Optimized detection of the infrequent response in P300-based brain-computer interfaces

Authors

  • C. Lindig - León Laboratorio de Neuroimagenología, Universidad Autónoma Metropolitana, Iztapalapa
  • O. Yáñez - Suárez Laboratorio de Neuroimagenología, Universidad Autónoma Metropolitana, Iztapalapa

Abstract

 

This paper presents an application developed on the BCI2000 platform which reduces the average spelling time per symbol on the Donchin speller. The motivation was to reduce the compromise between spelling rate and spelling accuracy due to a large amount of responses required in order to perform coherent average techniques. The methodology was made under a Bayesian approach which allows calculation of each target's class posterior probability. This result indicates the probability of each response of belonging to the infrequent class. When there is enough evidence to make a decision the system stops the stimulation process and moves on with the next symbol, otherwise it continues stimulating the user until it finds the selected letter. The average spelling rate, after using the proposed methodology with 14 healthy users and a maximum number of 5 stimulation sequences, was of 6.1 ± 0.63 char/min, compared to a constant rate of 3.93 char/min with the standard system.

Downloads

Download data is not yet available.

Downloads

Published

2013-01-15

How to Cite

Lindig - León, C., & Yáñez - Suárez, O. (2013). Optimized detection of the infrequent response in P300-based brain-computer interfaces. Revista Mexicana De Ingenieria Biomedica, 34(1), 53–69. Retrieved from https://rmib.com.mx/index.php/rmib/article/view/203

Issue

Section

Research Articles

Dimensions Citation