Contrastive Representation Learning for Electroencephalogram Classification

Mostafa Neo Mohsenvand, Mohammad Rasool Izadi, Pattie Maes
Proceedings of the Machine Learning for Health NeurIPS Workshop, PMLR 136:238-253, 2020.

Abstract

Interpreting and labeling human electroencephalogram (EEG) is a challenging task requiring years of medical training. We present a framework for learning representations from EEG signals via contrastive learning. By recombining channels from multi-channel recordings, we increase the number of samples quadratically per recording. We train a channel-wise feature extractor by extending the SimCLR framework to time-series data. We introduce a set of augmentations for EEG and study their efficacy on different classification tasks. We demonstrate that the learned features improve EEG classification and significantly reduce the amount of labeled data needed on three separate tasks: (1) Emotion Recognition (SEED), (2) Normal/Abnormal EEG classification (TUH), and (3) Sleep-stage scoring (SleepEDF). Our models show improved performance over previously reported supervised models on SEED and SleepEDF and self-supervised models on all three tasks.

Cite this Paper

BibTeX
@InProceedings{pmlr-v136-mohsenvand20a, title = {Contrastive Representation Learning for Electroencephalogram Classification}, author = {Mohsenvand, Mostafa Neo and Izadi, Mohammad Rasool and Maes, Pattie}, booktitle = {Proceedings of the Machine Learning for Health NeurIPS Workshop}, pages = {238--253}, year = {2020}, editor = {Alsentzer, Emily and McDermott, Matthew B. A. and Falck, Fabian and Sarkar, Suproteem K. and Roy, Subhrajit and Hyland, Stephanie L.}, volume = {136}, series = {Proceedings of Machine Learning Research}, month = {11 Dec}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v136/mohsenvand20a/mohsenvand20a.pdf}, url = {https://proceedings.mlr.press/v136/mohsenvand20a.html}, abstract = {Interpreting and labeling human electroencephalogram (EEG) is a challenging task requiring years of medical training. We present a framework for learning representations from EEG signals via contrastive learning. By recombining channels from multi-channel recordings, we increase the number of samples quadratically per recording. We train a channel-wise feature extractor by extending the SimCLR framework to time-series data. We introduce a set of augmentations for EEG and study their efficacy on different classification tasks. We demonstrate that the learned features improve EEG classification and significantly reduce the amount of labeled data needed on three separate tasks: (1) Emotion Recognition (SEED), (2) Normal/Abnormal EEG classification (TUH), and (3) Sleep-stage scoring (SleepEDF). Our models show improved performance over previously reported supervised models on SEED and SleepEDF and self-supervised models on all three tasks.} }
Endnote
%0 Conference Paper %T Contrastive Representation Learning for Electroencephalogram Classification %A Mostafa Neo Mohsenvand %A Mohammad Rasool Izadi %A Pattie Maes %B Proceedings of the Machine Learning for Health NeurIPS Workshop %C Proceedings of Machine Learning Research %D 2020 %E Emily Alsentzer %E Matthew B. A. McDermott %E Fabian Falck %E Suproteem K. Sarkar %E Subhrajit Roy %E Stephanie L. Hyland %F pmlr-v136-mohsenvand20a %I PMLR %P 238--253 %U https://proceedings.mlr.press/v136/mohsenvand20a.html %V 136 %X Interpreting and labeling human electroencephalogram (EEG) is a challenging task requiring years of medical training. We present a framework for learning representations from EEG signals via contrastive learning. By recombining channels from multi-channel recordings, we increase the number of samples quadratically per recording. We train a channel-wise feature extractor by extending the SimCLR framework to time-series data. We introduce a set of augmentations for EEG and study their efficacy on different classification tasks. We demonstrate that the learned features improve EEG classification and significantly reduce the amount of labeled data needed on three separate tasks: (1) Emotion Recognition (SEED), (2) Normal/Abnormal EEG classification (TUH), and (3) Sleep-stage scoring (SleepEDF). Our models show improved performance over previously reported supervised models on SEED and SleepEDF and self-supervised models on all three tasks.
APA
Mohsenvand, M.N., Izadi, M.R. & Maes, P.. (2020). Contrastive Representation Learning for Electroencephalogram Classification. Proceedings of the Machine Learning for Health NeurIPS Workshop, in Proceedings of Machine Learning Research 136:238-253 Available from https://proceedings.mlr.press/v136/mohsenvand20a.html.

Related Material