Electroencephalography (EEG)-based brain-computer interface (BCI): a 2-D virtual wheelchair control based on...

Area of Science:

• Neuroscience
• Biomedical Engineering
• Rehabilitation Technology

Background:

• Brain-computer interfaces (BCIs) offer potential for assistive devices.
• Traditional BCIs often rely solely on event-related desynchronization (ERD) for control.
• Improving the accuracy and usability of BCI control for mobility is crucial.

Purpose of the Study:

• To propose an effective and practical paradigm for 2-D virtual wheelchair control using a BCI.
• To enhance control performance by integrating event-related synchronization (ERS) with ERD in electroencephalogram (EEG) analysis.
• To assess the paradigm's accuracy and usability with healthy subjects.

Main Methods:

• Utilized multi-class discrimination of spatiotemporally distinct ERD/ERS phenomena in EEG signals.
• EEG signals were associated with motor execution and imagery of right/left hand movements.
• Tested five healthy subjects in motor execution and motor imagery sessions with calibration and control games.

Main Results:

• Achieved a high average target hit rate of 98.4% using motor imagery.
• All subjects reached a 100% hit rate in the second set of wheelchair control games.
• Demonstrated superior control performance without intensive BCI training.

Conclusions:

• The proposed BCI paradigm is effective and practical for 2-D virtual wheelchair control.
• Integrating ERS with ERD enhances spatiotemporal feature contrast for improved control.
• The paradigm shows promise for BCI users requiring assistive mobility solutions.