SSVEP enhancement in mixed reality environment for brain-computer interfaces.

Area of Science:

• Neuroscience
• Computer Science
• Human-Computer Interaction

Background:

• Brain-computer interfaces (BCIs) offer expanded applications within mixed reality (MR) environments.
• Realistic scenes in MR degrade BCI performance due to visual stimulus interference.

Purpose of the Study:

• To optimize stimulus colors for improved performance in MR-BCI systems.
• To investigate the impact of color contrast ratios (CCRs) on SSVEP-BCI accuracy.

Main Methods:

• Deployment of a 10-command steady-state visually evoked potential (SSVEP)-BCI in an MR environment.
• Testing and optimization of various stimulus and background colors using offline and online experiments.
• Proposal and evaluation of a simulated annealing-based cross-correlation task-related component analysis (SA-xTRCA) algorithm.

Main Results:

• Significant interaction effect between background and stimulus colors on system performance.
• Evidence of a nonlinear relationship between CCR and SSVEP detection accuracy.
• Optimal performance achieved with polychromatic stimuli on colored backgrounds; SA-xTRCA outperformed traditional algorithms.

Conclusions:

• Stimulus color optimization, considering background color, effectively enhances MR-BCI system performance.
• CCR serves as a quantitative criterion for selecting stimulus colors in MR-BCI design.
• The proposed SA-xTRCA algorithm significantly improves signal-to-noise ratio and detection accuracy.