PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

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.

Abstract

The 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.

PDF - PASCAL Members only - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Brain Computer Interfaces
ID Code:1383
Deposited By:Alain Rakotomamonjy
Deposited On:28 November 2005