P300 Detection for Brain Computer Interface

Abstract

P300 based brain computer interface (BCI) sometimes called brain machine interface (BMI) is a way of direct communication between human brain and external device which provides an alternative communication link with outside world to the people who are unable to communicate via conventional means because of sever motor disability. P300 wave is an event related potential which evoked in the process of decision making of human brain which can be generated using oddball paradigm. This thesis aims to detect the P300 wave as accurate as possible. To do that this study proposed discrete wavelet transforms (DWT) based feature extraction method from each P300 and No-P300 of EEG signal from the entire 64 channel. Principal component analysis (PCA) technique is further applied for the reduction of the dimension of the feature. Detection of P300 is achieved using support vector machine (SVM) and artificial neural network (ANN) classifier. Experimental result shows that the proposed method with SVM classifier yields better performance compared to the method with ANN.