期刊名称：International Journal of Computer Science and Network Security
印刷版ISSN：1738-7906
出版年度：2011
卷号：11
期号：12
页码：85-90
出版社：International Journal of Computer Science and Network Security
摘要：Support Vector Machine has become the reference for many classification problems, because of their flexibility, and capacity to handle high dimensional data. However, the success of Support Vector Machine classifier depends on the perfect choice of the values of its parameters along with the feature subset selection. So the objective of this paper is to propose an Evolutionary Optimization Algorithm (EA) for feature selection and parameter optimization to solve this kind of the SVM depended to improve its performance accuracy. The proposed approach is compared with other approach. The results show that our approach obtained the highest classification accuracy (100%) with limit feature subset selected.
