Selection of relevant features for classification of movements from single movement-related potentials using a genetic algorithm

Author

Yorn-Tov, E. ; Inbar, G.F.

Author_Institution

Fac. of Electr. Eng., Technion-Israel Inst. of Technol., Haifa, Israel

Volume

2

fYear

2001

fDate

2001

Firstpage

1364

Abstract

Classification of movement-related potentials recorded from the scalp to their corresponding limb is a crucial task in brain-computer interfaces based on such potentials. This paper demonstrates how the features for such a task can be selected from a large bank of features using a genetic algorithm. We show that it is possible to differentiate between the movements of contralateral fingers with a classification accuracy of 77% using a small number of features (10-20) selected from a bank containing roughly 1000 features.

Keywords

electroencephalography; feature extraction; genetic algorithms; handicapped aids; learning automata; medical signal processing; signal classification; EEG noise; autoregressive coefficients; brain-computer interfaces; classification accuracy; contralateral fingers; cortical potentials; disabled people; electroencephalographic signal; feature selection; genetic algorithm; large bank of features; movements classification; scalp potentials; single movement-related potentials; support vector machine; voluntary movement; Brain computer interfaces; Detectors; Electroencephalography; Feedback; Fingers; Genetic algorithms; Materials requirements planning; Microswitches; Scalp; Signal to noise ratio;

fLanguage

English

Publisher

ieee

Conference_Titel

Engineering in Medicine and Biology Society, 2001. Proceedings of the 23rd Annual International Conference of the IEEE

ISSN

1094-687X

Print_ISBN

0-7803-7211-5

Type

conf

DOI

10.1109/IEMBS.2001.1020450

Filename

1020450