期刊导航

论文摘要

可信度差别矩阵及其属性约简

Discernibility Matrix Based on Credibility and Attribute Reduction Method

作者:葛浩(滁州学院 电子信息工程系);李龙澍(安徽大学 计算机学院);杨传健(滁州学院 计算机系)

Author:Ge Hao(Dept. of Electronicand Info. Eng., Chuzhou Univ.);Li Longshu(School of Computer Sci.,Anhui Univ.);Yang Chuanjian(Dept. of Computer Sci.,Chuzhou Univ.)

收稿日期:2010-09-25          年卷(期)页码:2011,43(5):146-152

期刊名称:工程科学与技术

Journal Name:Advanced Engineering Sciences

关键字:粗糙集;差别矩阵;属性约简;核属性

Key words:rough set;discernibility matrix;attribute reduction;core attribute

基金项目:安徽省自然科学基金资助项目(090412054);安徽高校省级自然科学研究项目(KJ2011Z276);安徽省高等学校省级优秀青年人才基金项目(2011SQRL123);滁州学院科学研究项目(2010kj014B;2011kj003Z)

中文摘要

针对决策表中因存在不一致数据而造成求核和属性约简的错误,引入对象可信度的定义,并将其添加到决策表中,以区分不一致和一致对象;然后,给出差别矩阵的定义,以及基于该差别矩阵的核属性和属性约简定义,同时证明了由该定义获得的核和属性约简与正区域的核和属性约简是等价的;最后,设计属性约简算法及其改进算法,并通过实例和实验验证了算法的有效性。

英文摘要

In order to resolve the error of computing core and attribute reduction, which was caused by the inconsistency of decision table, a definition of object credibility was introduced and added into the decision table to tell inconsistent objects and consistent objects. Then a definition of discernibility matrix and definitions of core and attribute reduction based on the discernibility matrix were put forward. It was proved that the core and attribute reduction acquired from the definitions are the core and attribute reduction based on positive region. Finally, the general algorithm and its improved algorithm for computing attribute reduction were designed, and both of example and experiment results showed that the algorithms are effective.

关闭

Copyright © 2020四川大学期刊社 版权所有.

地址:成都市一环路南一段24号

邮编:610065