不完备区间值信息系统中基于相容-相似关系的模糊粗糙集方法  

Tolerance-similarity Based Fuzzy Rough Set Approach for Incomplete Interval-valued Information Systems

作　　者：王虹[1] 李宁 WANG Hong;LI Ning(College of Mathematics and Computer Science,Shan'xi Normal University,Linfen 041004,China)

机构地区：[1]山西师范大学数学与计算机科学学院

出　　处：《数学的实践与认识》2019年第24期123-132,共10页Mathematics in Practice and Theory

基　　金：省自然科学基金(201601D011043)

摘　　要：区间值信息系统是单值信息系统的推广模型.区间值是描述影响观测对象值的一种表示方法.然而,在实际应用中,由于遗漏、测量误差、数据传输、介质噪声等多种因素的影响,区间值往往会出现缺失值.如果忽略或丢弃包含缺失值的数据,则必须丢弃大量信息.主要针对不完备区间值信息系统,提出一种基于相容-相似关系的模糊粗糙集方法.在此基础上,推广了模糊近似算子的定义,研究了不确定性度量问题.Interval-valued information systems are general models of single-valued information systems.Interval value is a representation method to describe the value of the observed object.However,in real life applications,interval-valued data often obtain missing values caused by various factors such as omissions,measurement error,data transmission,media noise and others.If data containing missing values is ignored or discarded,we have to throw much information away.The aim of this paper is to present a tolerance-similarity relation based fuzzy rough set approach for incomplete interval・valued information systems.Based on the proposed relation,we extend the definitions of fuzzy approximation operators and investigate the uncertainty measurement issue.

关 键 词：不完备区间值信息系统 相容-相似关系 不确定性度量 条件熵 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]