EEG Electrode Selection for a Two-Class Motor Imagery Task in a BCI Using fNIRS Prior Data.

Area of Science:

• Neuroscience
• Biomedical Engineering
• Signal Processing

Background:

• Brain-computer interfaces (BCIs) enable communication and control for individuals with severe motor impairments.
• Optimizing sensor placement in BCIs is crucial for improving system performance and usability.
• Functional near-infrared spectroscopy (fNIRS) offers high spatial resolution for detecting brain activity.

Purpose of the Study:

• To investigate the use of fNIRS for selecting optimal electroencephalography (EEG) electrode positions for BCI applications.
• To enhance the efficiency and practicality of BCIs by reducing the number of required sensors.

Main Methods:

• Utilized fNIRS during right- and left-hand motor imagery tasks.
• Employed the ReliefF algorithm to identify the most reliable fNIRS channels.
• Selected adjacent EEG electrodes based on identified fNIRS channels.
• Evaluated classification performance using linear discriminant analysis, quadratic discriminant analysis, and support vector machine classifiers.

Main Results:

• Successfully identified optimal EEG electrode sets using fNIRS-guided channel selection.
• Demonstrated the feasibility of reducing sensor count while maintaining classification accuracy.
• The proposed method showed potential for improving BCI system usability.

Conclusions:

• fNIRS can effectively guide the selection of EEG electrodes for BCI development.
• Reducing the number of sensors through fNIRS-based optimization significantly enhances BCI usability for patients.
• This approach holds promise for more accessible and practical BCI systems.