Common Spatial Pattern and Particle Swarm Optimization for Channel Selection in BCI

Author

Lv, Jun ; Liu, Meichun

Author_Institution

Sch. of Electron. & Inf. Eng., South China Univ. of Technol., Guangzhou

fYear

2008

fDate

18-20 June 2008

Firstpage

457

Lastpage

457

Abstract

Common spatial pattern algorithm (CSP) is famous for extracting ERD/ERS feature from multi-channel BCIs based on motor imagery. However, if channel number is large, CSP will tend to overfitting and it is inconvenient for clinical operation. In this study, CSP filters´ discrimination and channel number are integrated under one roof. Then binary particle swarm optimization (BPSO) is employed to select the best channel groups. Experimental results of BCI2003 dataset IV and BCI2005 dataset I show that good classification accuracies can be achieved only with 914 channels.

Keywords

evolutionary computation; human computer interaction; particle swarm optimisation; BPSO; CSP; binary particle swarm optimization; channel groups; channel selection; common spatial pattern; multichannel BCIs; multichannel brain-computer interfaces; Covariance matrix; Data mining; Electroencephalography; Feature extraction; Filters; Linear discriminant analysis; Particle swarm optimization; Robustness; Testing; Topology;

fLanguage

English

Publisher

ieee

Conference_Titel

Innovative Computing Information and Control, 2008. ICICIC '08. 3rd International Conference on

Conference_Location

Dalian, Liaoning

Print_ISBN

978-0-7695-3161-8

Electronic_ISBN

978-0-7695-3161-8

Type

conf

DOI

10.1109/ICICIC.2008.196

Filename

4603646