Analysis of Matching Pursuit Features of EEG Signal for Mental Tasks Classification

Abstract

Brain Computer Interface (BCI) Systems have developed for new way of communication between computer and human who are suffer from severe motor disabilities and difficult to communicate with their environment. BCI let them for communication by non muscular way. For communication between human and computer, BCI uses a type of signal called Electroencephalogram (EEG) signal which are recorded from the human‘s brain by mean of electrode. Electroencephalogram (EEG) signal is an important information source for knowing brain processes for the non-invasive BCI. In translating human’s thought, it needs to classify acquired EEG signal accurately. Independent Component analysis (ICA) method via EEGLab Tools for removing artifacts which are caused by eye blinks in the recorded mental task EEG signal. For features extraction, the Time and Frequency features of non stationary EEG signals are extracted by Matching Pursuit (MP) algorithm. The classification of mental tasks is performed by Multi_Class Support Vector Machine (SVM).