-the-ear EEG channels.},
  langid = {english},
  keywords = {read_nonote}
}

@article{vandecasteele2021PowerECGMultimodal,
  title = {The Power of {{ECG}} in Multimodal Patient‐specific Seizure Monitoring: {{Added}} Value to an {{EEG}}‐based Detector Using Limited Channels},
  shorttitle = {The Power of {{ECG}} in Multimodal Patient‐specific Seizure Monitoring},
  author = {Vandecasteele, Kaat and De Cooman, Thomas and Chatzichristos, Christos and Cleeren, Evy and Swinnen, Lauren and Macea Ortiz, Jaiver and Van Huffel, Sabine and Dümpelmann, Matthias and Schulze‐Bonhage, Andreas and De Vos, Maarten and Van Paesschen, Wim and Hunyadi, Borbála},
  date = {2021-10},
  journaltitle = {Epilepsia},
  shortjournal = {Epilepsia},
  volume = {62},
  number = {10},
  pages = {2333--2343},
  issn = {0013-9580, 1528-1167},
  doi = {10.1111/epi.16990},
  url = {https://onlinelibrary.wiley.com/doi/10.1111/epi.16990},
  urldate = {2022-03-08},
  abstract = {Objective: Wearable seizure detection devices could provide more reliable seizure documentation outside the hospital compared to seizure self-­reporting by patients, which is the current standard. Previously, during the SeizeIT1 project, we studied seizure detection based on behind-­the-­ear electroencephalography (EEG). However, the obtained sensitivities were too low for practical use, because not all seizures are associated with typical ictal EEG patterns. Therefore, in this paper, we aim to develop a multimodal automated seizure detection algorithm integrating behind-t­he-­ear EEG and electrocardiography (ECG) for detecting focal seizures. In this framework, we quantified the added value of ECG to behind-­the-­ear EEG.},
  langid = {english},
  keywords = {read_nonote},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\FJ6B987N\\Vandecasteele et al. - 2021 - The power of ECG in multimodal patient‐specific se.pdf}
}

@inproceedings{vaneyndhoven2018SINGLECHANNELEEGCLASSIFICATION,
  title = {{{SINGLE-CHANNEL EEG CLASSIFICATION BY MULTI-CHANNEL TENSOR SUBSPACE LEARNING AND REGRESSION}}},
  booktitle = {2018 {{IEEE}} 28th {{International Workshop}} on {{Machine Learning}} for {{Signal Processing}} ({{MLSP}})},
  author = {Van Eyndhoven, Simon and Boussé, Martijn and Hunyadi, Borbála and De Lathauwer, Lieven and Van Huffel, Sabine},
  date = {2018-09},
  pages = {1--6},
  issn = {1551-2541},
  doi = {10.1109/MLSP.2018.8516927},
  abstract = {The classification of brain states using neural recordings such as electroencephalography (EEG) finds applications in both medical and non-medical contexts, such as detecting epileptic seizures or discriminating mental states in brain-computer interfaces, respectively. Although this endeavor is well-established, existing solutions are typically restricted to lab or hospital conditions because they operate on recordings from a set of EEG electrodes that covers the whole head. By contrast, a true breakthrough for these applications would be the deployment `in the real world', by means of wearable devices that encompass just one (or a few) channels. Such a reduction of the available information inevitably makes the classification task more challenging. We tackle this issue by means of a multilinear subspace learning step (using data from multiple channels during training) and subsequently solving a regression problem with a low-rank structure to classify new trials (using data from only a single channel during testing). We demonstrate the feasibility of this approach on EEG data recorded during a mental arithmetic task.},
  eventtitle = {2018 {{IEEE}} 28th {{International Workshop}} on {{Machine Learning}} for {{Signal Processing}} ({{MLSP}})},
  keywords = {Brain-computer interface (BCI),Delay effects,Electrodes,Electroencephalography,multi-linear algebra,printed,subspace learning,Task analysis,Tensile stress,tensor,tensor regression,Testing,Training,unread,wearable electroencephalography (EEG)},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Van Eyndhoven et al\\2018\\Van Eyndhoven et al_2018_SINGLE-CHANNEL EEG CLASSIFICATION BY MULTI-CHANNEL TENSOR SUBSPACE LEARNING AND.pdf;C\:\\Users\\selinederooij\\Zotero\\storage\\UP9XKW6D\\8516927.html}
}

