Parallel Spatial–Temporal Self-Attention CNN-Based Motor Imagery Classification for BCI

• Published in: Frontiers in neuroscience Vol. 14; p. 587520
• Main Authors: Liu, Xiuling, Shen, Yonglong, Liu, Jing, Yang, Jianli, Xiong, Peng, Lin, Feng
• Format: Journal Article
• Language: English
• Published: Switzerland Frontiers Research Foundation 11.12.2020; Frontiers Media S.A
• Subjects: Accuracy; BCI; Classification; Deep learning; EEG; Electroencephalography; Feature selection; Mental task performance; Methods; motor imagery; Neural networks; Neuroscience; spatial-temporal self-attention; Temporal variations; spatial-temporal self-attention; deep learning; BCI; motor imagery; EEG
• DOI: 10.3389/fnins.2020.587520
• ISSN: 1662-453X; 1662-4548

Motor imagery (MI) electroencephalography (EEG) classification is an important part of the brain-computer interface (BCI), allowing people with mobility problems to communicate with the outside world via assistive devices. However, EEG decoding is a challenging task because of its complexity, dynamic nature, and low signal-to-noise ratio. Designing an end-to-end framework that fully extracts the high-level features of EEG signals remains a challenge. In this study, we present a parallel spatial–temporal self-attention-based convolutional neural network for four-class MI EEG signal classification. This study is the first to define a new spatial-temporal representation of raw EEG signals that uses the self-attention mechanism to extract distinguishable spatial–temporal features. Specifically, we use the spatial self-attention module to capture the spatial dependencies between the channels of MI EEG signals. This module updates each channel by aggregating features over all channels with a weighted summation, thus improving the classification accuracy and eliminating the artifacts caused by manual channel selection. Furthermore, the temporal self-attention module encodes the global temporal information into features for each sampling time step, so that the high-level temporal features of the MI EEG signals can be extracted in the time domain. Quantitative analysis shows that our method outperforms state-of-the-art methods for intra-subject and inter-subject classification, demonstrating its robustness and effectiveness. In terms of qualitative analysis, we perform a visual inspection of the new spatial–temporal representation estimated from the learned architecture. Finally, the proposed method is employed to realize control of drones based on EEG signal, verifying its feasibility in real-time applications.