基于距离测度的模糊粗糙集属性约简  

Attribute reduction with fuzzy rough set based on distance measures

作　　者：齐媛媛[1] 王长忠[1] QI Yuan-yuan WANG Chang-zhong(College of Mathematics and Physics, Bohai University, Jinzhou 121013, China)

机构地区：[1]渤海大学数理学院,辽宁锦州121013

出　　处：《渤海大学学报（自然科学版）》2016年第3期208-212,共5页Journal of Bohai University:Natural Science Edition

基　　金：国家自然科学基金项目(No:61572082);辽宁省自然科学基金项目(No:2014020142)

摘　　要：属性约简是模糊粗糙集理论的重要研究内容.本文引进了基于距离的模糊相似关系,建立了距离测度下的模糊粗糙模型,从而得到条件属性和决策属性之间的依赖函数,通过此函数构造了前向搜索属性约简算法.并利用了UCI标准数据集与现有算法进行比较,从而验证了该算法的可行性和有效性.Attribute reduction is one of the most important topics in fuzzy rough set theory .This paper first introduces fuzzy similar relation based on distance ,presents a new fuzzy rough set model based on distance meas-ures.Then,the dependency between condition attribute and decision attribute is proposed ,by which a greedy for-ward algorithm for attribute reduction is designed .The data sets selected from UCI are used to compare the pro-posed algorithm with some existing algorithms ,and the experimental results show that the proposed reduction algo-rithm is feasible and effective .

关 键 词：属性约简 模糊粗糙集 模糊相似关系 依赖函数 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]