A multi-modal brain-computer interface based on threshold discrimination and its application in wheelchair control.

Area of Science:

• Neuroscience
• Biomedical Engineering
• Human-Computer Interaction

Background:

• Brain-computer interfaces (BCIs) offer potential for assistive technology.
• Existing single-modal BCIs (e.g., SSVEP or MI alone) have limitations in command diversity and control accuracy.
• Integrating heterogeneous brain signals can overcome these limitations.

Purpose of the Study:

• To develop and evaluate a novel multi-modal BCI system integrating SSVEP and MI.
• To enhance the number of control commands and improve asynchronous control performance for external devices.
• To demonstrate the system's efficacy in controlling an electric wheelchair for complex tasks.

Main Methods:

• A novel threshold discrimination method was developed to differentiate between SSVEP and MI signals.
• The multi-modal BCI system combined SSVEP and MI signals for enhanced control.
• An electric wheelchair was used as the experimental platform, with users performing tasks involving both continuous steering (MI) and discrete commands (SSVEP).
• An obstacle-avoidance experiment was conducted in a complex environment with ten subjects.

Main Results:

• The multi-modal BCI system successfully increased the number of available control commands.
• Significantly improved control accuracy was observed compared to single-modal BCI systems.
• Eight subjects demonstrated effective control of the electric wheelchair in a complex obstacle-avoidance task.
• The system proved effective for complex daily tasks requiring high control precision.

Conclusions:

• The proposed multi-modal BCI system integrating SSVEP and MI is effective for enhancing control command capabilities.
• This approach offers superior control accuracy and performance for assistive devices like electric wheelchairs.
• The findings highlight the potential of multi-modal BCIs for real-world applications in complex environments.