EEG Decoding Based on Normalized Mutual Information for Motor Imagery Brain–Computer Interfaces

In current research, noninvasive brain–computer interfaces (BCIs) typically rely on electroencephalogram (EEG) signals to measure brain activity. Motor imagery EEG decoding is an important research field of BCIs. Although multichannel EEG signals provide higher resolution, they contain noise and redundant data unrelated to the task, which affect the performance of BCI systems. We investigate the interactions between EEG signals from dependence analysis to improve the classification accuracy. In this article, a novel channel selection method based on normalized mutual information (NMI) is first proposed to select the informative channels. Then, a histogram of oriented gradient is applied to feature extraction in the rearranged NMI matrices. Finally, a support vector machine with a radial basis function kernel is used for the classification of different motor imagery tasks. Four publicly available BCI datasets are employed to evaluate the effectiveness of the proposed method. The experimental results show that the proposed decoding scheme significantly improves classification accuracy and outperforms other competing methods.