计算机工程与应用 ›› 2009, Vol. 45 ›› Issue (31): 115-117.DOI: 10.3778/j.issn.1002-8331.2009.31.034

• 数据库、信号与信息处理 • 上一篇    下一篇

基于覆盖算法的条件信息熵表示及属性约简

单雪红1,2,吴 涛2,3,李国成2   

  1. 1.宿州学院 数学系,安徽 宿州 234000
    2.安徽大学 数学科学学院,合肥 230039
    3.安徽大学 智能计算与信号处理教育部重点实验室,合肥 230039
  • 收稿日期:2008-06-24 修回日期:2009-09-20 出版日期:2009-11-01 发布日期:2009-11-01
  • 通讯作者: 单雪红

Conditional information entropy based on covering algorithm and attributes reduction

SHAN Xue-hong1,2,WU Tao2,3,LI Guo-cheng2   

  1. 1.Deparement of Mathematics,Suzhou College,Suzhou,Anhui 234000,China
    2.School of Mathematics Science,Anhui University,Hefei 230039,China
    3.Key Lab IC&SP,Anhui University,Hefei 230039,China
  • Received:2008-06-24 Revised:2009-09-20 Online:2009-11-01 Published:2009-11-01
  • Contact: SHAN Xue-hong

摘要: 利用覆盖算法对数据进行处理,得到论域U的一个划分,定义一种基于覆盖的条件信息熵,由新的条件信息熵定义新的属性重要性,并证明了对于一致决策表,它与代数定义下的重要性是等价的。以新的属性重要性为启发信息设计约简算法,并给出计算新的条件信息熵的算法。实验结果表明该约简算法能快速搜索到最优或次优约简。

关键词: 覆盖算法, Rough集理论, 知识约简, 条件信息熵

Abstract: Processing data can be partitioned using covering algorithm.In this paper,a new concept of conditional information entropy is put forward,and then the new significance of an attributes is defined based on this entropy.In a consistent decision table,the equivalence between algebraic significance and conditional information entropy significance of attributes is proved.But it is incorrect in the inconsistent decision table.A heuristic algorithm for knowledge reduction is designed.The experimental results show that this algorithm can find the minimal or optimal reduction.

Key words: covering algorithm, rough set theory, reduction, conditional information entropy

中图分类号: