Rough Set Methods for Constructing Support Vector Machines

Analyzed the generalities and specialties of Rough Sets Theory (RST) and Support Vector Machines (SVM) in knowledge representation and process of regression, a minimum decision network combining RST with SVM in intelligence processing is investigated, and a kind of SVM information process system on RST is proposed for forecasting. Using RST on the advantage of dealing with great data and eliminating redundant information, the system reduced the training data of SVM, and overcame the disadvantage of great data and slow training speed. The experimental results proved that the presented approach could achieve greater forecasting accuracy and generalization ability than the BP neural network and standard SVM.

Authors and Affiliations

1. Department of Automation, University of Science and Technology of China, JinZhai Main Road, 230026, HeFei, P.R.China

   Yuancheng Li

2. Institute of Intelligent Machines, Academia Sinica, 230031, HeFei, P.R.China

   Tingjian Fang

Editors and Affiliations

1. Institute of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, 400065, P.R. China

   Guoyin Wang

2. Department of Computer Science, Nanchang University, Nanchang, 330029, P.R. China

   Qing Liu

3. Department of Computer Science, University of Regina, Regina, Saskatchewan, S4S 0A2, Canada

   Yiyu Yao

4. Institute of Mathematics, Warsaw University, Banacha 2, 02-097, Warsaw, Poland

   Andrzej Skowron

Reprints and permissions

© 2003 Springer-Verlag Berlin Heidelberg

Policies and ethics