一种不完备信息系统的直接约简方法  

Direct Reduction Method for Incomplete Information System

作　　者：黄海[1] 王国胤[1] 吴渝[1] 

机构地区：[1]重庆邮电学院计算机科学与技术研究所,重庆400065

出　　处：《小型微型计算机系统》2005年第10期1761-1765,共5页Journal of Chinese Computer Systems

基　　金：国家自然科学基金(60373111)资助新世纪人才支持计划资助教育部科学技术研究重点项目资助重庆市应用基础研究基金资助重庆市教育委员会科学技术研究项目(040505)资助.

摘　　要：目前已有基于容差关系、相似关系、限制容差关系等的扩充rough集理论,但仅仅是提出了一些针对以上某种模型的 属性约简算法．在此提出从离散化到规则匹配的一系列不完备信息系统的约简处理方法,该方法可以适用于各种rough集扩充 模型,并且对完备信息系统和不完备信息系统是统一的．There are already some extensions of rough set theory for incomplete information systems, such as tolerance relation, limited tolerance relation, non-symmetric similarity relation, and etc, but there are only few attribute reduction algorithms, and each algorithm is based on a specific extension of rough set theory. An extended direct reduction approach for processing incomplete information systems is presented in this paper, which consists of discretization, attribute reduction, value reduction, and rule matching. This approach can be used in all kinds of extensions of rough set theory for incomplete information systems, and is unitive for complete information system and incomplete information systems.

关 键 词：ROUGH集 容差关系 限制容差关系 相似关系 不完备信息系统 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]