不确定语言评价信息下大群体决策的MC-EMD方法

发布时间：2018-03-16 05:20

本文选题：不确定语言变量　切入点：蒙特卡洛经验模态分解(MC-EMD)　出处：《中国管理科学》2017年04期 　论文类型：期刊论文

【摘要】：针对传统语言群决策方法专家权重难以合理求取且决策属性值为不确定语言变量的问题,提出一种基于蒙特卡洛经验模态分解(Mentor Carlo-Empirical Mode Decomposition,MC-EMD)提取专家语言评价信息的多属性大群体决策方法。考虑专家期望偏差越小为宜,建立偏差最小单目标优化模型求解属性权重;运用EMD方法分解各专家的综合语言评价值,得到客观趋势成分和主观随机成分,以客观趋势成分的均值作为评价结果;鉴于不同专家顺序可能有不同的分解结果,从而导致评价结果的不确定性,基于蒙特卡罗思想随机抽取专家排序,通过计算模拟获取专家评价的总体客观趋势,并借以进行方案优选排序。案例分析验证了该方法的有效性和可行性。
[Abstract]:In view of the problem that the expert weight of traditional language group decision making method is difficult to obtain reasonably and the value of decision attribute is uncertain language variable, A multi-attribute large group decision making method based on Monte Carlo empirical mode decomposition (Mentor Carlo-Empirical Mode DecompositionMC-EMD) is proposed to extract the evaluation information of expert language. Considering the smaller expected deviation of experts, the minimum deviation single objective optimization model is established to solve attribute weights. Using EMD method to decompose the comprehensive linguistic evaluation value of each expert, objective trend component and subjective random component are obtained, and the mean value of objective trend component is taken as the evaluation result. As a result of the uncertainty of evaluation results, experts are randomly selected and sorted based on Monte Carlo theory, and the general objective trend of expert evaluation is obtained by simulation. A case study shows that the method is effective and feasible.
【作者单位】：华北水利水电大学管理与经济学院;华北水利水电大学数学与信息科学学院;
【基金】：国家自然科学基金项目(71271086,71503080) 河南省科技厅重点攻关项目(142102310123) 河南省高等学校重点科研项目资助计划(15A630005) 华北水利水电大学博士研究生创新基金
【分类号】：C934

【相似文献】