SVM feature selection and sample regression for Chinese medicine research

Author

Li, Wei ; Zhao, Yannan ; Song, Yixu ; Yang, Zehong

Author_Institution

Dept. of Comput. Sci., Tsinghua Univ., Beijing

fYear

2008

fDate

20-23 June 2008

Firstpage

1773

Lastpage

1777

Abstract

In this paper, SVM based feature selection methods are introduced for regression problem of COX2 inhibitor activity prediction in Chinese medicine quantitative structure-activity relationship (QSAR) research. We develop a recursive SVM feature selection algorithm for regression and compare its performance with genetic algorithm and SVM recursive feature elimination (SVM-RFE) algorithm. Experiments on real Chinese medicine dataset show that our method is a fast and accurate algorithm for Chinese medicine regression problem with a small number of samples.

Keywords

feature extraction; genetic algorithms; medical information systems; recursive estimation; regression analysis; sampling methods; support vector machines; COX2 inhibitor activity prediction; Chinese medicine research; genetic algorithm; quantitative structure-activity relationship; recursive SVM feature elimination algorithm; recursive SVM feature selection algorithm; sample regression problem; Biochemistry; Chemical analysis; Computer science; Genetic algorithms; Humans; Inhibitors; Machine learning; Machine learning algorithms; Support vector machine classification; Support vector machines;

fLanguage

English

Publisher

ieee

Conference_Titel

Information and Automation, 2008. ICIA 2008. International Conference on

Conference_Location

Changsha

Print_ISBN

978-1-4244-2183-1

Electronic_ISBN

978-1-4244-2184-8

Type

conf

DOI

10.1109/ICINFA.2008.4608293

Filename

4608293