An enhanced EEG prediction system for motor cortex-imagery tasks using SVM

Abstract

After the emergence of many new technologies, it is possible to search on the development of new devices that can be predicting what is happening in human thought based on EEG signals, such as the method used this paper contains a novel classification of the EEG signals acquired for multiple motor cortex-imagery tasks, where this method was based on the use of the Extra Tree algorithm to well select the best channels that were used for the acquisition of EEG signals, then the use of support vector machine (SVM) algorithm for data classification, moreover this work uses grey wolf optimizer (GWO) algorithm to improve all SVM parameters quickly and to converge the accuracy of the system towards the highest possible values. As a result, this work shows that the accuracy of prediction of motor cortex-imagery based EEG signals can be increased more than 99%. Also, this paper contains a comparison with other methods of the literature.

Keywords

• brain-computer interface (bci)
• electroencephalogram (eeg)
• data analysis
• machine learning
• parameters optimization