Learning EEG Representations with Weighted Convolutional Siamese Network: a Large Multi-session Post-stroke Rehabilitation Study

Learning EEG Representations with Weighted Convolutional Siamese Network: a Large Multi-session Post-stroke Rehabilitation Study

IEEE Transactions on Neural Systems and Rehabilitation Engineering

10.1109/TNSRE.2022.3209155

http://dx.doi.org/10.1109/tnsre.2022.3209155

Shuailei Zhang, Kai Keng Ang, Dezhi Zheng, Qianxin Hui, Xinlei Chen, Yang Li, Ning Tang, Effie Chew, Rosary Yuting Lim, Cuntai Guan

Electroencephalography, Feature extraction, Training, convolution, Stroke, Measurement, Decoding, Brain-computer interface (BCI), weighted convolutional siamese network, post-stroke rehabilitation

26 September 2022

Zhang, S., Ang, K. K., Zheng, D., Hui, Q., Chen, X., Li, Y., Tang, N., Chew, E., Lim, R. Y., & Guan, C. (2022). Learning EEG Representations with Weighted Convolutional Siamese Network: a Large Multi-session Post-stroke Rehabilitation Study. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 1–1. https://doi.org/10.1109/tnsre.2022.3209155

Although brain-computer interface (BCI) shows promising prospects to help post-stroke patients recover their motor function, its decoding accuracy is still highly dependent on feature extraction methods. Most current feature extractors in BCI are classification-based methods, yet very few works from literature use metric learning based methods to learn representations for BCI. In this paper, we propose a deep metric learning based method, Weighted Convolutional Siamese Network (WCSN) to learn representations from electroencephalogram (EEG) signal. This approach enhances the decoding accuracy by learning a low dimensional embedding to extract distance-based representations from pair-wise EEG data. To enhance training efficiency and algorithm performance, a temporal-spectral distance weighted sampling method is proposed to select more informative input samples. In addition, an adaptive training strategy is adopted to address the session-to-session non-stationarity by progressively updating the subject-specific model. The proposed method is applied on both upper limb and lower limb neurorehabilitation datasets acquired from 33 stroke patients, with a total of 358 sessions. Results indicate that using k-Nearest Neighbor as the classification algorithm, the proposed method yields 72.8% and 66.0% accuracies for the two datasets respectively, significantly better than the other state-of-the-arts (p < 0.05). The proposed method also demonstrates superior average performance on two publicly available datasets acquired from healthy subjects in most cases as well. Our results support, for the first time, the use of a metric learning based feature extractor to learn representations from non-stationary EEG signals for BCI-assisted post-stroke rehabilitation.

Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)

This research / project is supported by the A*STAR - RIE2020 AME Programmatic Fund
Grant Reference no. : A20G8b0102

This research was funded by National Natural Science Foundation of China (Grant No. 61873021; 62088101), the China Scholarship Council (Grant No. 202006020219)

© 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

https://oar.a-star.edu.sg/communities-collections/articles/18638

1534-4320
1558-0210

Institute for Infocomm Research