An efficient P300 speller system for Brain-Computer Interface

P300 speller for Brain-Computer Interface systems aim to provide a direct communication between computer - machine and human brain, without any muscular activity. The communication is provided by detecting the presence of P300 Event Related Potentials (ERPs) in the electroencophelogram (EEG) signals, recorded from scalp. The major problem associated with P300 spellers is the stratification of EEGs recorded out of visual stimulation given to a subject. In this paper, we present a method to analyze the EEG data for P300 speller system using Support Vector Machines (SVM) classification technique. Using the proposed method, we are able to find a correct and faster solution for the “target character detection” associated with the P300 speller system. The method requires minimal preprocessing and provides a high transfer rate, which makes it suitable for online analysis also.