Electroencephalogram-Based Motor Imagery Classification Using Deep Residual Convolutional Networks

Jing-Shan Huang; Wan-Shan Liu; Bin Yao; Zhan-Xiang Wang; Si-Fang Chen; Wei-Fang Sun

doi:10.3389/fnins.2021.774857

Electroencephalogram-Based Motor Imagery Classification Using Deep Residual Convolutional Networks

Front Neurosci. 2021 Nov 17:15:774857. doi: 10.3389/fnins.2021.774857. eCollection 2021.

Authors

Jing-Shan Huang^{1

2}, Wan-Shan Liu^{1

2}, Bin Yao^{1

2}, Zhan-Xiang Wang^{3

4

5}, Si-Fang Chen⁵, Wei-Fang Sun⁶

Affiliations

¹ School of Aerospace Engineering, Xiamen University, Xiamen, China.
² Shenzhen Research Institute of Xiamen University, Shenzhen, China.
³ Institute of Neurosurgery, School of Medicine, Xiamen University, Xiamen, China.
⁴ Xiamen Key Laboratory of Brain Center, The First Affiliated Hospital of Xiamen University, Xiamen, China.
⁵ Department of Neurosurgery, The First Affiliated Hospital of Xiamen University, Xiamen, China.
⁶ College of Mechanical and Electrical Engineering, Wenzhou University, Wenzhou, China.

Abstract

The classification of electroencephalogram (EEG) signals is of significant importance in brain-computer interface (BCI) systems. Aiming to achieve intelligent classification of motor imagery EEG types with high accuracy, a classification methodology using the wavelet packet decomposition (WPD) and the proposed deep residual convolutional networks (DRes-CNN) is proposed. Firstly, EEG waveforms are segmented into sub-signals. Then the EEG signal features are obtained through the WPD algorithm, and some selected wavelet coefficients are retained and reconstructed into EEG signals in their respective frequency bands. Subsequently, the reconstructed EEG signals were utilized as input of the proposed deep residual convolutional networks to classify EEG signals. Finally, EEG types of motor imagination are classified by the DRes-CNN classifier intelligently. The datasets from BCI Competition were used to test the performance of the proposed deep learning classifier. Classification experiments show that the average recognition accuracy of this method reaches 98.76%. The proposed method can be further applied to the BCI system of motor imagination control.

Keywords: convolutional neural networks; electroencephalogram (EEG); motor imagery (MI); residual; wavelet packet decomposition (WPD).