|
BCI Competition III : Dataset II - Ensemble of SVMs for BCI P300 speller
Alain Rakotomamonjy and Vincent Guigue
IEEE Transactions on Neural Systems and Rehabilitation Engineering
2005.
AbstractThe Brain-Computer Interface P300 speller aims at helping patients unable to activate
muscle to spell words by means of their brain signal activities. Associated to this BCI
paradigm, there is the problem of classifying electroencephalogram signals related to the
mental spelling action. This paper addresses the problem of signal responses variability
within a single subject in such Brain-Computer Interface. We propose a method that copes
with such variabilities through an ensemble of classifier approach. Each classifier is composed
of a linear Support Vector Machines trained on only a small part of the available data and
for which a channel selection procedure has been performed. Performances of our algorithm
has been evaluated on dataset II of the BCI Competition III and has yielded the maximum
classification performance rate. [Edit]
| 
