模式识别与人工智能
2025年4月7日 星期一   首 页     期刊简介     编委会     投稿指南     伦理声明     联系我们                                                                English
模式识别与人工智能  2017, Vol. 30 Issue (12): 1121-1129    DOI: 10.16451/j.cnki.issn1003-6059.201712008
研究与应用 最新目录| 下期目录| 过刊浏览| 高级检索 |
联合谱聚类与邻域互信息的特征选择算法*
胡敏杰,郑荔平,唐莉,林耀进
闽南师范大学 计算机学院 漳州 363000
Feature Selection Algorithm Based on Joint Spectral Clustering and Neighborhood Mutual Information
HU Minjie, ZHENG Liping, TANG Li, LIN Yaojin
School of Computer Science, Minnan Normal University, Zhangzhou 363000

全文: PDF (815 KB)   HTML (1 KB) 
输出: BibTeX | EndNote (RIS)      
摘要 针对特征空间中存在潜在相关特征的规律,分别利用谱聚类探索特征间的相关性及邻域互信息以寻求最大相关特征子集,提出联合谱聚类与邻域互信息的特征选择算法.首先利用邻域互信息移除与标记不相干的特征.然后采用谱聚类将特征进行分簇,使同一簇组中的特征强相关而不同簇组中的特征强相异.继而基于邻域互信息从每一特征簇组中选择与类标记强相关而与本组特征低冗余的特征子集.最后将所有选中特征子集组成最终的特征选择结果.在2个基分类器下的实验表明,文中算法能以较少的合理特征获得较高的分类性能.
服务
把本文推荐给朋友
加入我的书架
加入引用管理器
E-mail Alert
RSS
作者相关文章
胡敏杰
郑荔平
唐莉
林耀进
关键词 特征选择谱聚类互信息邻域互信息    
Abstract:Aiming at some potential correlation between features in feature space, spectral clustering and neighborhood mutual information are exploited to explore the correlation features and obtain maximal relevant feature subset, respectively. And a feature selection algorithm combining spectral clustering and neighborhood mutual information is proposed. In this paper, the neighborhood mutual information is firstly applied to remove uncorrelated features, and then the spectral clustering is utilized to group features. The features of the same group are strongly correlated and the features of different groups are strongly different. Then, the feature subset strongly associated with class label is selected from each feature group. Finally, all selected feature subsets are collected together to form the final selected features. Extensive experiment is conducted with two different classifiers. Experimental results show that the proposed model effectively improves the classification performance with less features.
Key wordsFeature Selection    Spectral Clustering    Mutual Information    Neighborhood Mutual Information   
收稿日期: 2017-05-10     
ZTFLH: TP 18  
基金资助:国家自然科学基金项目(No.61303131)、福建省教育厅科技项目(No.JAT170347,JAT1703501)资助
作者简介: 胡敏杰(通讯作者),女,1979年生,硕士,讲师,主要研究方向为特征选择.E-mail:zzhuminjie@sina.com.
郑荔平,女,1977年生,硕士,讲师,主要研究方向为数据挖掘.E-mail:zheng_joy9306188@qq.com.
唐 莉,女,1993年生,硕士研究生,主要研究方向为数据挖掘.E-mail:tangli0447@163.com.
林耀进,男,1980年生,博士,副教授,主要研究方向为数据挖掘、粒计算.E-mail:yjlin@mnnu.edu.cn.
引用本文:   
胡敏杰,郑荔平,唐莉,林耀进. 联合谱聚类与邻域互信息的特征选择算法*[J]. 模式识别与人工智能, 2017, 30(12): 1121-1129. HU Minjie, ZHENG Liping, TANG Li, LIN Yaojin. Feature Selection Algorithm Based on Joint Spectral Clustering and Neighborhood Mutual Information. , 2017, 30(12): 1121-1129.
链接本文:  
http://manu46.magtech.com.cn/Jweb_prai/CN/10.16451/j.cnki.issn1003-6059.201712008      或     http://manu46.magtech.com.cn/Jweb_prai/CN/Y2017/V30/I12/1121
版权所有 © 《模式识别与人工智能》编辑部
地址:安微省合肥市蜀山湖路350号 电话:0551-65591176 传真:0551-65591176 Email:bjb@iim.ac.cn
本系统由北京玛格泰克科技发展有限公司设计开发 技术支持:support@magtech.com.cn