EEG signals analysis for motor imagery brain computer interface

Abstract

A brain{computer interface is a medium for communication which converts neuronal signals into commands towards controlling external system. This thesis presented the process of classifying three motor imagery tasks using EEG signals which can be further evolved into BCI system that can remotely control external devices. Different bands are ltered from EEG signals in order to extract di erent frequency distributed features. These features are used to classify di erent motor imagery tasks based on SVM and ANN. Experimental results show that SVM carried higher accuracy (i.e., 80%) compared to other machine learning algorithms where seven subjects participated in this experiment.