Classification of EEG Signals Recorded During Imagery of Hand Grasp Movement

Abstract

Brain-computer interfaces (BCI) are the systems that enable to provide communication between users and an external device through only brain activities. One of significant purposes of BBA technology is to enable communication of the patients like who has motor disability or are paralyzed. This communication can be performed by electroencephalogram (EEG) that is a method providing to be followed brain activities through electrical system. In this study, the EEG data set recorded during brain imagination of right or left hand grasp attemtp movements of subjects having hand functional disability was used. It is aimed to have high classification accuracy (CA) for eight different subjects by creating feature vectors using statistical based features. k-nearest neigbors (kNN), support vector machines (SVM) and linear discriminant analysis (LDA) methods were used for classification. We obtained the highest average CA as 81.17% for eight subjects using kNN algorithm. The results indicate that these proposed features can be used for the classification of motor imagery EEG signals.