Classification of EEG colour imagination tasks based BMI using energy and entropy features

Abstract

Electroencephalogram (EEG) signals are the electrophysiological measures of brain function and it is used to develop a brain machine interface. Brain machine interface (BMI) system is used to provide a communication and control technology for the mentally able people having neuromuscular disorders. In this paper, a simple BMI system based on EEG signal emanated while imagining of different colours has been proposed. The proposed BMI uses the color imagination tasks (CIT) and aims to provide a communication link using brain activated control signal; the required task operation can be then performed and the needs of the physically retarded community can be accomplished. Two feature extraction method are used for analysis namely energy and entropy. The extracted features are then associated to different control signals and a probabilistic neural network model (PNN) has been developed. The effectiveness of the two features are compared using PNN classification accuracy.