Novel channel selection model based on graph convolutional network for motor imagery

Wei Liang; Jing Jin; Ian Daly; Hao Sun; Xingyu Wang; Andrzej Cichocki

doi:10.1007/s11571-022-09892-1

Novel channel selection model based on graph convolutional network for motor imagery

Cogn Neurodyn. 2023 Oct;17(5):1283-1296. doi: 10.1007/s11571-022-09892-1. Epub 2022 Oct 10.

Authors

Wei Liang¹, Jing Jin^{1

2}, Ian Daly³, Hao Sun¹, Xingyu Wang¹, Andrzej Cichocki^{4

5

6}

Affiliations

¹ Key Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education, East China University of Science and Technology, Shanghai, 200237 China.
² Shenzhen Research Institute of East China University of Technology, Shenzhen, 518063 China.
³ Brain-Computer Interfacing and Neural Engineering Laboratory, School of Computer Science and Electronic Engineering, University of Essex, Colchester, UK.
⁴ Skolkovo Institute of Science and Technology, Moscow, Russia 143026.
⁵ Systems Research Institute of Polish Academy of Science, Warsaw, Poland.
⁶ Department of Informatics, Nicolaus Copernicus University, Torun, Poland.

Abstract

Multi-channel electroencephalography (EEG) is used to capture features associated with motor imagery (MI) based brain-computer interface (BCI) with a wide spatial coverage across the scalp. However, redundant EEG channels are not conducive to improving BCI performance. Therefore, removing irrelevant channels can help improve the classification performance of BCI systems. We present a new method for identifying relevant EEG channels. Our method is based on the assumption that useful channels share related information and that this can be measured by inter-channel connectivity. Specifically, we treat all candidate EEG channels as a graph and define channel selection as the problem of node classification on a graph. Then we design a graph convolutional neural network (GCN) model for channels classification. Channels are selected based on the outputs of our GCN model. We evaluate our proposed GCN-based channel selection (GCN-CS) method on three MI datasets. On three datasets, GCN-CS achieves performance improvements by reducing the number of channels. Specifically, we achieve classification accuracies of 79.76% on Dataset 1, 89.14% on Dataset 2 and 87.96% on Dataset 3, which outperform competing methods significantly.

Keywords: Brain-computer interface(BCI); Channel selection; Graph convolutional neural network (GCN); Motor imagery(MI).

© The Author(s), under exclusive licence to Springer Nature B.V. 2022. Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.