A shallow mirror transformer for subject-independent motor imagery BCI

Jing Luo; Yaojie Wang; Shuxiang Xia; Na Lu; Xiaoyong Ren; Zhenghao Shi; Xinhong Hei

doi:10.1016/j.compbiomed.2023.107254

A shallow mirror transformer for subject-independent motor imagery BCI

Comput Biol Med. 2023 Sep:164:107254. doi: 10.1016/j.compbiomed.2023.107254. Epub 2023 Jul 10.

Authors

Jing Luo¹, Yaojie Wang², Shuxiang Xia², Na Lu³, Xiaoyong Ren⁴, Zhenghao Shi², Xinhong Hei²

Affiliations

¹ Shaanxi Key Laboratory for Network Computing and Security Technology and Human-Machine Integration Intelligent Robot Shaanxi University Engineering Research Center, School of Computer Science and Engineering, Xi'an University of Technology, Xi'an, Shaanxi, China. Electronic address: luojing@xaut.edu.cn.
² Shaanxi Key Laboratory for Network Computing and Security Technology and Human-Machine Integration Intelligent Robot Shaanxi University Engineering Research Center, School of Computer Science and Engineering, Xi'an University of Technology, Xi'an, Shaanxi, China.
³ State Key Laboratory for Manufacturing Systems Engineering, Systems Engineering Institute, Xi'an Jiaotong University, Xi'an, Shaanxi, China.
⁴ Department of Otolaryngology Head and Neck Surgery & Center of Sleep Medicine, The Second Affiliated Hospital of Xi'an Jiaotong University, Xi'an, Shaanxi, China.

PMID: 37499295
DOI: 10.1016/j.compbiomed.2023.107254

Abstract

Objective: Motor imagery BCI plays an increasingly important role in motor disorders rehabilitation. However, the position and duration of the discriminative segment in an EEG trial vary from subject to subject and even trial to trial, and this leads to poor performance of subject-independent motor imagery classification. Thus, determining how to detect and utilize the discriminative signal segments is crucial for improving the performance of subject-independent motor imagery BCI.

Approach: In this paper, a shallow mirror transformer is proposed for subject-independent motor imagery EEG classification. Specifically, a multihead self-attention layer with a global receptive field is employed to detect and utilize the discriminative segment from the entire input EEG trial. Furthermore, the mirror EEG signal and the mirror network structure are constructed to improve the classification precision based on ensemble learning. Finally, the subject-independent setup was used to evaluate the shallow mirror transformer on motor imagery EEG signals from subjects existing in the training set and new subjects.

Main results: The experiments results on BCI Competition IV datasets 2a and 2b and the OpenBMI dataset demonstrated the promising effectiveness of the proposed shallow mirror transformer. The shallow mirror transformer obtained average accuracies of 74.48% and 76.1% for new subjects and existing subjects, respectively, which were highest among the compared state-of-the-art methods. In addition, visualization of the attention score showed the ability of discriminative EEG segment detection. This paper demonstrated that multihead self-attention is effective in capturing global EEG signal information in motor imagery classification.

Significance: This study provides an effective model based on a multihead self-attention layer for subject-independent motor imagery-based BCIs. To the best of our knowledge, this is the shallowest transformer model available, in which a small number of parameters promotes the performance in motor imagery EEG classification for such a small sample problem.

Keywords: Brain–computer interfaces (BCI); Motor imagery (MI); Multihead self-attention; Subject-independent BCI.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Algorithms
Brain-Computer Interfaces*
Electroencephalography* / methods
Humans
Imagination
Learning