Multiple classification algorithms for the BCI P300 speller diagram using ensemble of SVMs

Author

El Dabbagh, Hend ; Fakhr, Waleed

Author_Institution

Arab Acad. for Sci. & Technol., Cairo, Egypt

fYear

2011

fDate

19-22 Feb. 2011

Firstpage

393

Lastpage

396

Abstract

Brain computer interface is one of the most recent and controversial field in Computer Science which emerged in order to help some handicapped people. This paper investigates different classification algorithms dealing with the BCI P300 speller diagram. The system used is composed of an ensemble of Support vector machines. Three different methods are used namely weighted ensemble of SVM, row & column based SVM ensemble and channel selection with optimized SVM´s. Experimental results show that proposed methods obtain better results than published results of competition III dataset II.

Keywords

brain-computer interfaces; statistical analysis; support vector machines; BCI P300 speller diagram; brain computer interface; channel selection; column based SVM ensemble; computer science; multiple classification algorithm; row based SVM ensemble; support vector machine; weighted ensemble; Classification algorithms; Continuous wavelet transforms; Electroencephalography; Feature extraction; Support vector machines; Training; Training data; Brain Computer Interface; Ensemble of SVM; Event Related Potential; P300;

fLanguage

English

Publisher

ieee

Conference_Titel

GCC Conference and Exhibition (GCC), 2011 IEEE

Conference_Location

Dubai

Print_ISBN

978-1-61284-118-2

Type

conf

DOI

10.1109/IEEEGCC.2011.5752542

Filename

5752542