Performance analysis of different feature-classifier binomials in motor-imagering BCIs: Preliminary results

Author

Bermúdez, Germán Rodríguez ; Roca-Gonzalez, J. ; Martínez-González, F. ; Peña-Morán, L. ; Roca-González, J.L. ; Roca-Dorda, J.

Author_Institution

Politechnic Sci. Dept., Catholic Univ. of Murcia, Murcia, Spain

fYear

2010

fDate

7-10 Nov. 2010

Firstpage

1

Lastpage

5

Abstract

Brain Computer Interface Systems (BCIs) allow the identification of volitive brain activity patterns. This allows their use as input channels for alternative communication and computer access systems by patients suffering from severe motor disabilities. This paper presents preliminary results obtained after extracting four different features from EEG signals in order to recognize the activity patterns by means of four different classifiers. The final goal is to determine the proper "feature - classifier” binomial for each user in order to increase system reliability and satisfaction in use.

Keywords

bioelectric potentials; brain-computer interfaces; electroencephalography; feature extraction; medical signal processing; neurophysiology; patient care; pattern classification; BCI; EEG signal; brain computer interface system; computer access systems; feature-classifier binomial; motor disabilities; motor-imagering; pattern identification; volitive brain activity; Artificial Neural Network; Brain Computer Interface; Feature extraction; Linear Discriminant analysis; Support Vector Machine; formatting;

fLanguage

English

Publisher

ieee

Conference_Titel

Applied Sciences in Biomedical and Communication Technologies (ISABEL), 2010 3rd International Symposium on

Conference_Location

Rome

Print_ISBN

978-1-4244-8131-6

Type

conf

DOI

10.1109/ISABEL.2010.5702912

Filename

5702912