Skip to main content
Journal cover image

Channel selection methods for the P300 Speller.

Publication ,  Journal Article
Colwell, KA; Ryan, DB; Throckmorton, CS; Sellers, EW; Collins, LM
Published in: J Neurosci Methods
July 30, 2014

The P300 Speller brain-computer interface (BCI) allows a user to communicate without muscle activity by reading electrical signals on the scalp via electroencephalogram. Modern BCI systems use multiple electrodes ("channels") to collect data, which has been shown to improve speller accuracy; however, system cost and setup time can increase substantially with the number of channels in use, so it is in the user's interest to use a channel set of modest size. This constraint increases the importance of using an effective channel set, but current systems typically utilize the same channel montage for each user. We examine the effect of active channel selection for individuals on speller performance, using generalized standard feature-selection methods, and present a new channel selection method, termed jumpwise regression, that extends the Stepwise Linear Discriminant Analysis classifier. Simulating the selections of each method on real P300 Speller data, we obtain results demonstrating that active channel selection can improve speller accuracy for most users relative to a standard channel set, with particular benefit for users who experience low performance using the standard set. Of the methods tested, jumpwise regression offers accuracy gains similar to the best-performing feature-selection methods, and is robust enough for online use.

Duke Scholars

Published In

J Neurosci Methods

DOI

EISSN

1872-678X

Publication Date

July 30, 2014

Volume

232

Start / End Page

6 / 15

Location

Netherlands

Related Subject Headings

  • Universities
  • Students
  • ROC Curve
  • Photic Stimulation
  • Neurology & Neurosurgery
  • Male
  • Humans
  • Female
  • Event-Related Potentials, P300
  • Electroencephalography
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Colwell, K. A., Ryan, D. B., Throckmorton, C. S., Sellers, E. W., & Collins, L. M. (2014). Channel selection methods for the P300 Speller. J Neurosci Methods, 232, 6–15. https://doi.org/10.1016/j.jneumeth.2014.04.009
Colwell, K. A., D. B. Ryan, C. S. Throckmorton, E. W. Sellers, and L. M. Collins. “Channel selection methods for the P300 Speller.J Neurosci Methods 232 (July 30, 2014): 6–15. https://doi.org/10.1016/j.jneumeth.2014.04.009.
Colwell KA, Ryan DB, Throckmorton CS, Sellers EW, Collins LM. Channel selection methods for the P300 Speller. J Neurosci Methods. 2014 Jul 30;232:6–15.
Colwell, K. A., et al. “Channel selection methods for the P300 Speller.J Neurosci Methods, vol. 232, July 2014, pp. 6–15. Pubmed, doi:10.1016/j.jneumeth.2014.04.009.
Colwell KA, Ryan DB, Throckmorton CS, Sellers EW, Collins LM. Channel selection methods for the P300 Speller. J Neurosci Methods. 2014 Jul 30;232:6–15.
Journal cover image

Published In

J Neurosci Methods

DOI

EISSN

1872-678X

Publication Date

July 30, 2014

Volume

232

Start / End Page

6 / 15

Location

Netherlands

Related Subject Headings

  • Universities
  • Students
  • ROC Curve
  • Photic Stimulation
  • Neurology & Neurosurgery
  • Male
  • Humans
  • Female
  • Event-Related Potentials, P300
  • Electroencephalography