@article{vervliet2014BreakingCurseDimensionality,
  title = {Breaking the {{Curse}} of {{Dimensionality Using Decompositions}} of {{Incomplete Tensors}}: {{Tensor-based}} Scientific Computing in Big Data Analysis},
  shorttitle = {Breaking the {{Curse}} of {{Dimensionality Using Decompositions}} of {{Incomplete Tensors}}},
  author = {Vervliet, Nico and Debals, Otto and Sorber, Laurent and De Lathauwer, Lieven},
  date = {2014-09},
  journaltitle = {IEEE Signal Processing Magazine},
  shortjournal = {IEEE Signal Process. Mag.},
  volume = {31},
  number = {5},
  pages = {71--79},
  issn = {1053-5888},
  doi = {10.1109/MSP.2014.2329429},
  url = {https://ieeexplore.ieee.org/document/6879619},
  urldate = {2022-03-08},
  langid = {english},
  keywords = {read_nonote},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\AG9YES8I\\Vervliet et al. - 2014 - Breaking the Curse of Dimensionality Using Decompo.pdf}
}

@article{wang2021AutomaticECGClassification,
  title = {Automatic {{ECG Classification Using Continuous Wavelet Transform}} and {{Convolutional Neural Network}}},
  author = {Wang, Tao and Lu, Changhua and Sun, Yining and Yang, Mei and Liu, Chun and Ou, Chunsheng},
  date = {2021-01},
  journaltitle = {Entropy},
  volume = {23},
  number = {1},
  pages = {119},
  publisher = {{Multidisciplinary Digital Publishing Institute}},
  issn = {1099-4300},
  doi = {10.3390/e23010119},
  url = {https://www.mdpi.com/1099-4300/23/1/119},
  urldate = {2022-03-16},
  abstract = {Early detection of arrhythmia and effective treatment can prevent deaths caused by cardiovascular disease (CVD). In clinical practice, the diagnosis is made by checking the electrocardiogram (ECG) beat-by-beat, but this is usually time-consuming and laborious. In the paper, we propose an automatic ECG classification method based on Continuous Wavelet Transform (CWT) and Convolutional Neural Network (CNN). CWT is used to decompose ECG signals to obtain different time-frequency components, and CNN is used to extract features from the 2D-scalogram composed of the above time-frequency components. Considering the surrounding R peak interval (also called RR interval) is also useful for the diagnosis of arrhythmia, four RR interval features are extracted and combined with the CNN features to input into a fully connected layer for ECG classification. By testing in the MIT-BIH arrhythmia database, our method achieves an overall performance of 70.75\%, 67.47\%, 68.76\%, and 98.74\% for positive predictive value, sensitivity, F1-score, and accuracy, respectively. Compared with existing methods, the overall F1-score of our method is increased by 4.75\textasciitilde 16.85\%. Because our method is simple and highly accurate, it can potentially be used as a clinical auxiliary diagnostic tool.},
  issue = {1},
  langid = {english},
  keywords = {arrhythmia,continuous wavelet transform,convolutional neural network,deep learning,ECG classification,heartbeat classification,unread},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Wang et al\\2021\\Wang et al_2021_Automatic ECG Classification Using Continuous Wavelet Transform and.pdf;C\:\\Users\\selinederooij\\Zotero\\storage\\W322SC3K\\119.html}
}

