An Optimized Multi-class Classification Algorithm Based on SVM Decision Tree

Author

Donghui, Chen ; Zhijing, Liu

Author_Institution

Sch. of Comput. Sci. & Technol., Xidian Univ. Xi´´an, Xi´´an, China

fYear

2010

fDate

24-25 July 2010

Firstpage

44

Lastpage

47

Abstract

An optimized multi-class classification algorithm based on SVM decision tree (SVMDT) is proposed. But by SVMDT, the generalization ability depends on the tree structure. In this paper, the relativity separability measure between classes is defined based on the distribution of the training samples to improve the generalization ability of SVMDT. SVM is extended to non-linear SVM by using kernel functions and the classification experiments prove the algorithm is more effective and feasible for classification accuracy.

Keywords

decision trees; pattern classification; support vector machines; SVM decision tree; kernel functions; multiclass classification algorithm; relativity separability measurement; support vector machines; Classification algorithms; Classification tree analysis; Kernel; Support vector machine classification; Training; SVM; SVMDT; kernel functions; the relativity separability measure;

fLanguage

English

Publisher

ieee

Conference_Titel

Information Technology and Computer Science (ITCS), 2010 Second International Conference on

Conference_Location

Kiev

Print_ISBN

978-1-4244-7293-2

Electronic_ISBN

978-1-4244-7294-9

Type

conf

DOI

10.1109/ITCS.2010.17

Filename

5557333