一种利用属性序关系的变精度粗糙集知识约简方法  

Approaches to Knowledge Reduction of Variable Precision Rough Set Model by Ordered Attributes

作　　者：张玉琢[1] 

机构地区：[1]云南师范大学计算机科学与技术系,云南昆明650092

出　　处：《江西师范大学学报（自然科学版）》2008年第4期449-452,共4页Journal of Jiangxi Normal University(Natural Science Edition)

基　　金：云南省教育厅科学研究基金(5y0615D)资助项目

摘　　要：变粗糙集模型主要用于包含错误信息或缺失一些重要信息的决策表的知识获取.该文引入了变粗糙集模型和β上、下分布约简和分布约简(μ约简)的概念,并讨论了它们之间的关系;通过对约简的进一步研究,得到可辩识矩阵及其特性;在此基础上提供了利用属性序关系的约简算法,并通过含有噪声的实例验证了此方法的可行性和有效性.When the given decision table includes errors or lacks some important information,variable precision rough set(VPRS) model has been proposed as an extension of the classical RS model.This paper introduces variable precision rough set(VPRS) model.lower distribute reduct,upper distribute reduct and distribute reduct(It is called reduct) and relationship among them are discussed.Discernibility matrixes with respect to upper and lower reductions are obtained.Algorithm of ordered attributes is designed to reduct knowledge of decision tables.Finnally,an example shows that this new algorithm is both feasible and effective in practice.

关 键 词：变粗糙集模型 知识约简 决策表 协调集 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]