Authors:
André Ferreira
1
;
Teodiano Freire Bastos-Filho
1
;
Mário Sarcinelli-Filho
1
;
José Luis Martín Sánchez
2
;
Juan Carlos García García
2
and
Manuel Mazo Quintas
2
Affiliations:
1
Federal University of Espirito Santo, Brazil
;
2
Universiity of Alcala (UAH), Spain
Keyword(s):
Adaptive autoregressive parameters, Power spectral density components, Support-vector machines, Braincomputer interfaces, Robotic wheelchair.
Related
Ontology
Subjects/Areas/Topics:
Biomedical Engineering
;
Biomedical Instruments and Devices
;
Emerging Technologies
;
Telecommunications
;
Wireless and Mobile Technologies
;
Wireless Information Networks and Systems
Abstract:
Two distinct signal features suitable to be used as input to a Support-Vector Machine (SVM) classifier in an application involving hands motor imagery and the correspondent EEG signal are evaluated in this paper. Such features are the Power Spectral Density (PSD) components and the Adaptive Autoregressive (AAR) parameters. Different classification times (CT) and time intervals are evaluated, for the AAR-based and the PSD-based features, respectively. The best result (an accuracy of 97.1%) is obtained when using PSD components, while the AAR parameters generated an accuracy of 94.3%. The results also demonstrate that it is possible to use only two EEG channels (bipolar configuration around C3 and C4), discarding the bipolar configuration around Cz. The algorithms were tested with a proprietary EEG data set involving 4 individuals and with a data set provided by the University of Graz (Austria) as well. The resulting classification system is now being implemented in a Brain-Computer In
terface (BCI) used to guide a robotic wheelchair.
(More)