Correlative exploration of EEG signals for direct brain-computer communication

Author

Garcia, Gary N. ; Ebrahimi, Touradj ; Vesin, Jean-Marc

Author_Institution

Swiss Fed. Inst. of Technol., Ecole Polytech. Fed. de Lausanne, Switzerland

Volume

5

fYear

2003

fDate

6-10 April 2003

Abstract

In this study we present a method for classifying EEG signals based on the information content of their correlative time-frequency-space representation (CTFSR). A support vector machine (SVM) kernel is proposed that can be calculated in the time domain while it computes a similarity measure in the CTFSR space. This classification method is used in a brain-computer interface (BCI) application. The use of the SVM approach allows us to propose a simple strategy for adapting the BCI to possible long term variations in the brain activity.

Keywords

electroencephalography; handicapped aids; human computer interaction; medical signal detection; medical signal processing; signal classification; signal representation; support vector machines; time-frequency analysis; BCI; CTFSR; EEG signals; SVM kernel; brain activity; brain-computer interface; correlative time-frequency-space representation; direct brain-computer communication; information content; long term variations; signal classification; similarity measure; support vector machine; time domain; Brain computer interfaces; Electrodes; Electroencephalography; Frequency domain analysis; Signal analysis; Signal generators; Signal processing; Support vector machine classification; Support vector machines; Time frequency analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03). 2003 IEEE International Conference on

ISSN

1520-6149

Print_ISBN

0-7803-7663-3

Type

conf

DOI

10.1109/ICASSP.2003.1200096

Filename

1200096