Novel Hybrid Brain-Computer Interface for Virtual Reality Applications Using Steady-State Visual-Evoked...

Area of Science:

• Neuroscience
• Human-Computer Interaction
• Biomedical Engineering

Background:

• Brain-computer interfaces (BCIs) are increasingly used in virtual reality (VR) for hands-free control.
• Traditional electroencephalogram (EEG)-based BCIs can be enhanced by eye-tracking, but video-oculography (VOG) is often too expensive for practical VR head-mounted displays (HMDs).
• There is a need for cost-effective and efficient eye-tracking solutions integrated with BCIs for VR.

Purpose of the Study:

• To develop and evaluate a novel, calibration-free hybrid BCI system for VR.
• To enhance the performance of a nine-target steady-state visual-evoked potential (SSVEP)-based BCI using electrooculogram (EOG)-based eye tracking.
• To increase the information transfer rate (ITR) of SSVEP-BCI in a VR environment.

Main Methods:

• A hybrid BCI system was created, combining SSVEP detection with EOG-based horizontal eye movement classification.
• The system uses a 3x3 matrix of pattern-reversal checkerboard stimuli.
• Horizontal EOG signals, recorded using electrodes compatible with VR-HMDs, identified the target column, while the extension of multivariate synchronization index (EMSI) algorithm identified the specific target within the column.

Main Results:

• The proposed hybrid BCI system demonstrated significantly improved accuracy compared to traditional SSVEP-BCI.
• The information transfer rate (ITR) of the hybrid BCI was significantly higher than the traditional SSVEP-BCI in the VR environment.
• Experiments were conducted with 20 participants using a commercial VR-HMD.

Conclusions:

• The novel calibration-free hybrid BCI system effectively integrates SSVEP and EOG for enhanced VR control.
• This approach offers a practical and cost-effective solution for improving BCI performance in VR applications.
• The findings suggest a promising direction for developing more intuitive and efficient human-computer interfaces in immersive environments.