期刊
PATTERN RECOGNITION LETTERS
卷 40, 期 -, 页码 104-112出版社
ELSEVIER
DOI: 10.1016/j.patrec.2013.12.008
关键词
Pattern recognition; Unsupervised feature selection; Mutual information; Normalized mutual information
资金
- Department of Science and Technology, India [DST/INSPIRE 2011/208]
- Department of Science and Technology, Government of India [DST/SJF/ET-02/2006-07]
In this article a dense subgraph finding approach is adopted for the unsupervised feature selection problem. The feature set of a data is mapped to a graph representation with individual features constituting the vertex set and inter-feature mutual information denoting the edge weights. Feature selection is performed in a two-phase approach where the densest subgraph is first obtained so that the features are maximally non-redundant among each other. Finally, in the second stage, feature clustering around the non-redundant features is performed to produce the reduced feature set. An approximation algorithm is used for the densest subgraph finding. Empirically, the proposed approach is found to be competitive with several state of art unsupervised feature selection algorithms. (C) 2013 Elsevier B. V. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据