Unsupervised feature selection based on maximum information and minimum redundancy for hyperspectral images
详细信息 查看全文
- 作者：Jie Feng ; jiefeng0109@163.com" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae ; Licheng Jiao lchjiao@mail.xidian.edu.cn" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae ; Fang Liu f63liu@163.com" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae ; Tao Sun taosun@mail.xidian.edu.cn" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae ; Xiangrong Zhang xrzhang@mail.xidian.edu.cn" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae
- 关键词：Unsupervised feature selection ; Hyperspectral images ; Maximum information and minimum redundancy ; Information theory ; Clonal selection algorithm
- 刊名：Pattern Recognition
- 出版年：2016
- 出版时间：March 2016
- 年：2016
- 卷：51
- 期：Complete
- 页码：295-309
- 全文大小：7838 K
文摘
- •
A new MIMR criterion is proposed for unsupervised feature selection.
- •
MIMR can select more informative and distinctive features.
- •
Many classical criteria and MIMR can be unified into the same framework.
- •
The theoretical advantage of MIMR over many classical criteria is given.
- •
Feature selection problem is solved by combinatorial optimization with a new CSA.