A pattern classification method based on GA and SVM

Author

Xiangrong, Zhang ; Fang, Liu

Author_Institution

Sch. of Comput. Sci. & Technol., Xidian Univ., Xi´´an, China

Volume

1

fYear

2002

fDate

26-30 Aug. 2002

Firstpage

110

Abstract

A method for pattern classification on large-scale training data is presented in this paper, which is based upon the genetic algorithm (GA) and support vector machine (SVM). The initial training data are optimized with GA in order to find a sample subset including the important samples that can preserve or improve the discrimination ability of SVM. Training on the subset is equal to that on the initial sample sets. The training time is greatly shortened. Following the result, we take advantage of the excellent classification performance of SVM to accomplish the pattern classification.

Keywords

genetic algorithms; learning automata; pattern classification; GA; SVM; classification performance; discrimination ability; genetic algorithm; large-scale. training data; pattern classification method; support vector machine; training data; training time; Face detection; Genetic algorithms; Machine learning; Multi-layer neural network; Neural networks; Pattern classification; Risk management; Support vector machine classification; Support vector machines; Training data;

fLanguage

English

Publisher

ieee

Conference_Titel

Signal Processing, 2002 6th International Conference on

Print_ISBN

0-7803-7488-6

Type

conf

DOI

10.1109/ICOSP.2002.1180997

Filename

1180997