Self-Paced Brain Computer Interface Performance with Eye Movement Artifacts
Author Information
Author(s): Mehrdad Fatourechi, Ward Rabab K., Gary E. Birch
Primary Institution: University of British Columbia
Hypothesis
Can a self-paced brain computer interface (SBCI) maintain performance in the presence of eye movement artifacts?
Conclusion
The SBCI showed only a slight decrease in performance when tested with data contaminated by eye movement artifacts.
Supporting Evidence
- The average true positive rate dropped from 56.2% to 51.8% when tested on artifact-contaminated data.
- The average false positive rate increased from 0.1% to 0.4% with artifact-contaminated data.
- The system maintained performance across sessions, with only a slight drop in true positive rates.
Takeaway
This study tested a brain-computer interface that lets people control devices with their thoughts, even when their eye movements mess up the signals.
Methodology
The study used a self-paced brain-computer interface tested on data from four participants, comparing performance on artifact-contaminated and non-contaminated data.
Potential Biases
Potential bias due to the small sample size and the specific demographics of participants.
Limitations
The study's findings may not generalize to individuals with motor disabilities, as it primarily involved able-bodied participants.
Participant Demographics
Four right-handed able-bodied participants (three males and one female) aged 31 to 56.
Statistical Information
P-Value
p<0.001 for participant effect; p>0.05 for artifact contamination effect.
Statistical Significance
p<0.05
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website