Performance of a Self-Paced Brain Computer Interface on Data Contaminated with Eye-Movement Artifacts and on Data Recorded in a Subsequent Session
2008

Self-Paced Brain Computer Interface Performance with Eye Movement Artifacts

Sample size: 4 publication 10 minutes Evidence: moderate

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)

10.1155/2008/749204

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication