Development of a robust method for an online P300 Speller Brain Computer Interface

This research presents a robust method for P300 component recognition and classification in EEG signals for a P300 Speller Brain-Computer Interface (BCI). The multiresolution wavelet decomposition technique was used for feature extraction. The feature selection was done using an improved t-test method. For feature classification the Quadratic Discriminant Analysis was employed. No any particular specification is previously assumed in the proposed algorithm and all the constants of the system are optimized to generate the highest accuracy on a validation set. The method is first verified in offline experiments on “BCI competition 2003” data set IIb and data recorded by Emotiv Neuroheadset and the results are among the highest previously reported but using a few features from limited number of channels. This method is robust and does not require high computational power. Therefore, it was next implemented in an online P300 speller BCI and tested on four healthy subjects using Emotiv neuroheadset.