P300-Based Brain-Computer Interface Speller Performance Estimation with Classifier-Based Latency Estimation
Journal of Visualized Experiments · 2023-09-08 · (199)
DOI: 10.3791/64959 ↗At a glance
Video/Audio in Journal of Visualized Experiments, published online on 2023-09-08. Written by Nazmun N Khan and 5 co-authors. Institution: Brain and Body Sensing Lab, Mike Wiegers Department of Electrical & Computer Engineering, Kansas State University; nkhan1@ksu.edu. Major MEDLINE topics: Brain-Computer Interfaces. Cited 3 times so far (Crossref); 21 references.
Abstract (original language)
Performance estimation is a necessary step in the development and validation of Brain-Computer Interface (BCI) systems. Unfortunately, even modern BCI systems are slow, making collecting sufficient data for validation a time-consuming task for end users and experimenters alike. Yet without sufficient data, the random variation in performance can lead to false inferences about how well a BCI is working for a particular user. For example, P300 spellers commonly operate around 1-5 characters per minute. To estimate accuracy with a 5% resolution requires 20 characters (4-20 min). Despite this time investment, the confidence bounds for accuracy from 20 characters can be as much as ±23% depending on observed accuracy. A previously published method, Classifier-Based Latency Estimation (CBLE), was shown to be highly correlated with BCI accuracy. This work presents a protocol for using CBLE to predict a user's P300 speller accuracy from relatively few characters (~3-8) of typing data. The resulting confidence bounds are tighter than those produced by traditional methods. The method can thus be used to estimate BCI performance more quickly and/or more accurately.
Subjects
MeSH terms (MEDLINE)
Authors and institutions
- Brain and Body Sensing Lab, Mike Wiegers Department of Electrical & Computer Engineering, Kansas State University; nkhan1@ksu.edu.
- Brain and Body Sensing Lab, Mike Wiegers Department of Electrical & Computer Engineering, Kansas State University.
- Adaptive Cognitive Assessment Laboratory, Department of Physical Medicine and Rehabilitation, University of Michigan, Ann Arbor.
- Direct Brain Interface Laboratory, Department of Physical Medicine and Rehabilitation, University of Michigan, Ann Arbor; Direct Brain Interface Laboratory, Department of Biomedical Engineering, University of Michigan,…
Cite
APA
Khan, N. N., Sweet, T., Harvey, C. A., Warschausky, S., Huggins, J. E., & Thompson, D. E. (2023). P300-Based Brain-Computer Interface Speller Performance Estimation with Classifier-Based Latency Estimation. Journal of Visualized Experiments. https://doi.org/10.3791/64959
Vancouver
Khan NN, Sweet T, Harvey CA, Warschausky S, Huggins JE, Thompson DE. P300-Based Brain-Computer Interface Speller Performance Estimation with Classifier-Based Latency Estimation. Journal of Visualized Experiments. 2023. doi:10.3791/64959
BibTeX
@article{Khan2023,
author = {Khan, Nazmun N and Sweet, Taylor and Harvey, Chase A and Warschausky, Seth and Huggins, Jane E and Thompson, David E},
title = {P300-Based Brain-Computer Interface Speller Performance Estimation with Classifier-Based Latency Estimation},
journal = {Journal of Visualized Experiments},
year = {2023},
number = {199},
doi = {10.3791/64959}
}
EUVIMED