Computer Engineering and Applications ›› 2008, Vol. 44 ›› Issue (24): 162-164.DOI: 10.3778/j.issn.1002-8331.2008.24.049

• 数据库、信号与信息处理 • Previous Articles     Next Articles

Attribute reduction algorithm for inconsistent decision tables

QIN Chuan1,CHEN Hai-jun3,SHI Hua-ji1,LI Xing-yi1,2   

  1. 1.College of Computer,Jiangsu University,Zhenjiang,Jiangsu 212013,China
    2.College of Electronics and Information,Beijing Jiaotong University,Beijing 100044,China
    3.The Units of Taiyuan Railway,Taiyuan 030013,China
  • Received:2007-10-29 Revised:2008-01-02 Online:2008-08-21 Published:2008-08-21
  • Contact: QIN Chuan

不相容决策表的属性约简算法

秦 川1,陈海军3,施化吉1,李星毅1,2   

  1. 1.江苏大学 计算机学院,江苏 镇江 212013
    2.北京交通大学 电子信息学院,北京 100044
    3.太原铁路局,太原 030013
  • 通讯作者: 秦 川

Abstract: The Skowron’s discernibility matrix is analyzed in this article.The anti-cases is presented that shows the mistake still exists in the attribute reduction algorithm based on Skowron’s discernibility matrix.To this issue,an attribute frequency reduction algorithm based on improved discernibility matrix is presented in this article.The discernibility matrix is the foundation of the algorithm,the attribute frequency is used as heuristic information in this algorithm and a process of reducing again is used in the algorithm in order to eliminate redundancy attributes.The example is presented in the article that validates the attribute reduction algorithm can be used in consistent decision tables and inconsistent decision tables.

Key words: inconsistent decision table, attribute reduction, attribute frequency, discernibility matrix, core

摘要: 对Skowron可辨识矩阵方法进行分析,并应用反例说明基于Skowron可辨识矩阵的属性约简算法对不相容决策表的属性约简,可能会导致错误的结果。针对这一问题,提出了一种基于改进可辨识矩阵的属性频率约简算法。该算法以改进的可辨识矩阵为基础,以属性频率作为启发信息,同时在算法中加入消除冗余属性二次约简过程。提供了实例分析,验证了该算法能够有效地对相容与不相容的决策表进行属性约简。

关键词: 不相容决策表, 属性约简, 属性频率, 可辨识矩阵,