«上一篇/Previous Article|本期目录/Table of Contents|下一篇/Next Article»

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:

期数:

2006年09期

页码:

30-31

栏目:

智能、算法、系统工程

出版日期:

1900-01-01

文章信息/Info

Title:

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

文章编号:

1673-629X（2006）09-0030-02

作者:

冯利军¹; 2 李书全¹ 宋连友[3]

[1]天津财经大学[2]河北农业大学[3]沧州师范专科学校

Author(s):

FENG Li-jun;  LI Shu-quan;  SONG Lian-you

[1]Tianjin University of Finance and Economics[2]Agriculture University of Hebei[3]Cangzhou Teacher＇ s College

关键词:

粗糙集; 支持向量机; 预测

Keywords:

rough sets;  support vector machine;  prediction

分类号:

TP18

文献标志码:

A

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

Abstract:

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

备注/Memo

备注/Memo:

天津市教委十五综合投资项目（2004BA11）冯利军（1974-），男，河北涉县人，博士研究生，主要从事项目智能管理等研究；李书全，教授，主要从事项目管理、机器学习等方面的研究

常用功能

更新日期/Last Update: 1900-01-01