@article{wei2018AutomaticSeizureDetection,
  title = {Automatic Seizure Detection Using Three-Dimensional {{CNN}} Based on Multi-Channel {{EEG}}},
  author = {Wei, Xiaoyan and Zhou, Lin and Chen, Ziyi and Zhang, Liangjun and Zhou, Yi},
  date = {2018-12-07},
  journaltitle = {BMC Medical Informatics and Decision Making},
  shortjournal = {BMC Medical Informatics and Decision Making},
  volume = {18},
  number = {5},
  pages = {111},
  issn = {1472-6947},
  doi = {10.1186/s12911-018-0693-8},
  url = {https://doi.org/10.1186/s12911-018-0693-8},
  urldate = {2022-04-25},
  abstract = {Automated seizure detection from clinical EEG data can reduce the diagnosis time and facilitate targeting treatment for epileptic patients. However, current detection approaches mainly rely on limited features manually designed by domain experts, which are inflexible for the detection of a variety of patterns in a large amount of patients’ EEG data. Moreover, conventional machine learning algorithms for seizure detection cannot accommodate multi-channel Electroencephalogram (EEG) data effectively, which contains both temporal and spatial information. Recently, deep learning technology has been widely applied to perform image processing tasks, which could learns useful features from data and process multi-channel data automatically. To provide an effective system for automatic seizure detection, we proposed a new three-dimensional (3D) convolutional neural network (CNN) structure, whose inputs are multi-channel EEG signals.},
  keywords = {Convolutional neural network,Epilepsy,Multi-channel,Seizure detection,Three-dimensional,unread},
  annotation = {52 citations (Semantic Scholar/DOI) [2022-04-25]},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Wei et al\\2018\\Wei et al_2018_Automatic seizure detection using three-dimensional CNN based on multi-channel.pdf;C\:\\Users\\selinederooij\\Zotero\\storage\\QPBGECG9\\s12911-018-0693-8.html}
}

@article{weselLargeScaleLearningFourier,
  title = {Large-{{Scale Learning}} with {{Fourier Features}} and {{Tensor Decompositions}}},
  author = {Wesel, Frederiek and Batselier, Kim},
  pages = {12},
  abstract = {Random Fourier features provide a way to tackle large-scale machine learning problems with kernel methods. Their slow Monte Carlo convergence rate has motivated the research of deterministic Fourier features whose approximation error can decrease exponentially in the number of basis functions. However, due to their tensor product extension to multiple dimensions, these methods suffer heavily from the curse of dimensionality, limiting their applicability to one, two or threedimensional scenarios. In our approach we overcome said curse of dimensionality by exploiting the tensor product structure of deterministic Fourier features, which enables us to represent the model parameters as a low-rank tensor decomposition. We derive a monotonically converging block coordinate descent algorithm with linear complexity in both the sample size and the dimensionality of the inputs for a regularized squared loss function, allowing to learn a parsimonious model in decomposed form using deterministic Fourier features. We demonstrate by means of numerical experiments how our low-rank tensor approach obtains the same performance of the corresponding nonparametric model, consistently outperforming random Fourier features.},
  langid = {english},
  keywords = {read_nonote},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\DCZPS3P3\\Wesel and Batselier - Large-Scale Learning with Fourier Features and Ten.pdf}
}

@report{WHO2019EpilepsyPublicHealth,
  title = {Epilepsy: a public health imperative: summary},
  shorttitle = {Epilepsy},
  author = {{World Health Organization}},
  date = {2019},
  number = {WHO/MSD/MER/19.2},
  institution = {{World Health Organization}},
  url = {https://apps.who.int/iris/handle/10665/325440},
  urldate = {2022-08-04},
  langid = {arabic},
  pagetotal = {12},
  keywords = {Technical documents},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\World Health Organization\\2019\\World Health Organization_2019_Epilepsy.pdf;C\:\\Users\\selinederooij\\Zotero\\storage\\UXBJW6AA\\325440.html}
}

