Journal of Computer Applications ›› 2012, Vol. 32 ›› Issue (04): 1067-1069.DOI: 10.3724/SP.J.1087.2012.01067

• Database technology • Previous Articles     Next Articles

Rough set based attribute reduction with consistent confidence

GAO CanMIAO Duo-qian2,3,ZHANG Zhi-fei2,3,ZHANG Hong-yun2,3   

  • Received:2011-09-08 Revised:2011-11-18 Online:2012-04-20 Published:2012-04-01
  • Contact: GAO Can

粗糙集信度一致属性约简

高灿1,苗夺谦1,2,张志飞1,2,张红云1,2   

  1. 1. 同济大学 计算机科学与技术系,上海 201804
    2. 同济大学 嵌入式系统与服务计算教育部重点实验室,上海 201804
  • 通讯作者: 高灿
  • 作者简介:高灿(1983-),男,湖南南县人,博士研究生,CCF会员,主要研究方向:粗糙集理论、机器学习;苗夺谦(1964-),男,山西祁县人,教授,博士生导师,CCF高级会员,主要研究方向:粗糙集理论、Web智能、机器学习;张志飞(1986-),男,江苏南通人,博士研究生,CCF会员,主要研究方向:粒计算、文本挖掘;张红云(1972-),女,江苏丹阳人,讲师,博士,CCF会员,主要研究方向:主曲线、粒计算。
  • 基金资助:
    国家自然科学基金资助项目;上海市重点学科建设项目

Abstract: In order to solve the problem of reduction anomaly in the existing probabilistic rough set models, non-parameterized and parameterized maximum decision entropy measures for attribute reduction were proposed by using the concept of maximum confidence of uncertain object. The monotonicity of the parameterized maximum decision entropy was explained and the relationship between its attribute reduction and other ones was analyzed. The definitions for core and relatively dispensable attributes in the proposed model were also given. Moreover, non-parameterized and parameterized confidence discernibility matrixes were put forward and the difference of classical discernibility matrix and the proposed ones in charactering the uncertain object were discussed. Finally, a case study was given to show the validity of the proposed model.

Key words: probabilistic rough set, attribute reduction, reduction anomaly, maximum decision entropy, confidence discernibility matrix

摘要: 为了消除现有概率粗糙集模型约简过程中出现的诸多约简异常问题,通过引入对象最大信度概念,提出了非参与带参最大决策熵属性约简模型,阐明了带参最大决策熵测度的单调性,给出了带参最大决策熵核和相对不必要属性的定义,并分析了其约简与已有概率粗糙集模型约简的关系。其次将对象置信度引入差别矩阵,构建了带参与非参信度差别矩阵,讨论了其定义与经典差别矩阵对不确定对象刻画的差异性。最后运用实例验证了方法的有效性。

关键词: 概率粗糙集, 属性约简, 约简异常, 最大决策熵, 信度差别矩阵

CLC Number: