Imagined hand movement identification based on spatio-temporal pattern recognition of EEG

Author

Liu, He Sheng ; Gao, Xiaorong ; Yang, Fusheng ; Gao, Shangkai

Author_Institution

Dept. of Biomed. Eng., Tsinghua Univ., Beijing, China

fYear

2003

fDate

20-22 March 2003

Firstpage

599

Lastpage

602

Abstract

Brain-computer interface (BCI) based on EEG changes during different types of motor imagery is an interesting research area attracting many researchers. A novel hierarchical multi-method approach is proposed which has been successfully applied to discrimination of the imagined left- and right-hand movements. The signal processing methods employed are described in detail, including common spatial subspace decomposition (CSSD), Shrinking LORETA-FOCUSS, 3D micro-state analysis and hidden Markov model (HMM). The results on a set of experimental data are also provided.

Keywords

electroencephalography; hidden Markov models; medical signal processing; pattern recognition; prosthetics; user interfaces; 3D micro-state analysis; CSSD; EEG; HMM; Shrinking LORETA-FOCUSS; brain-computer interface; common spatial subspace decomposition; hidden Markov model; hierarchical multi-method approach; imagined hand movement identification; imagined left-hand movements; imagined right-hand movements; motor imagery; research area; signal processing methods; spatio-temporal pattern; spatio-temporal pattern recognition; Biomedical engineering; Brain computer interfaces; Covariance matrix; Electroencephalography; Helium; Hidden Markov models; Pattern recognition; Principal component analysis; Scalp; Spatial filters;

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.2003.1196899

Filename

1196899