基于判断矩阵的专家模糊核聚类组合赋权方法  

Method for combination weighting experts based on judgment matrix and fuzzy kernel clustering analysis

作　　者：李闯[1] 端木京顺[1] 蔡忠义[1] 高建国[1] 

机构地区：[1]空军工程大学 工程学院,西安710038

出　　处：《控制与决策》2012年第9期1411-1414,1420,共5页Control and Decision

基　　金：国家自然科学基金项目(60773209)

摘　　要：研究群决策中专家赋权问题,实际决策问题中,由于客体信息自身存在的不完备性和不确定性以及人们描述过程中的模糊性,更适合采用模糊聚类的分析方法,为此提出一种基于判断矩阵的专家模糊核聚类赋权方法,该方法运用模糊核聚类理论对专家排序向量进行分类,根据分类结果、判断矩阵一致性和排序向量的熵对各专家进行组合赋权,算例表明,所提出的方法是可行且有效的。The problem of weighting experts in group decision-making is studied. In the decision-making problems, because the information of object itself is incomplete and uncertainty, and people describe fuzzily in the process of decision-making, the fuzzy clustering analysis is more suitable for such problems. Therefore, a method for deriving experts＇ combination weights based on judgment matrix and fuzzy kernel cluster analysis is provided, in which the collating vectors of an individual expert are classified by using fuzzy kernel clustering principle. The experts＇ combination weights are determined according to the result of classification, the judgment matrix＇s consistency and the entropy of collating vectors. Finally, a numerical example shows the feasibility and effectiveness of the proposed method.

关 键 词：专家赋权 判断矩阵 模糊核聚类分析 

分 类 号：C943[自然科学总论—系统科学]