An Evolutionary Artificial Immune System for feature selection and parameters optimization of support vector machines for ERP assessment in a P300-based GKT

Author

Shojaie, S. ; Moradi, M.H.

Author_Institution

Biomed. Eng. Fac., Amirkabir Univ. of Technol., Tehran

fYear

2008

fDate

18-20 Dec. 2008

Firstpage

1

Lastpage

5

Abstract

Optimizing a classifier is a subject of great interest in the research area. A lot of methods inspired of biological metaphors are proposed for this task. This paper present a new algorithm based on the natural immune metaphors which select a proper subset of features and optimal parameters of a support vector machines (SVM) classifier. The designed optimization method is validated for ERP assessment in a P300-based GKT (guilty knowledge test). The result experiment shows the effectiveness of the method.

Keywords

artificial immune systems; bioelectric potentials; electroencephalography; feature extraction; medical signal processing; signal classification; support vector machines; ECG; ERP assessment; P300-based GKT; SVM; artificial immune system; biological metaphor; electroencephalography; event related potential; guilty knowledge test; natural immune metaphor; support vector machine; Adaptive systems; Artificial immune systems; Cloning; Enterprise resource planning; Immune system; Kernel; Optimization methods; Support vector machine classification; Support vector machines; Testing; Artificial Immune System; Classification; Feature selection; Support vector machines;

fLanguage

English

Publisher

ieee

Conference_Titel

Biomedical Engineering Conference, 2008. CIBEC 2008. Cairo International

Conference_Location

Cairo

Print_ISBN

978-1-4244-2694-2

Electronic_ISBN

978-1-4244-2695-9

Type

conf

DOI

10.1109/CIBEC.2008.4786065

Filename

4786065