河北大学学报(自然科学版) ›› 2019, Vol. 39 ›› Issue (3): 225-229.DOI: 10.3969/j.issn.1000-1565.2019.03.001

• •    下一篇

最小相关性最大依赖度属性约简的改进算法

毛华, 赵书峰   

  • 收稿日期:2018-10-25 出版日期:2019-05-25 发布日期:2019-05-25
  • 作者简介:毛华(1963—),女,河北石家庄人,河北大学教授,博士,主要从事拟阵、概念格理论及其应用的研究. E-mail:mh@hbu.edu.cn
  • 基金资助:
    国家自然科学基金资助项目(61572011);河北省自然科学基金资助项目(A2018201117)

An improved algorithm with the principle of minimal correlation and maximal dependency

MAO Hua,ZHAO Shufeng   

  1. College of Mathematics and Information Science, Hebei University, Baoding 071002, China
  • Received:2018-10-25 Online:2019-05-25 Published:2019-05-25

摘要: 对于决策表的属性约简,通过分析最小相关性最大依赖度属性约简算法,得到了一种更加完善的最小相关性最大依赖度属性约简算法,并通过实例验证其可行性.

关键词: 属性约简, 依赖度, 信息熵, 互信息

Abstract: For attribute reduction in decision table, after analyzing the algorithm which calculates the reduction with the principle of minimal correlation and maximal dependency,an improved algorithm with the principle of minimal correlation and maximal dependency is found out. An example is used to check the feasibility of this algorithm.

Key words: attribute reduction, dependency, information entropy, mutual information

中图分类号: