Comparison of EEG blind source separation techniques to improve the classification of P300 trials

This paper provides a comparison of several blind source separation (BSS) techniques as they are applied to EEG signals. Specifically, this work focuses on the P300 speller paradigm and assesses the classification accuracies for the identification of P300 trials. Previous work has shown that BSS methods such as independent component analysis (ICA) are useful in extracting the P300 source information from the background noise, increasing the classification rates. ICA will be compared with two other BSS methods, maximum noise fraction (MNF) and principal component analysis (PCA). In addition to this, we will analyze the effect of adding temporal information to the original data, which allows these BSS algorithms to find more complex spatio-temporal patterns.