EEG-P300 Extraction using Recursive Principal Component Analysis

By extracting specific brain activity from recorded EEG signals and linking it to specifically developed algorithms, an interface between a computer and the users’ brain is created. Artifacts or noise sources increase the difficulty in analyzing the EEG and to obtaining neural activity. In this paper, a recursive principal component analysis algorithm for brain activity extraction is proposed. The algorithm is designed to adaptively derive a relatively small number of decorrelated linear combinations of a set of random zero-mean variables while retaining as much of the information from the original variables as possible. The proposed method was tested in real EEG records acquired from seven subjects and it can effectively enhance the spike for all subjects. Finally, the promising results reported here reflect the considerable potential of EEG for the continuous extraction of mental states. International Journal of Engineering and Technology (IJET)