Comparison of multi-class motor imagery classification methods for EEG signals

Abstract

This paper presents a comparative study of EEG-based multiclass motor imagery classifiers based on Kullback-Leiber regularised Riemann Mean and support vector machine, hybrid one versus one classifier, linear discriminant analysis, and convolutional neural network. The paper is felt to be of interest to those researchers working in the motor imagery classification of EEG signals. The work presented in this paper helps to understand the basics of different multi-class motor imagery classifiers, their accuracy, and the number of channels involved.