@article{xiong2021SeizureForecastingUsing,
  title = {Seizure {{Forecasting Using Long-Term Electroencephalography}} and {{Electrocardiogram Data}}},
  author = {Xiong, Wenjuan and Nurse, Ewan S. and Lambert, Elisabeth and Cook, Mark J. and Kameneva, Tatiana},
  date = {2021-09},
  journaltitle = {International Journal of Neural Systems},
  shortjournal = {Int. J. Neur. Syst.},
  volume = {31},
  number = {09},
  pages = {2150039},
  issn = {0129-0657, 1793-6462},
  doi = {10.1142/S0129065721500398},
  url = {https://www.worldscientific.com/doi/abs/10.1142/S0129065721500398},
  urldate = {2022-03-08},
  abstract = {Electroencephalography (EEG) has been used to forecast seizures with varying success. There is an increasing interest to use electrocardiogram (ECG) to help with seizure forecasting. The neural and cardiovascular systems may exhibit critical slowing, which is measured by an increase in variance and autocorrelation of the system, when change from a normal state to an ictal state. To forecast seizures, the variance and autocorrelation of long-term continuous EEG and ECG data from 16 patients were used for analysis. The average period of recordings was 161.9 h, with an average of 9 electrographic seizures in an individual patient. The relationship between seizure onset times and phases of variance and autocorrelation in EEG and ECG data was investigated. The results of forecasting models using critical slowing features, seizure circadian features, and combined critical slowing and circadian features were compared using the receiver-operating characteristic curve. The results demonstrated that the best forecaster was patient-specific and the average area under the curve (AUC) of the best forecaster across patients was 0.68. In 50\% of patients, circadian forecasters had the best performance. Critical slowing forecaster performed best in 19\% of patients. Combined forecaster achieved the best performance in 31\% of patients. The results of this study may help to advance the field of seizure forecasting and lead to the improved quality of life of people who suffer from epilepsy.},
  langid = {english},
  keywords = {read_nonote},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\XVAL3YN6\\Xiong et al. - 2021 - Seizure Forecasting Using Long-Term Electroencepha.pdf}
}

@article{xu2021ClusterbasedOversamplingAlgorithm,
  title = {A Cluster-Based Oversampling Algorithm Combining {{SMOTE}} and k-Means for Imbalanced Medical Data},
  author = {Xu, Zhaozhao and Shen, Derong and Nie, Tiezheng and Kou, Yue and Yin, Nan and Han, Xi},
  date = {2021-09},
  journaltitle = {Information Sciences},
  shortjournal = {Information Sciences},
  volume = {572},
  pages = {574--589},
  issn = {00200255},
  doi = {10.1016/j.ins.2021.02.056},
  url = {https://linkinghub.elsevier.com/retrieve/pii/S0020025521001985},
  urldate = {2022-03-14},
  abstract = {The algorithm of C4.5 decision tree has the advantages of high classification accuracy, fast calculation speed and comprehensible classification rules, so it is widely used for medical data analysis. However, for imbalanced medical data, the classification accuracy of decision trees-based models is not ideal. Therefore, this paper proposes a cluster-based oversampling algorithm (KNSMOTE) combining Synthetic minority oversampling technique (SMOTE) and k-means algorithm. The sample classes clustered by k-means and the original sample classes are calculated to select the ‘‘safe samples” whose sample classes have not been changed. The ‘‘safe samples” are linearly interpolated to synthesize the new samples. The improved SMOTE sets the oversampling ratio according to the imbalance ratio of the original samples, which is used to synthesize the samples whose number is the same as that of the original samples. Compared with other oversampling algorithms on 8 UCI datasets, our algorithm has achieved significant advantages. Our algorithm was applied to the medical datasets, and the average values of the Sensitivity and Specificity indexes of the Random forest (RF) algorithm were 99.84\% and 99.56\%, respectively.},
  langid = {english},
  keywords = {read_nonote},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\ZWYP6BSN\\Xu et al. - 2021 - A cluster-based oversampling algorithm combining S.pdf}
}

