Study on Application of Support Vector Machine for Classification Based on KPCA and RS Theory
Yuan Mei-lingb · Tongji yu xinxi luntan · 2008
Kernel Principle Component Analysis KPCA is one of the most effective methods for dimention reduction proposed in recent years.However,it does not guarantee that the selected first principle components will be the most adequate for classification.An effective solution dealing with this problem is to apply rough sets theory.This paper proposes a Support Vector Classifier SVC based on KPCA and Rough Sets Theory.In order to reduce the scale of the problem as well as improve the performance of SVC,the presented classifier implements a feature selection algorithm based on Rough Sets Theory and information entropy to reserve important features of dataset after feature extraction using KPCA.The numerical experiment of modeling financial distress early warning for listed companies shows the superior performance of this classifier.