Study on Classification of Left-Right Hands Motor Imagery EEG Signals Based on CNN

Abstract

The performance of classification is one of the most key issues in brain computer interface (BCI) system. This paper proposes a classification method of two-class motor imagery electroencephalogram (EEG) signals based on convolutional neural networks (CNN), in which EEG signals from C3, C4 and Cz electrodes of publicly available BCI competition IV dataset 2b were used to test the performance of CNN. We investigate CNN with a form of input from short time Fourier transform (STFT) combining time, frequency and location information. Fisher discriminant analysis-type F-score based on band pass (BP) feature and power spectra density (PSD) feature are employed respectively to select the subject-optimal frequency bands. In the experiments, typical frequency bands related to motor imagery EEG signals, subject-optimal frequency bands and Extension Frequency Bands are employed respectively as the frequency range of the input image of CNN. The better classification performance of Extension Frequency Bands show that CNN can extract optimal feature from frequency information automatically. The classification result also demonstrates that the proposed approach is more competitive in prediction of left/right hand motor imagery task compared with other state-of-art approaches.