Channel selection from EEG signals and application of support vector machine on EEG data

Abstract

In this study, EEG data recorded during mental arithmetic operations and silent reading were analyzed by discrete wavelet transform and feature vectors were obtained. The obtained feature vectors are classified by Support Vector Machines (SVM). Results are given for 26 channels, all recorded channels, and for 10 most effective channels. Correlation based feature selection based algorithm is used for choosing the most effective channels. Decreasing the number of channels without compromising the accuracy, is an important issue for real time applications for which a short analysis time is crucial. In this study, mental arithmetic and silent reading tasks are classified with an accuracy of 90.71%, a precision rate of 91.03% and F-measure rate of 90.63% on the average using 26 channels, whereas the accuracy, precision and F-measure were 90.44%, 90.61% and 90.08, respectively which were comparable to that of obtained using all channels, for reduced number of channels.