A new approach based on principal ERPs and LDA to improve P300 mind spellers

P300 speller is a brain-machine interface that lets us type by focusing on our desired letter. When the desired letter intensifies, there is a P300 in electroencephalography signals. P300 has a low signal-to-noise ratio; thus, it is hard to be detected. This work presents a new approach toward P300 detection based on a three-step spatial filter (known as principal ERP reduction technique), as the preprocessing stage, in conjunction with linear discriminant analysis, as the classifier. This method is applied to real data, and the results show the effectiveness of the proposed method, especially in the case of small training sets.