Research on Adaptive Discriminating Method of Brain-Computer Interface for Motor Imagination

Area of Science:

• Neuroscience
• Biomedical Engineering
• Human-Computer Interaction

Background:

• Brain-computer interface (BCI) technology merges human and machine intelligence.
• Motor imagery-based BCIs (MI-BCIs) utilize imagined movements for signal generation, differing from externally stimulated BCIs.
• Individual variability in MI-BCI signals necessitates methods to identify suitable users and enhance system efficiency.

Purpose of the Study:

• To investigate the relationship between functional brain networks and adaptability to motor imagery-based Brain-Computer Interfaces (MI-BCIs).
• To identify potential predictors of MI-BCI performance based on brain signal characteristics during motor imagery tasks.

Main Methods:

• Collected data from 50 healthy subjects performing four motor imagery tasks (left hand, right hand, foot, tongue).
• Assessed MI-BCI adaptability via classification accuracy.
• Constructed functional brain networks using the weighted phase lag index (WPLI) and analyzed graph theory parameters.

Main Results:

• A significant correlation was observed between tongue imagination network characteristics and MI-BCI adaptability.
• Nodal degree and characteristic path length in the right hemisphere during tongue imagination showed significant correlation with classification accuracy (p < 0.05).

Conclusions:

• Tongue imagination exhibits potential as a predictive indicator for motor imagery-based Brain-Computer Interface (MI-BCI) adaptability.
• Findings provide novel insights into the functional network mechanisms underlying motor imagery.