基于证据理论的覆盖类决策多粒度粗糙集的下近似约简  

Reduction Methods of Covering Decision Multigranulation Rough Set Based on Evidence Theory

作　　者：游小英 李进金 YOU Xiao-ying;LI Jin-jin(School of Mathematics and Statistics,Minnan Normal University,Zhangzhou 363000,China)

机构地区：[1]闽南师范大学数学与统计学院,福建漳州363000

出　　处：《模糊系统与数学》2020年第5期133-138,共6页Fuzzy Systems and Mathematics

基　　金：国家自然科学基金资助项目(11871259,61379021,11701258,61602415)。

摘　　要：知识约简向来是知识发现的重要研究问题之一。该论文研究了基于证据理论的覆盖类决策的多粒度粗糙集的约简方法。首先构造了覆盖类决策多粒度粗糙集的信任结构,然后利用该信任结构中的信任函数和似然函数刻画了覆盖类决策多粒度粗糙集的约简特征,再者引入了基于信任函数的覆盖重要度的概念,并给出了求解覆盖约简的近似算法。最后用实例说明该算法的合理性和有效性。Knowledge Reduction is one of the most important issues of knowledge discovery.This paper investigates the reduction methods of covering decision multigranulation rough set based on evidence theory.First,the belief structure of covering decision multigranulation rough set is constructed,and then the reduction properties of covering decision multigranulation rough set are characterized by using the belief and plausibility functions from evidence theory.Third,the significance of coverings based on the belief function is introduced and the approximate reduction algorithm of coverings is proposed.In the end,a practical example is given to illustrate the rationality and validity of the algorithm.

关 键 词：多粒度 覆盖 粗糙集 约简 证据理论 

分 类 号：O159[理学—数学]