Hybrid approach of SSVEP and EEG-based eye-gaze tracking for enhancing BCI performance

Abstract

In the conventional steady-state visual evoked potential (SSVEP)-based brain-computer interface (BCI), the information transfer rate (ITR) and classification accuracy are affected by the length of time. To solve this issue, we proposed a hybrid SSVEP-BCI using an electroencephalogram (EEG)-based eye-gaze tracking method. In EEG-based eye-gaze detection, three frontal EEG electrodes are used to identify the direction of the stimulus that the BCI user would have stared at. The results revealed that the ITR and accuracy of the proposed hybrid method were better than those of the conventional SSVEP for various time window lengths. Therefore, the EEG-based eye-gaze tracking method could serve as a novel hybrid approach for improving SSVEP performance.