Skip to main content

Bayesian approach to dynamically controlling data collection in P300 spellers.

Publication ,  Journal Article
Throckmorton, CS; Colwell, KA; Ryan, DB; Sellers, EW; Collins, LM
Published in: IEEE Trans Neural Syst Rehabil Eng
May 2013

P300 spellers provide a noninvasive method of communication for people who may not be able to use other communication aids due to severe neuromuscular disabilities. However, P300 spellers rely on event-related potentials (ERPs) which often have low signal-to-noise ratios (SNRs). In order to improve detection of the ERPs, P300 spellers typically collect multiple measurements of the electroencephalography (EEG) response for each character. The amount of collected data can affect both the accuracy and the communication rate of the speller system. The goal of the present study was to develop an algorithm that would automatically determine the necessary amount of data to collect during operation. Dynamic data collection was controlled by a threshold on the probabilities that each possible character was the target character, and these probabilities were continually updated with each additional measurement. This Bayesian technique differs from other dynamic data collection techniques by relying on a participant-independent, probability-based metric as the stopping criterion. The accuracy and communication rate for dynamic and static data collection in P300 spellers were compared for 26 users. Dynamic data collection resulted in a significant increase in accuracy and communication rate.

Duke Scholars

Published In

IEEE Trans Neural Syst Rehabil Eng

DOI

EISSN

1558-0210

Publication Date

May 2013

Volume

21

Issue

3

Start / End Page

508 / 517

Location

United States

Related Subject Headings

  • Young Adult
  • Task Performance and Analysis
  • Pattern Recognition, Automated
  • Male
  • Information Storage and Retrieval
  • Humans
  • Event-Related Potentials, P300
  • Diagnosis, Computer-Assisted
  • Databases, Factual
  • Database Management Systems
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Throckmorton, C. S., Colwell, K. A., Ryan, D. B., Sellers, E. W., & Collins, L. M. (2013). Bayesian approach to dynamically controlling data collection in P300 spellers. IEEE Trans Neural Syst Rehabil Eng, 21(3), 508–517. https://doi.org/10.1109/TNSRE.2013.2253125
Throckmorton, Chandra S., Kenneth A. Colwell, David B. Ryan, Eric W. Sellers, and Leslie M. Collins. “Bayesian approach to dynamically controlling data collection in P300 spellers.IEEE Trans Neural Syst Rehabil Eng 21, no. 3 (May 2013): 508–17. https://doi.org/10.1109/TNSRE.2013.2253125.
Throckmorton CS, Colwell KA, Ryan DB, Sellers EW, Collins LM. Bayesian approach to dynamically controlling data collection in P300 spellers. IEEE Trans Neural Syst Rehabil Eng. 2013 May;21(3):508–17.
Throckmorton, Chandra S., et al. “Bayesian approach to dynamically controlling data collection in P300 spellers.IEEE Trans Neural Syst Rehabil Eng, vol. 21, no. 3, May 2013, pp. 508–17. Pubmed, doi:10.1109/TNSRE.2013.2253125.
Throckmorton CS, Colwell KA, Ryan DB, Sellers EW, Collins LM. Bayesian approach to dynamically controlling data collection in P300 spellers. IEEE Trans Neural Syst Rehabil Eng. 2013 May;21(3):508–517.

Published In

IEEE Trans Neural Syst Rehabil Eng

DOI

EISSN

1558-0210

Publication Date

May 2013

Volume

21

Issue

3

Start / End Page

508 / 517

Location

United States

Related Subject Headings

  • Young Adult
  • Task Performance and Analysis
  • Pattern Recognition, Automated
  • Male
  • Information Storage and Retrieval
  • Humans
  • Event-Related Potentials, P300
  • Diagnosis, Computer-Assisted
  • Databases, Factual
  • Database Management Systems