Data

Tools

Indexes

Applications

Experiments

Open Source Science

cpsc2021

Paroxysmal Atrial Fibrillation Events Detection from Dynamic ECG Recordings: The 4th China Physiological Signal Challenge 2021

https://github.com/deeppsp/cpsc2021

Science Score: 10.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ○
    CITATION.cff file
  • ○
    codemeta.json file
  • ○
    .zenodo.json file
  • ○
    DOI references
  • ✓
    Academic publication links
    Links to: sciencedirect.com
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (9.4%) to scientific vocabulary
Last synced: 9 months ago · JSON representation

Repository

Paroxysmal Atrial Fibrillation Events Detection from Dynamic ECG Recordings: The 4th China Physiological Signal Challenge 2021

Basic Info
  • Host: GitHub
  • Owner: DeepPSP
  • License: mit
  • Language: Python
  • Default Branch: master
  • Size: 146 MB
Statistics
  • Stars: 7
  • Watchers: 3
  • Forks: 6
  • Open Issues: 2
  • Releases: 0
Created about 5 years ago · Last pushed over 2 years ago
Metadata Files
Readme License Citation

README.md

CPSC2021

Paroxysmal Atrial Fibrillation Events Detection from Dynamic ECG Recordings: The 4th China Physiological Signal Challenge 2021

format-check

Offline generated training data

CPSC2021-sliced on Kaggle.

Graphical Abstract of the Solution

res_pht

Main files

Click to view! * Files required by the submission system - [`entry_2021.py`](entry_2021.py): entry file of the challenge - [`score_2021.py`](score_2021.py): scoring function of the challenge * Files of the solution: - [`cfg.py`](cfg.py): configurations for the preprocessing, augmentation, model, trainer, etc. - [`data_reader.py`](data_reader.py): contains a class which makes reading data, annotations, etc. more easy - [`dataset.py`](dataset.py): torch Dataset which generates tensors for training the models - [`model.py`](model.py): models, adjustification of the architecture is highly flexible - [`trainer.py`](trainer.py): contains a trainer class * Files for analyzing and visualizing experiments: - [`gather_results.py`](gather_results.py) * Test files: - [`test_entry.py`](test_entry.py) * Notebooks (the filenames imply the usages): - [`inspect_data.ipynb`](inspect_data.ipynb) - [`train_models.ipynb`](train_models.ipynb) - [`aggregate_val_res.ipynb`](aggregate_val_res.ipynb)

Remember to change BaseCfg.db_dir to your local data directory.

Results (Rankings)

Results on the hidden test set

Click to view!
NameAffiliationTeam MembersTest_ITest_IIAverage
usstmedUniversity of Shanghai for Science and TechnologyWenjie Cai, Fanli Liu, Bolin Xu, Xuan Wang, Yufeng Ji2.06294.39213.2275
CeZIS1.VSL Software, a.s., Koice, Slovakia;
2.Pavol Jozef afrik University in Koice, Slovakia		Peter Bugata1, Peter Bugata Jr.1, David Gajdos1, David Hudak1,Vladimira Kmecova1, Monika Stankova1, Lubomir Antoni2, Erik Bruoth2, Simon Horvat2, Richard Stana2, Alexander Szabari2, Gabriela Vozarikova22.11283.57162.8422
UNIWAUniversity of West Attica, GreeceLampros Kokkalas, Nicolas A. Tatlas, Stelios M. Potirakis2.01443.38332.6989
lingshui_BME1.Dalian University of Technology;
2.RWTH Aachen University		Yating Hu1, Tengfei Feng2, Hong Tang11.87543.51162.6935
TaoziTianjin Medical University, Beihang UniversityJingsu Kang, Hao Wen 1.99723.09072.5440
Metformin-121National Taiwan University; Academia Sinica; Taiwan Artificial Intelligence Academy FoundationTsai-Min Chen, Yi-Dar Tang, Huan-Hsin Tseng, Wei Luok Ngu, Le-Yin Hsu, Miao-Chen Chiang, Yu-Te Ku, Ming-Yi Hong, Yu Tsao1.62772.66492.1463
MVTECHShanghai Medical Vision Technology Co. Ltd.Yang Hou, Jinlei Li1.79662.43462.1156
FUDU_CarFudan UniversitySen Liu, Yanan Wang, Haijun Jia 1.91471.94731.9310
WHS 1.Central South University
2.China University of Geosciences		Lebing Pan, Jiechen Tang1.85851.92361.8911
Muhammad Uzair Zahid1. Tampere University, Finland;
2. Qatar University, Qatar		Muhammad Uzair Zahid1, Mustafa Serkan Kiranyaz2, Moncef Gabbouj11.81921.94691.8831
DaBinBeijing University of TechnologyFengya Liu, Rui Yu, Shuicai Wu, Guangyu Bin,Zhuhuang Zhou ,Qian Wang1.83520.97281.4040
LastoneKing's College London, UKXinqi Bao, Fenghe Hu0.96161.64301.3023
BSUBeijing Sport UniversityKuan Tao, Lixin Sun1.23841.17101.2047
CUTCMCity University of Hong KongMarshall0.67061.38541.0280
AZ-unetAstraZenecaHannes Whittingham, Long Luu1.11680.77880.9478
AIBI_LABLudong UniversityShuhong Wei, Yipeng Wang, Yu Ji, Yinhao Sun0.78371.10060.9422
CPSC_eieZhejiang University of Technology, ChinaXinyuan Ying, Qing Pan, Ziyou Zhang0.85550.96290.9092
Baseline//0.68190.64850.6652

See the official website for more details.

Results on the validation set

Raw results are gathered into one zip file, the val_res.zip in the results folder

| Network(s) | Merge Rule | Score on Partial Hidden Test Set | Score on Validation Set| |-------------------|---------------|----------------------------------|------------------------| | LSTM | NA | 1.9392 | 2.0621 | | SeqTag | NA | 1.9781 | 2.1577 | | U-Net | NA | 1.3699 | NA | | LSTM + U-Net | Union | 1.7829 | NA | | LSTM + SeqTag | Intersection | 1.9287 | NA | | LSTM + SeqTag | Union | 1.9766 | 2.1682 | | LSTM + SeqTag | New Union | 1.9972 | 2.2179 |

Confusion matrices of the LSTM model and the SeqTag model

              

More detailed analysis using pandas

Citation

See the file CITATIONS.bib. Also at sciencedirect.

References

See the references listed on the sciencedirect webpage.

Owner

  • Name: DeepPSP
  • Login: DeepPSP
  • Kind: organization
  • Location: China

deep learning for physiological signal processing

GitHub Events

Total
  • Watch event: 6
  • Fork event: 1
Last Year
  • Watch event: 6
  • Fork event: 1

Dependencies

requirements.txt pypi
  • biosppy *
  • deprecated *
  • easydict *
  • joblib ==1.0.1
  • numpy ==1.21.0
  • opencv-python *
  • packaging *
  • pandas ==1.2.2
  • peakutils *
  • scikit-learn ==0.24.1
  • scipy ==1.6.1
  • tensorboardX *
  • torch ==1.8.0
  • torch_optimizer *
  • torchsummary *
  • tqdm *
  • wfdb ==3.2.0
.github/workflows/check-formatting.yml actions
  • actions/checkout v3 composite
  • actions/setup-python v4 composite