@article{yang2020SelectionFeaturesPatientindependent,
  title = {Selection of Features for Patient-Independent Detection of Seizure Events Using Scalp {{EEG}} Signals},
  author = {Yang, Shuhan and Li, Bo and Zhang, Yinda and Duan, Meiyu and Liu, Shuai and Zhang, Yexian and Feng, Xin and Tan, Renbo and Huang, Lan and Zhou, Fengfeng},
  date = {2020-04-01},
  journaltitle = {Computers in Biology and Medicine},
  shortjournal = {Computers in Biology and Medicine},
  volume = {119},
  pages = {103671},
  issn = {0010-4825},
  doi = {10.1016/j.compbiomed.2020.103671},
  url = {https://www.sciencedirect.com/science/article/pii/S0010482520300639},
  urldate = {2022-03-17},
  abstract = {Epilepsy involves brain abnormalities that may cause sudden seizures or other uncontrollable body activities. Epilepsy may have substantial impacts on the patient's quality of life, and its detection heavily relies on tedious and time-consuming manual curation by experienced clinicians, based on EEG signals. Most existing EEG-based seizure detection algorithms are patient-dependent and train a detection model for each patient. A new patient can only be monitored effectively after several episodes of epileptic seizures. This study investigates the patient-independent detection of seizure events using the open dataset CHB-MIT Scalp EEG. First, a novel feature extraction algorithm called MinMaxHist is proposed to measure the topological patterns of the EEG signals. Following this, MinMaxHist and several other feature extraction algorithms are applied to parameterize the EEG signals. Next, a comprehensive series of feature screening and classification optimization experiments are conducted, and finally, an optimized EEG-based seizure detection model is presented that can achieve overall values for accuracy, sensitivity, specificity, Matthews correlation coefficient, and Kappa of 0.8627, 0.8032, 0.9222, 0.7504 and 0.7254, respectively, with only 30 features. The classification accuracy of the method with MinMaxHist features was 0.0464 higher than that without MinMaxHist features. Compared with existing methods, the proposed algorithm achieved higher accuracy and sensitivity, as shown in the experimental results.},
  langid = {english},
  keywords = {EEG,Epileptic seizure detection,Feature selection,MinMaxHist,Nonlinear features,read_nonote,Time-domain feature extraction,unread,XGBoost},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Yang et al\\2020\\Yang et al_2020_Selection of features for patient-independent detection of seizure events using.pdf;C\:\\Users\\selinederooij\\Zotero\\storage\\G9YWJZU6\\S0010482520300639.html}
}

@article{yangTensorTrainRecurrentNeural,
  title = {Tensor-{{Train Recurrent Neural Networks}} for {{Video Classification}}},
  author = {Yang, Yinchong and Krompass, Denis and Tresp, Volker},
  pages = {10},
  abstract = {The Recurrent Neural Networks and their variants have shown promising performances in sequence modeling tasks such as Natural Language Processing. These models, however, turn out to be impractical and difficult to train when exposed to very high-dimensional inputs due to the large input-to-hidden weight matrix. This may have prevented RNNs’ large-scale application in tasks that involve very high input dimensions such as video modeling; current approaches reduce the input dimensions using various feature extractors. To address this challenge, we propose a new, more general and efficient approach by factorizing the input-to-hidden weight matrix using Tensor-Train decomposition which is trained simultaneously with the weights themselves. We test our model on classification tasks using multiple real-world video datasets and achieve competitive performances with state-of-the-art models, even though our model architecture is orders of magnitude less complex. We believe that the proposed approach provides a novel and fundamental building block for modeling highdimensional sequential data with RNN architectures and opens up many possibilities to transfer the expressive and advanced architectures from other domains such as NLP to modeling highdimensional sequential data.},
  langid = {english},
  keywords = {read_nonote},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\KXKJ3Y7R\\Yang et al. - Tensor-Train Recurrent Neural Networks for Video C.pdf}
}

@article{you2020UnsupervisedAutomaticSeizure,
  title = {Unsupervised Automatic Seizure Detection for Focal-Onset Seizures Recorded with behind-the-Ear {{EEG}} Using an Anomaly-Detecting Generative Adversarial Network},
  author = {You, Sungmin and Cho, Baek Hwan and Yook, Soonhyun and Kim, Joo Young and Shon, Young-Min and Seo, Dae-Won and Kim, In Young},
  date = {2020-09-01},
  journaltitle = {Computer Methods and Programs in Biomedicine},
  shortjournal = {Computer Methods and Programs in Biomedicine},
  volume = {193},
  pages = {105472},
  issn = {0169-2607},
  doi = {10.1016/j.cmpb.2020.105472},
  url = {https://www.sciencedirect.com/science/article/pii/S0169260719320000},
  urldate = {2022-05-20},
  abstract = {Background and Objective: Epilepsy is a neurological disorder of the brain, which involves recurrent seizures. An encephalogram (EEG) is a gold standard method in the detection and analysis of epileptic seizures. However, the standard EEG recording system is too obstructive to be used in daily life. Behind-the-ear EEG is an alternative approach to record EEG conveniently. Previous researchers applied machine learning to automatically detect seizures with EEG, but the epileptic EEG waveform contains subtle changes that are difficult to be identified. Furthermore, the extremely small proportion of ictal events in the long-term monitoring may cause the imbalance problem and, consequently, poor prediction performance in supervised learning approaches. In this study, we present an automatic seizure detection algorithm with a generative adversarial network (GAN) trained by unsupervised learning and evaluated it with behind-the-ear EEG. Methods: We recorded behind-the-ear EEGs from 12 patients who have various types of epilepsy. Data were reviewed separately by two epileptologists, who determined the onsets and ends of seizures. First, we conducted unsupervised learning with the normal records for the GAN to learn the representation of normal states. Second, we performed automatic seizure detection with the trained GAN as an anomaly detector. Last, we combined the Gram matrix with other anomaly losses to improve detection performance. Results: The proposed approach achieved detection performance with an area under the receiver operating curve of 0.939 and sensitivity of 96.3\% with a false alarm rate of 0.14 per hour in the test dataset. In addition, we confirmed distinguishability with the distribution of the anomaly scores in terms of EEG frequency bands. Conclusions: It is expected that the proposed anomaly detection via GAN with the behind-the-ear EEG can be effectively used for long-term seizure monitoring in daily life.},
  langid = {english},
  keywords = {Deep learning,Electroencephalography,Epilepsy,Generative adversarial network,Seizures},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\You et al\\2020\\You et al_2020_Unsupervised automatic seizure detection for focal-onset seizures recorded with.pdf;C\:\\Users\\selinederooij\\Zotero\\storage\\3A7K5GEL\\S0169260719320000.html}
}

