Two-class brain computer interface using eyes-closed steady-state visual evoked potential

Brain computer interfaces (BCIs) provide an assistive tool for communication between disabled with severe motor disability and care personnel. Although state-of-the-art BCIs have achieved the outstanding improvement in its information transfer rate and classification accuracy, most of the BCIs are difficult to use for patients with impaired oculomotor control due to requirement of visual modality. The present study thus considered a BCI which was independent of oculomotor control using event-related desynchronization (ERD)-like modulation of steady-state visual evoked potential (SSVEP) synchronized at stimulus frequency of flicker stimuli under eyes-closed condition. The amplitude of SSVEP in the posterior region of twelve healthy subjects aged 21-22 years old was seen to be significantly modulated when they repeated mental focusing on the flicker stimuli. Moreover, such amplitude modulation also occurred in performing image recalling and mental calculation for other six healthy subjects. Mean classification accuracy on whether the subjects performed task or not, corresponding to intention of Yes or No, reached 81.9 %, 64.6 % and 71.9 % for the mental focus, image recall and mental calculation, respectively. Reinforcement of amplitude recovery in the relaxed state is needed to give the validity to the proposed BCI.