WAVELET2VEC: A Filter Bank Masked Autoencoder for EEG-Based Seizure Subtype Classification

Ruimin Peng; Changming Zhao; Yifan Xu; Jun Jiang; Guangtao Kuang; Jianbo Shao; Dongrui Wu

ICASSP 2023accepted0 citations

WAVELET2VEC: A Filter Bank Masked Autoencoder for EEG-Based Seizure Subtype Classification

Ruimin Peng, Changming Zhao, Yifan Xu, Jun Jiang, Guangtao Kuang, Jianbo Shao, Dongrui Wu

Abstract

Electroencephalogram (EEG) based seizure subtype classification plays an important role in clinical diagnostics. However, existing deep learning approaches face two challenges in such applications: 1) convolutional or recurrent neural network based models have difficulty learning long-term dependencies; and, 2) there are not enough labeled seizure sub-type data for training such models. This paper proposes a Transformer-based self-supervised learning model for EEG-based seizure subtype classification, which copes well with these two challenges. Filter bank analysis is first employed to improve Vision Transformer as a Wavelet Transformer (WaT) encoder, which generates multi-grained feature representations of EEG signals. Then, self-supervised learning is used to pre-train WaT from unlabeled EEG data. Experiments on two public datasets demonstrated that Wavelet2Vec outperformed several other supervised and self-supervised models in cross-subject seizure subtype classification.

BibTeX

@inproceedings{icassp2023_wavelet2vecafilt,
  title = {WAVELET2VEC: A Filter Bank Masked Autoencoder for EEG-Based Seizure Subtype Classification},
  author = {Ruimin Peng and Changming Zhao and Yifan Xu and Jun Jiang and Guangtao Kuang and Jianbo Shao and Dongrui Wu},
  booktitle = {ICASSP 2023},
  year = {2023}
}