计算机工程与应用 ›› 2010, Vol. 46 ›› Issue (1): 99-102.DOI: 10.3778/j.issn.1002-8331.2010.01.031

• 数据库、信号与信息处理 • 上一篇    下一篇

不完备信息系统中属性的重要度及约简方法

杨霁琳1,周玉华2,秦克云1   

  1. 1.西南交通大学 数学学院,成都 610031
    2.信阳职业技术学院,河南 信阳 464000
  • 收稿日期:2008-12-30 修回日期:2009-02-27 出版日期:2010-01-01 发布日期:2010-01-01
  • 通讯作者: 杨霁琳

Important degree of attribute and attribute reduction in incomplete information system

YANG Ji-lin1,ZHOU Yu-hua2,QIN Ke-yun1   

  1. 1.School of Mathematics,Southwest Jiaotong University,Chengdu 610031,China
    2.Xinyang Vocational and Technical College,Xinyang,Henan 464000,China
  • Received:2008-12-30 Revised:2009-02-27 Online:2010-01-01 Published:2010-01-01
  • Contact: YANG Ji-lin

摘要: 在不完备信息系统中,基于相似关系的定义,讨论了属性相对于对象的重要度。通过聚合算子聚合属性相对于所有对象的重要度,可得到属性的重要度。根据属性的重要度,给出了不完备信息系统的一种属性约简方法。实例说明该方法可以减少属性约简的搜索空间并找到不完备信息系统的属性约简。

关键词: 不完备信息系统, 相似关系, 粗糙集, 属性约简, OWA算子

Abstract: Based on definition of similarity relations,significance of the attribute relative to each object is discussed in incomplete information systems.Important degree of the attribute is obtained by using the OWA operator,which can aggregate relative significance of each attribute.According to important degree of the attribute,a new method of attributes reduction is presented.Finally,the experimental results show that the way can not only find the reduction of an incomplete information system,but also reduce the search space of attribute reduction.

Key words: incomplete information system, similarity relations, rough set, attributes reduction, Ordered Weighted Averaging(OWA) operator

中图分类号: