Discriminating MEG signals recorded during hand movements using selection of efficient features

Abstract

Read online

The aim of a Brain-Computer Interface (BCI) system is to establish a new communication system that translates human intentions, reflected by brain signals such as Magnetoencephalogram (MEG), into a control signal for an output device. In this paper, an algorithm is proposed for discriminating MEG signals, which were recorded during hand movements in four directions. These signals are presented as data set 3 of BCI competition IV. The proposed algorithm has four main stages: pre-processing, primary feature extraction, the selection of efficient features and classification. The classification stage was a combination of linear SVM and LDA classifiers. The proposed method was validated in the BCI competition IV, where it obtained the best result among BCI competitors: a classification accuracy of 59.5% and 34.3% for subject 1 and subject 2 on the test data respectively.

Keywords

• MEG
• BCI
• Feature Selection
• LDA
• Linear SVM