| A bidirectional feature selection method based on mutual information and redundancy-synergy coefficient |
| |
| 作者姓名： | 杨胜 张治 施鹏飞 |
| |
| 作者单位： | [1]School of Computer and Communication,Hunan University, Changsha 410082,China [2]Institute of Image Processing ＆ Pattern Recognition, Shanghai Jiaotong University, Shanghai 200030, China |
| |
| 摘 要： | Featuresubsetselection(FSS)istoselectrele vantfeaturesandcastawayirrelevantandredundantfeaturesfromtheoriginalfeaturesetaccordingtoaFSSmeasure1].IfafeaturesubsetsatisfiestheFSSmeas ureandhastheminimumsize,itisconsideredapartoftheoptimalfeaturesubset.Comp…
|
| 关 键 词： | 交互信息 特征选择 模式分类 数据挖掘 |
| 文章编号： | 1005-9113（2006）03-0299-08 |
| 收稿时间： | 2003-10-31 |
A bidirectional feature selection method based on mutual information and redundancy-synergy coefficient |
| |
| YANG Sheng,ZHANG Zhi,SHI Peng-fei.A bidirectional feature selection method based on mutual information and redundancy-synergy coefficient[J].Journal of Harbin Institute of Technology,2006,13(3):299-306. |
| |
| Authors: | YANG Sheng ZHANG Zhi SHI Peng-fei |
| |
| Abstract: | Feature subset selection is a fundamental problem of data mining. The mutual information of feature subset is a measure for feature subset containing class feature information. A hashing mechanism is proposed to calculate the mutual information of feature subset. The feature relevancy is defined by mutual information. Redundancy-synergy coefficient, a novel redundancy and synergy measure for features to describe the class feature, is defined. In terms of information maximization rule, a bidirectional heuristic feature subset selection method based on mutual information and redundancy-synergy coefficient is presented. This study' s experiments show the good performance of the new method. |
| |
| Keywords: | mutual information feature selection pattern classification data mining |
| 本文献已被 维普 万方数据 等数据库收录！ |
