多属性决策中赋权方法的自适应选择研究  

Research on adaptive selection based on weighted method in multiple attribute decision

作　　者：白晓波[1] 陈金广[2] 邵景峰[1] 雷霞[1] 刘聪颖[1] 

机构地区：[1]西安工程大学管理学院,西安710048 [2]西安工程大学计算机学院,西安710048

出　　处：《计算机工程与应用》2016年第11期215-220,共6页Computer Engineering and Applications

基　　金：国家自然科学基金(No.61201118);陕西省教育厅课题(No.2013KRM07);陕西省科技厅课题(No.2013KJ0742)

摘　　要：为解决多属性决策中众多赋权方法难以选择的问题,对主客观权值向量冲突因子与评估结果精度的相关性进行了分析,进而提出了一种基于冲突阈值的自适应选择算法。通过实验仿真,结果表明:该算法消除了主、客观权值向量冲突对评估结果的影响,提高了计算精度,实现了基于冲突阈值的自适应选择。而且,当冲突因子小于阈值时,自适应选择算法将选择算法时间复杂度低于乘法合成原理的综合赋权法。当冲突因子大于阈值时,选择计算结果准确度高的基于博弈论的综合赋权法。To solve the problem of the difficulty selecting many weighting methods in multiple attribute decision, the correlation between subjective and objective weighted vector conflict factor and the assessment result accuracy is analyzed,and then, an adaptive selection algorithm based on conflict threshold is proposed. As verified by the simulation, the results show that the algorithm eliminates the effect on subjective and objective weighted vector conflict to the evaluation result,improves the calculation accuracy, and realizes the adaptive selection based on conflict threshold. Moreover, when the conflict factor is less than the threshold, adaptive selection algorithm will choose time complexity been lower than integrated weighting method of the multiplicative synthesis principle. On the contrary, when the conflict factor is greater than the threshold, it will choose the combination weighted method of high calculation result accuracy based on game theory.

关 键 词：冲突因子 权值向量 自适应 阈值 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]