群决策中基于SVDD的专家权重的评价方法  

An Assessment Method for Judgment Level of Experts Based on SVDD in Group Decision Making

作　　者：刘万里[1] 王金艳[2] 

机构地区：[1]洛阳师范学院数学科学学院,洛阳471022 [2]洛阳师范学院物理与电子信息学院,洛阳471022

出　　处：《武汉理工大学学报（交通科学与工程版）》2009年第4期807-810,共4页Journal of Wuhan University of Technology（Transportation Science & Engineering）

基　　金：国家自然科学基金项目(60674108);河南省教育厅自然科学基金项目(2004601013)资助

摘　　要：针对群决策中专家权重的评价问题,提出一种基于支持向量域描述(SVDD)的确定方法.利用生成树的方法把判断矩阵进行一致性剖分,利用支持向量域描述的方法排除干扰信息,找出群体公共信息,并引入群体相容性、群体信息贡献率等概念及其判断方法;给出不同专家的群体信息贡献率的计算方法,确定出每位专家的评价权重,并通过示例验证了该方法的可行性和有效性.该方法能消除片面的影响,抓住关键信息,对专家的权重能比较客观地评价.An assessment method is proposed based on support vector domain description （SVDD） for weight problem of experts in group decision making. Firstly, a consistency dissection is performed for every judgment matrix by means of the spanning-tree method. Secondly, the disturbance information is removed and the group information is found by using the SVDD, and several concepts, such as tree vector, group compatibility and group information contribution ratio are introduced. The computational method for the contribution ratio of every expert is given so as to determine the assessment weight of every expert, the feasibility and efficiency of the method are shown by an example. The method can eliminate unilateral influence and extract key information, and give a more objective evaluation to weight of each expert.

关 键 词：群决策 生成树 相容性 支持向量域描述 权重 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] C934[自动化与计算机技术—控制科学与工程]