Classification in emotional BCI using phase information from the EEG

Synchronization and distributed functional networks have been used with success in different areas of engineering. In this paper we use the synchronization information from electroencephalogram (EEG) channels through the Phase Locking Value (PLV) as a potential classification method for a Brain Computer Interface (BCI); this achieved using emotional schematic faces as stimuli in a motor imagery (MI) task. Based on the variations of the PLV values for each proposed task and for each participant, the principal channel pairs are identified. Selected channel pairs, corresponding with the accomplished task, present PLV patterns similarly to Evoked Potentials (ERS/ERD) which are widely used as classification features for MI based BCI.

[1]  F. L. D. Silva,et al.  Event-related EEG/MEG synchronization and desynchronization: basic principles , 1999, Clinical Neurophysiology.

[2]  Clemens Brunner,et al.  Online Control of a Brain-Computer Interface Using Phase Synchronization , 2006, IEEE Transactions on Biomedical Engineering.

[3]  Jin-Ho Cho,et al.  Adaptive estimation of EEG for subject-specific reactive band identification and improved ERD detection , 2012, Neuroscience Letters.

[4]  Y. Wang,et al.  Phase synchrony in subject-specific reactive band of EEG for classification of motor imagery tasks , 2013, 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[5]  Stefano Ramat,et al.  Optimizing spatial filter pairs for EEG classification based on phase-synchronization , 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[6]  R. Hornero,et al.  A comparative study of event-related coupling patterns during an auditory oddball task in schizophrenia , 2015, Journal of neural engineering.