Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/alexanderbertrandlab/unsupervised-aad-stimulus-reconstruction

MATLAB code for the unsupervised AAD training algorithm based on stimulus reconstruction

https://github.com/alexanderbertrandlab/unsupervised-aad-stimulus-reconstruction

Science Score: 36.0%

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

  • ○
    CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ○
    .zenodo.json file
  • ✓
    DOI references
    Found 6 DOI reference(s) in README
  • ✓
    Academic publication links
    Links to: zenodo.org
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (8.0%) to scientific vocabulary
Last synced: 10 months ago · JSON representation

Repository

MATLAB code for the unsupervised AAD training algorithm based on stimulus reconstruction

Basic Info
  • Host: GitHub
  • Owner: AlexanderBertrandLab
  • License: mit
  • Language: MATLAB
  • Default Branch: main
  • Size: 16.6 KB
Statistics
  • Stars: 0
  • Watchers: 2
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created almost 2 years ago · Last pushed almost 2 years ago
Metadata Files
Readme License

README.md

Unsupervised Self-Adaptive AAD Algorithm based on Stimulus Reconstruction

License

See the LICENSE file for license rights and limitations.

If this code has been useful for you, please cite Geirnaert et al. [1].

About

This repository includes the MATLAB-code for the unsupervised self-adaptive auditory attention decoding (AAD) algorithm based on a stimulus reconstruction decoder presented in Algorithm 1 in Geirnaert et al. [1], and the code to reproduce most experiments in Geirnaert et al. [1]. The datasets on which the experiments are conducted are publicly available [2, 3]. A preprocessing script for the first dataset [2] is provided in preprocess_data.m and replaces that script in the Zenodo-version of [2].

trainUnsupStimRecDec.m contains the core unsupervised training algorithm as presented in Algorithm 1 in Geirnaert et al. [1].

Developed and tested in MATLAB R2021b.

Note: Tensorlab is required (https://www.tensorlab.net/).

Quick guide

  1. Download the dataset from https://zenodo.org/records/4004271 [2].
  2. Run preprocess_data.m.
  3. Run main.m.
  4. Add your own datasets and play around!

Contact

Simon Geirnaert
KU Leuven, Department of Electrical Engineering (ESAT), STADIUS Center for Dynamical Systems, Signal Processing and Data Analytics
KU Leuven, Department of Neurosciences, Research Group ExpORL
Leuven.AI - KU Leuven institute for AI
simon.geirnaert@esat.kuleuven.be

Tom Francart KU Leuven, Department of Neurosciences, Research Group ExpORL
Leuven.AI - KU Leuven institute for AI
tom.francart@kuleuven.be

Alexander Bertrand KU Leuven, Department of Electrical Engineering (ESAT), STADIUS Center for Dynamical Systems, Signal Processing and Data Analytics
Leuven.AI - KU Leuven institute for AI
alexander.bertrand@esat.kuleuven.be

## References

[1] S. Geirnaert, T. Francart, and A. Bertrand, “Unsupervised Self-Adaptive Auditory Attention Decoding,” IEEE Journal on Biomedical and Health Informatics, vol. 25, no. 10, pp. 3955–3966, 2021 https://doi.org/10.1109/JBHI.2021.3075631.

[2] N. Das, T. Francart, and A. Bertrand, “Auditory Attention Detection Dataset KULeuven”. Zenodo, Aug. 30, 2019. doi: 10.5281/zenodo.4004271.

[3] S. A. Fuglsang, D. D. E. Wong, and J. Hjortkjær, “EEG and audio dataset for auditory attention decoding”. Zenodo, Mar. 15, 2018. doi: 10.5281/zenodo.1199011.

Owner

  • Name: AlexanderBertrandLab
  • Login: AlexanderBertrandLab
  • Kind: organization

GitHub Events

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