《计算机应用研究》|Application Research of Computers

非一致性引导的无监督特征选择

Unsupervised feature selection guided by disagreement

免费全文下载 (已被下载 次)  
获取PDF全文
作者 王莹莹,曲衍鹏
机构 大连海事大学 信息科学技术学院,辽宁 大连 116026
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2021)10-023-3019-06
DOI 10.19734/j.issn.1001-3695.2021.03.0043
摘要 由于无监督环境下特征选择缺少类别信息的依赖,所以利用模糊粗糙集理论提出一种非一致性度量方法DAM(disagreement measure),用于度量任意两个特征集合或特征间引起的模糊等价类含义的差异程度。在此基础上实现DAMUFS无监督特征选择算法,其在无监督条件下可以选择出包含更多信息量的特征子集,同时还保证特征子集中属性冗余度尽可能小。实验将DAMUFS算法与一些无监督以及有监督特征选择算法在多个数据集上进行分类性能比较,结果证明了DAMUFS的有效性。
关键词 无监督特征选择; 非一致性; 模糊粗糙集; 数据预处理
基金项目 国家自然科学基金资助项目(61502068)
大连市青年科技之星项目(2018RQ70)
本文URL http://www.arocmag.com/article/01-2021-10-023.html
英文标题 Unsupervised feature selection guided by disagreement
作者英文名 Wang Yingying, Qu Yanpeng
机构英文名 School of Information Science & Technology,Dalian Maritime University,Dalian Liaoning 116026,China
英文摘要 Because feature selection in an unsupervised environment lacks dependence on category information, this paper proposed a disagreement measure(DAM) with the use of the fuzzy rough set theory. DAM measured the degree of difference in meaning of fuzzy equivalence of any two feature sets or features. On this basis, this paper proposed the DAMUFS unsupervised feature selection algorithm. The DAMUFS algorithm could select feature subsets that contained more information under unsupervised conditions, while also ensuring that the attribute redundancy in the feature subset was as small as possible. The experiment compared the classification performance of DAMUFS algorithm with some unsupervised and supervised feature selection algorithms on multiple data sets. And the results prove the effectiveness of DAMUFS algorithm.
英文关键词 unsupervised feature selection; disagreement; fuzzy-rough set; data preprocessing
参考文献 查看稿件参考文献
 
收稿日期 2021/3/10
修回日期 2021/4/25
页码 3019-3024
中图分类号 TP3
文献标志码 A