利用粗糙集理论提高SVM预测系统的实时性  

Improving Real-Time Character of Prediction System Based on SVM Using RS Theory

作　　者：冯利军[1] 李书全[1] 宋连友[2] 

机构地区：[1]天津财经大学 [2]沧州师范专科学校,河北沧州061001

出　　处：《计算机技术与发展》2006年第9期30-31,34,共3页Computer Technology and Development

基　　金：天津市教委十五综合投资项目(2004BA11)

摘　　要：支持向量机是一种新的机器学习方法,它具有良好的推广性和分类精确性。但是在利用支持向量机的分类算法处理实际问题时,该算法的计算速度较慢、处理问题效率较低。文中介绍了一种新的学习算法,就是将粗糙集和支持向量机相结合,利用粗糙集对支持向量机的训练样本进行预处理,从而缩短样本的训练时间,提高基于SVM预测系统实时性。文中最后利用该方法进行了数据试验,试验结果表明了该方法可以大大缩短样本的训练时间,提高基于支持向量机处理预测系统的效率。从而也证明了该方法的有效性。Support vector machine is a kind of new machine learning method. This method has good generality capability and better classification accuracy. But when solve real problem using support vector machine, its computation rate is slow and its efficiency is low. Introduce a kind of method that improves the real - time character of prediction system based on SVM in this paper. That can shorten the training time of prediction system based on SVM by preprocessing the training sample of SVM using rough sets theory. At last, carried on data experiments using this method in this paper. The experiments result indicated that this method can shorten the training time greatly and improve the efficiency of prediction system based on support vector machine. Consequently the experiments result proved the validity of this method.

关 键 词：粗糙集 支持向量机 预测 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]