A Novel Hybrid Brain-Computer Interface Integrating Motor Imagery and Multiple Visual Stimuli

Area of Science:

• Neuroscience
• Biomedical Engineering
• Human-Computer Interaction

Background:

• Motor Imagery (MI) Brain-Computer Interfaces (BCI) show potential but have limitations.
• Integrating MI with visual tasks like Steady-State Visual Evoked Potentials (SSVEP) or Overt Spatial Attention (OSA) can improve performance.
• Existing hybrid BCIs often exhibit weak synchronization between MI and visual tasks.

Purpose of the Study:

• To introduce and validate a novel BCI paradigm integrating MI with both SSVEP and OSA.
• To investigate the effectiveness of combining MI with two simultaneous visual stimuli.
• To assess the performance improvements offered by this hybrid approach compared to MI-only and single-visual-task paradigms.

Main Methods:

• A new BCI paradigm was developed, combining MI with dynamic visual stimuli (SSVEP and OSA) representing arm movements.
• Visual stimuli flashed at distinct frequencies and were positioned bilaterally.
• Four different classification methods were employed to evaluate the paradigm's performance.

Main Results:

• The combined MI+SSVEP+OSA paradigm demonstrated significantly higher average accuracy than MI-only, MI+SSVEP, and MI+OSA paradigms.
• Integration of SSVEP provided notable performance gains for participants with low MI-only accuracy.
• Comparable performance was observed between the MI+SSVEP and MI+OSA paradigms.

Conclusions:

• The novel MI+SSVEP+OSA paradigm is effective and feasible for simultaneous integration of MI with dual visual stimuli.
• This hybrid BCI approach offers enhanced accuracy and potential benefits for specific user groups.
• The findings provide valuable guidance for developing more efficient and user-friendly hybrid BCIs.