A visual keyboard system using hybrid dual frequency SSVEP based brain computer interface with VOG integration

The focus of this paper is to increase the number of targets and classification rate in the SSVEP-BCI visual keyboard system. The dual frequency steady state visual evoked potential (SSVEP) and video-oculography (VOG) based hybrid system has been developed in this study. The visual stimuli (targets) were designed using dual frequency SSVEP method. This method could create more targets through a suitable combination of limited number of frequencies. The keyboard screen was divided into three sections (left, middle and right), and each section visual stimuli/keys were designed with a unique set of frequencies. The webcam based video-oculography was used to detect the direction of the eye gaze. This selection reduces the issue of misclassification of SSVEP frequencies. Extended multivariate synchronization index (EMSI) method is used for SSVEP frequency recognition. Both online and offline experiments were conducted on 10 subjects and an average online detection accuracy of 94.987% was obtained with the information transfer rate (ITR) of 82.786 bits/minutes.