A Novel Visual Keyboard System for Disabled People/Individuals Using Hybrid SSVEP Based Brain Computer Interface

• Published in: 2018 International Conference on Cyberworlds (CW) pp. 264 - 269
• Main Authors: Saravanakumar, D., Reddy M., Ramasubba
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.10.2018
• Subjects: Biomedical monitoring; Brain Computer Interface (BCI); Electrodes; Electroencephalography; Keyboards; Monitoring; Steady State Visual Evoked Potential (SSVEP); Video-Oculography (VOG); Visualization; Webcams
• DOI: 10.1109/CW.2018.00054

This paper aims to design a new stimulus paradigm for SSVEP based keyboard system. The proposed paradigm was implemented using black and white checkerboard flickering visual stimuli along with the integration of videooculography (VOG). The on-screen speller was designed using three frequencies. The goal of this study is how to increase more number of targets using less number of stimulus frequencies. It is achieved by the use of VOG data. The study was carried out using 36 selected characters. A webcam is integrated along with the system to obtain VOG data. The webcam captures the images of the eyes, which in turn is used to detect the eye gaze direction. This additional information from VOG overcomes the limitations of SSVEP based spelling system. The extended multivariate synchronization index (EMSI) method is used for SSVEP frequency recognition. Offline and online analysis of the experiment were conducted and the duration of recognition of each character required by the participant was calculated based on the classification accuracy. Online experiment was conducted on 10 subjects to validate the accuracy and information transfer rate (ITR) of the system. An average online detection accuracy of 90.46 % was obtained with the ITR of 65.98 bits/minutes.