多属性决策中属性权重的无偏好赋权方法  

Weight Integration Method without Preference on Multi-attribute Decision Making

作　　者：郭红玲[1] 黄定轩[2] 

机构地区：[1]西南交通大学公共管理学院,四川成都610031 [2]同济大学经济管理学院,上海200092

出　　处：《西南交通大学学报》2007年第4期505-510,共6页Journal of Southwest Jiaotong University

基　　金：国家自然科学基金资助项目(70272022);四川省哲学社会科学"十一五"规划项目(SC06B020)

摘　　要：针对具有条件属性和决策属性的多属性决策系统在融合主观权重与客观权重时具有人为偏好的缺陷,为实现客观权重与主观权重的无偏好融合,用粗集理论中的属性重要性原理确定各属性的客观权重,再用MATLAB中细胞数组的基本特征和多维空间距离的概念,建立了基于空间距离的二次规划数学模型,确定无人为偏好的主客观权重融合方案.用对流感病人诊断过程的知识决策表说明了本方法的可行性.To overcome the shortcomings resulted from the preferred integration between subjective and objective weights in multi-attribute decision-making with condition and decision attributes, a quadratic programming model was proposed to get optimal weight integration without preference between the subjective and the objective weights. In the model, the objective weights are determined according to the attribute importance in rough sets theory, and the concepts of basic characteristic of the cell array in MATLAB and the distance in a multi-dimensional space are utilized. An example of diagnoses of flue patients was presented to show the feasibility of the proposed method.

关 键 词：多属性决策 属性权重 二次规划 融合 主观权重 客观权重 

分 类 号：F270.7[经济管理—企业管理] F830.59[经济管理—国民经济]