基于熵最大化的区间直觉模糊多属性群决策方法  

Approach to interval-valued intuitionistic fuzzy multiple attributes group decision making based on maximum entropy

作　　者：戚筱雯[1] 梁昌勇[1] 张恩桥[1] 丁勇[1] 

机构地区：[1]合肥工业大学管理学院,合肥230009

出　　处：《系统工程理论与实践》2011年第10期1940-1948,共9页Systems Engineering-Theory & Practice

基　　金：国家自然科学基金(70631003;70671037);教育部高等学校优秀青年教师研究基金(09YJC630055)

摘　　要：针对决策信息为区间直觉模糊数且属性权重完全未知的多属性群决策问题,提出了一种基于信息熵的决策方法.为保证决策的完善性,首先从区间直觉模糊数的几何意义出发,提出了一种相对合理的比较方法,同时定义了一种区间直觉模糊矩阵的规范化方法,并详细论证了方法的相关性质.该方法不仅能够保证区间直觉模糊数的形式,而且最大程度的降低了信息损失.接着,提出一种基于区间直觉模糊值熵最大化的权重确定方法,最后,将该方法应用在ERP选优的群决策问题中,用一个实例验证了方法的有效性.This article proposed an approach to multi-attribute group decision making based on information entropy with unknown attribute weight information where individual assessments are provided as interval-valued intuitionistic fuzzy numbers.To ensure the complement of decision,first of all,a reasonable method is developed for comparing two values by introducing the geometric meaning of interval-valued intuitionistic fuzzy numbers.Then,a normalization method of interval-valued intuitionistic fuzzy matrix is defined,and some of its desirable properties are investigated in detail.Through this method,not only maintain the form of interval-valued intuitionistic fuzzy numbers,but also can diminish loss of information at large scale.Next,a method based on maximizing entropy values of interval-valued intuitionistic fuzzy numbers to ensure unknown attribute weights is developed.Finally,apply this method in ERP choosing group decision-making problem,a practical example is provided to verify the effectiveness of the developed approach.

关 键 词：区间直觉模糊矩阵 规范化 熵 群决策 

分 类 号：C934[经济管理—管理学]