Comparison of different feature classifiers for brain computer interfaces

Author

Cincotti, F. ; Scipione, A. ; Timperi, A. ; Mattia, D. ; Marciani, M.G. ; Millán, J. ; Salinari, S. ; Bianchi, L. ; Bablioni, F.

Author_Institution

La Sapienza Univ., Rome, Italy

fYear

2003

fDate

20-22 March 2003

Firstpage

645

Lastpage

647

Abstract

Changes in EEG power spectra related to the imagination of movements may be used to build up a direct communication channel between brain and computer (brain computer interface; BCI). However, for the practical implementation of a BCI device, the feature classifier plays a crucial role. We compared the performance of three different feature classifiers for the detection of the imagined movements in a group of 6 normal subjects by means the EEG. The feature classifiers compared were those based on the hidden Markov models (HMM), the artificial neural network (ANN) and on the Mahalanobis distance (MD). Results show a better performance of the MD and ANN classifiers with respect to the HMM classifier.

Keywords

electroencephalography; feature extraction; hidden Markov models; medical signal processing; neural nets; signal classification; user interfaces; BC1 device; EEG; EEG power spectra; HMM; Mahalanobis distance; artificial neural network; brain computer interfaces; direct communication channel; feature classifier; feature classifiers; hidden Markov models; imagined movement detection; movement imagination; normal subjects; Artificial neural networks; Brain computer interfaces; Communication channels; Computer interfaces; Electrodes; Electroencephalography; Frequency estimation; Hidden Markov models; Scalp; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Engineering, 2003. Conference Proceedings. First International IEEE EMBS Conference on

Print_ISBN

0-7803-7579-3

Type

conf

DOI

10.1109/CNE.2003.1196911

Filename

1196911