@inproceedings{yuan2020AutomaticSeizurePrediction,
  title = {Automatic {{Seizure Prediction}} Based on {{Modified Stockwell Transform}} and {{Tensor Decomposition}}},
  booktitle = {2020 {{IEEE International Conference}} on {{Bioinformatics}} and {{Biomedicine}} ({{BIBM}})},
  author = {Yuan, Shasha and Liu, Jinxing and Shang, Junliang and Xu, Fangzhou and Dai, Lingyun and Kong, Xiangzhen},
  date = {2020-12},
  pages = {1503--1509},
  doi = {10.1109/BIBM49941.2020.9313146},
  abstract = {Reliable epileptic seizure prediction is significantly important in improving the life of patients and enhancing the therapy effect. In this paper, a novel seizure prediction algorithm is proposed employing the tensor decomposition on long-term intracranial EEG recordings. The modified Stockwell transform (MST) is conducted on the segmented EEG signals to transform into two-dimensional instantaneous power spectra. Then, the third-order tensor representation of the multi-channel EEG signals are structured with the models of time, frequency and space. Tucker decomposition, one valid tensor decomposition method, is applied to obtain the principal components of the EEG tensors and the smaller core tensors after decomposition are extracted as features of interictal EEG and preictal EEG. After that, the classification of preictal and interictal data is achieved by feeding the features into Bayesian Linear Discriminant Analysis (BLDA) classifier. The evaluation of the proposed algorithm is carried out on the Freiburg EEG database and a sensitivity of 88.49\% for the seizure occurrence period of 30 min, meanwhile, a sensitivity of 97.62\% for the seizure occurrence period of 50 min are yielded with a false alarm rate of 0. 25/h. The results show that this algorithm based on tensor analysis has notable performance for seizure prediction.},
  eventtitle = {2020 {{IEEE International Conference}} on {{Bioinformatics}} and {{Biomedicine}} ({{BIBM}})},
  keywords = {Databases,Electroencephalography,Epilepsy,Feature extraction,Intracranial EEG,modified Stockwell transform Tensor decomposition,Seizure prediction,Tensors,Time-frequency analysis,Training,Transforms},
  file = {C\:\\Users\\selinederooij\\OneDrive - Delft University of Technology\\Zotero\\Yuan et al\\2020\\Yuan et al_2020_Automatic Seizure Prediction based on Modified Stockwell Transform and Tensor.pdf;C\:\\Users\\selinederooij\\Zotero\\storage\\85RW7VGC\\9313146.html}
}

@thesis{zinInvestigationFocalEpilepsy,
  title = {Investigation of Focal Epilepsy Using Graph Signal Processing},
  author = {Zin, Gaia},
  langid = {english},
  keywords = {read_nonote},
  file = {C\:\\Users\\selinederooij\\Zotero\\storage\\KIB5UK4N\\Zin - Investigation of focal epilepsy using graph signal.pdf}
}