Determination of an optimal training strategy for a BCI classification task with LDA

Author

Gareis, I.E. ; Acevedo, R.C. ; Atum, Y.V. ; Gentiletti, G.G. ; Banuelos, V.M. ; Rufiner, H.L.

Author_Institution

Lab. de Ing. en Rehabilitacion e Investig. Neuromusculares y Sensoriales, Univ. Nac. de Entre Rios, Parana, Argentina

fYear

2011

fDate

April 27 2011-May 1 2011

Firstpage

286

Lastpage

289

Abstract

Brain computer interfaces (BCIs) translate brain activity into computer commands. To enhance the performance of a BCI, it is necessary to improve the feature extraction techniques being applied to decode the users´ intentions. Objective comparison methods are needed to analyze different feature extraction techniques. One possibility is to use the classifier performance as a comparative measure. In this paper, we study the behavior of linear discriminant analysis (LDA) when used to distinguish between electroencephalographic (EEG) signals with and without the presence of event related potentials (ERPs).

Keywords

bioelectric potentials; brain-computer interfaces; decoding; electroencephalography; feature extraction; handicapped aids; medical signal processing; signal classification; BCI classification task; EEG; ERP; LDA; brain activity; brain computer interfaces; decoding; electroencephalographic signals; event related potentials; feature extraction; linear discriminant analysis; optimal training strategy; Brain computer interfaces; Databases; Electroencephalography; Erbium; Feature extraction; Sensitivity; Training;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Engineering (NER), 2011 5th International IEEE/EMBS Conference on

Conference_Location

Cancun

ISSN

1948-3546

Print_ISBN

978-1-4244-4140-2

Type

conf

DOI

10.1109/NER.2011.5910543

Filename

5910543