An Algorithm for Brain Computer Interfacing Based on Phase Synchronization Spatial Patterns

Brain computer interfacing (BCI) is an interdisciplinary area that connects biomedical knowledge on brain physiology with the use of effective computational techniques for mental task discrimination. One of the most successful algorithms in BCI is the method of common spatial patterns (CSP). The spatial filters computed using this method are based on a joint diagonalization of the covariance matrices of two classes of data. However, in the standard CSP implementation the influence of amplitude and phase characteristics are not distinguished. In order to investigate phase synchronization links for the scope of task discrimination, we propose a variant of the method of CSP that depends explicitly on phase synchronization information. The phase-based CSP (P-CSP) was tested on simulated data to analyze if the implemented method yields significant patterns of phase interaction. The algorithm was also used on real EEG data for the classification of two motor imagery tasks and results were compared to those obtained using the phase locking value (PLV). The results obtained indicate that using the method of P-CSP with a few spatial filters can yield classification rates close to or exceeding the best classification rate obtained from the PLV measures for any pair of channels.