Computer Engineering and Applications ›› 2011, Vol. 47 ›› Issue (2): 124-126.DOI: 10.3778/j.issn.1002-8331.2011.02.039

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

New method of attribute reduction algorithm for inconsistent decision table

LIU Haitao1,2,ZHAI Jingmei1,XU Xiao1   

  1. 1.School of Mechanical & Automotive Engineering,South China University of Technology,Guangzhou 510640,China
    2.School of Engineering,Guangdong Ocean University,Zhanjiang,Guangdong 524088,China
  • Received:2009-04-27 Revised:2009-07-21 Online:2011-01-11 Published:2011-01-11
  • Contact: LIU Haitao


刘海涛1,2,翟敬梅1,徐 晓1   

  1. 1.华南理工大学 机械与汽车工程学院,广州 510640
    2.广东海洋大学 工程学院,广东 湛江 524088
  • 通讯作者: 刘海涛

Abstract: In order to solve the disadvantages of the attribute reduction algorithm for inconsistent decision table,combining information view and the algebra view in rough set,the discernibility matrix is improved,a new method of attribute reduction algorithm is presented,which reduces the time complexity in the case of the positive regions and information entropy unchanged after attribute reduction.The example of computing and analyzing with the proposed method shows its advantages and feasibility.

Key words: rough set, discernibility matrix, attribute reduction

摘要: 针对不相容决策表中一些属性约简算法的不足,结合粗糙集的代数观与信息观的优点,对差别矩阵加以改进,提出了一种新的属性约简算法,该算法在保证约简后决策表的正域和条件信息熵不变的情况下,降低了时间复杂度。通过实例说明了该算法的有效性和可行性。

关键词: 粗糙集, 差别矩阵, 属性约简

CLC Number: