Enhanced Motor Imagery Training Using a Hybrid BCI With Feedback

Area of Science:

• Neuroscience
• Biomedical Engineering
• Human-Computer Interaction

Background:

• Motor imagery (MI)-related mu/beta rhythms are crucial for EEG-based Brain-Computer Interfaces (BCIs).
• Existing BCIs often struggle with insufficient EEG signal differences in naive users, hindering effective feedback and training.
• Steady-state visually evoked potentials (SSVEPs) offer an alternative signal modality for BCI applications.

Purpose of the Study:

• To propose and evaluate a hybrid BCI paradigm combining motor imagery and SSVEPs for enhanced motor imagery training.
• To address the limitations of traditional BCIs in providing effective feedback for novice users.
• To improve the accuracy and reliability of EEG control through a combined feedback system.

Main Methods:

• A hybrid BCI system was developed, integrating motor imagery and SSVEP signals.
• During initial training, subjects focused on visual cues to generate SSVEPs while performing motor imagery tasks.
• Feedback was generated using hybrid features, with SSVEPs initially dominating, gradually shifting to motor imagery as training progressed.

Main Results:

• Subjects demonstrated distinguishable hand motor imagery brain patterns after just five training sessions (approx. 1.5 hours each).
• The hybrid feedback system proved effective in facilitating motor imagery training.
• The system successfully identified subject intentions through combined EEG signals.

Conclusions:

• The proposed hybrid feedback paradigm significantly enhances motor imagery training.
• This hybrid BCI system offers an effective method for identifying user intentions.
• The integration of SSVEPs aids in overcoming initial challenges in motor imagery-based BCI control.