| 一种改进的SVM决策树Web文本分类算法 |
| |
| 引用本文： | 徐丽,伏玉琛,李斯.一种改进的SVM决策树Web文本分类算法[J].苏州大学学报(工科版),2011,31(5). |
| |
| 作者姓名： | 徐丽 伏玉琛 李斯 |
| |
| 作者单位： | 苏州大学计算机科学与技术学院,江苏苏州,215006 |
| |
| 基金项目： | 国家自然科学基金资助项目(编号61070122、60873116); 江苏省自然科学基金资助项目(编号BK2008161); 江苏省高校自然科学研究项目(编号09KJA520002); 江苏省计算机信息处理技术重点实验室基金资助项目(编号kjs1024); 江苏省现代企业信息化应用支撑软件工程技术研究开发中心项目(编号SX200902) |
| |
| 摘 要： | SVM决策树能够较好地进行Web文本信息分类,在此基础上进一步结合遗传算法,将SVM决策树分类器的分类正确率作为GA适应度函数,对SVM决策树层次结构进行优化,在每一决策节点自动选择最优或近优的分类决策。实验结果表明,采用该方法进行多类分类,分类精度明显提高,体现了将遗传算法与SVM决策树结合的优越性。
|
| 关 键 词： | Web文本文类 支持向量机 遗传算法 多分类 |
Web Text Classifier Based on an Improved SVM Decision Tree |
| |
| Xu Li ,Fu Yuchen,Li Si.Web Text Classifier Based on an Improved SVM Decision Tree[J].Journal of Suzhou University(Engineering Science Edition),2011,31(5). |
| |
| Authors: | Xu Li Fu Yuchen Li Si |
| |
| Affiliation: | Xu Li 1,Fu Yuchen1,2,Li Si1(1.School of Computer Science and Technology,Soochow University,Suzhou 215006,China,2.R&D Center of Jiangsu Modern Enterprise Informationization Application Support for Software Engineering Technology,Suzhou 215104,China) |
| |
| Abstract: | The method of SVM decision tree can solve Web text information classification problems.In this paper,we generate a decision tree to build the SVM classifier on the test samples of the classification accuracy rate as the genetic algorithm fitness function,and then with the help of genetic algorithm,we find the optimal decision tree,and then construct an optimal decision tree SVM classifier.Experiment results show that the accuracy of the method of improved SVM decision tree is improved,manifest the advantage... |
| |
| Keywords: | Web document classification support vector machine genetic algorithm multi-class classification |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
