P300 Feature Extraction Based on Parametric Model and FastICA Algorithm

Author

Xiaoyan, Qiao ; Douzhe, Li ; Youer, Dong

Author_Institution

Coll. of Phys. & Electron. Eng., Shanxi Univ., Taiyuan, China

Volume

2

fYear

2009

fDate

14-16 Aug. 2009

Firstpage

585

Lastpage

589

Abstract

A method based on AR model and FastICA algorithm for P300 feature extracting is presented. In the study, the visual evoked signal is obtained via the alternate pictures. Then, principal component analysis (PCA) is used for reducing the dimension of EEG signal, independent component analysis (ICA) is used for removing EOG artifact. And AR model is constructed for filtrating the spontaneous EEG. Finally, a coherence average is used to extract P300 in real-time. The results have shown that this method can perform effectively to extract P300 feature independently to any prior information and avoid the subject´s visual fatigue caused by long time visual evoking. It can be applied on online BCI system.

Keywords

electro-oculography; electroencephalography; feature extraction; filtering theory; independent component analysis; medical signal processing; principal component analysis; AR model; EEG signal; EOG artifact removal; FastICA algorithm; P300 feature extraction; coherence average; independent component analysis; online BCI system; parametric model; principal component analysis; visual evoked signal; Brain modeling; Coherence; Data mining; Electroencephalography; Electrooculography; Fatigue; Feature extraction; Independent component analysis; Parametric statistics; Principal component analysis; Feature Extract; ICA; P300; Parametric Model;

fLanguage

English

Publisher

ieee

Conference_Titel

Natural Computation, 2009. ICNC '09. Fifth International Conference on

Conference_Location

Tianjin

Print_ISBN

978-0-7695-3736-8

Type

conf

DOI

10.1109/ICNC.2009.160

Filename

5362777