Classification of two-class motor imagery for Brain Computer Interface

Abstract

Robotics and Artificial Intelligence have played a significant role in the development of assistive technologies for people with motor disabilities. Brain-Computer Interface (BCI) is a type of communication system that allows humans to communicate with their environment by detecting and quantifying control signals produced from different modalities, and translating them into voluntary commands for actuating an external device. This project deals with the classification of two-class and multi-class motor imagery electroencephalography (EEG) signals and translating them into voluntary commands for actuating an external device through a brain-computer interface (BCI). For efficient classification of EEG signals, a new framework has been proposed, that employs a combination of Butterworth bandpass filter and ICA for pre-processing, and CSP & log-variance for feature extraction, along with different classification techniques such as SVM, LDA, naïve Bayes, decision trees, k-NN, and logistic regression to choose the most relevant classifier to obtain a significant improvement in the average classification accuracies of various datasets as compared to the approaches proposed earlier. Classification is performed using the MATLAB platform. The classified signals are then fed to the embedded system to operate an actuator