Phase synchrony in subject-specific reactive band of EEG for classification of motor imagery tasks

Recent works on brain functional analysis have highlighted the importance of distributed functional networks and synchronized activity between networks in mediating cognitive functions. The network perspective is fundamental to relate mechanisms of brain functions and the basis for classifying brain states. This work analyzes the network mechanisms related to motor imagery tasks based on synchronization measure (PLV (phase-locking value)) in EEG alpha-band for the BCI Competition IV Data Set. Based on network dissimilarities between motor imagery and rest tasks, important nodes and important channel pairs corresponding to tasks for all subjects are identified. The identified important channel pairs corresponding to tasks demonstrate significant PLV variation in line with the experiment protocol. With the selection of subject-specific reactive band, these channel pairs provide even more higher variation corresponding to tasks. This paper demonstrates the potential of these identified channel pairs in task classification for future BCI applications.