模糊数空间上的积分度量及其在模糊聚类中的应用  

Integral metric on Fuzzy Number space and its application to Fuzzy Clustering

作　　者：包玉娥[1] 雷一鸣[1] 

机构地区：[1]内蒙古民族大学数学学院,内蒙古通辽028043

出　　处：《模糊系统与数学》2017年第4期69-77,共9页Fuzzy Systems and Mathematics

基　　金：国家自然科学基金项目(11461052);内蒙古自然科学基金项目(2014MS0107)

摘　　要：在本文中,首先利用区间数的EW-型度量探讨了模糊数空间上的积分度量问题,给出了模糊数空间上的一种新的积分度量-EW-型积分度量,并证明了其相关性质.其次,作为EW-型积分度量的应用,设计了对属性特征为三角模糊数的事物进行分类的模糊聚类算法.然后通过实例分析,说明了EW-型积分度量使模糊聚类算法实现的更简单易行,分类更加精细,合理有效等。In this paper, the metric problem of integrals in the fuzzy number space is firstly discussed using EW metric of interval numbers. A new integral metric, EW-type integral metric, and proposed with its proved relevant properties. Secondly, as an application, a fuzzy clustering algorithm is designed to classify objects with the feature of triangle fuzzy numbers. The example analysis shows that the proposed algorithm using EW-type integral metric has easier implementation, better precision and efficiency.

关 键 词：模糊数 积分度量 三角模糊数 聚类中心 模糊聚类 

分 类 号：O159[理学—数学] TP301[理学—基础数学]