基于共识性测度的概率语言多准则群决策方法研究

针对准则值为概率语言术语集的决策问题,提出一种基于共识性测度的概率语言多准则群决策方法.首先,方法定义概率语言共识性测度公式,据此判断个体决策信息是否满足共识性检验.其次,建立考虑决策者协作意愿的群体共识反馈调整模型及权重惩罚体系.此外,利用网络层次分析法(ANP)和共识性测度公式构建指标定权模型,模型可有效解决指标间互相影响导致的权重计算失准问题.随后,提出改进的TODIM决策方法,结合准则权系数及通过共识性检验的群决策矩阵,对方案进行择优排序.最后,通过算例分析验证了该方法的有效性.     

改进的多属性群决策共识方法及其在图书供应商选择中的应用

针对多属性群决策问题,提出了一种改进的加型集结共识方法.在每轮决策中,共识一致性指标较小的决策个体都修改其偏差较大的偏好,能快速使参与决策的个体对各属性形成满意的一致性意见.数值实验也表明该共识方法是合理有效的.     

群体综合评价中兼顾权威与共识的专家权重方法研究

针对多指标综合评价中专家权重确定问题,提出一种新的专家赋权思路.首先,对评价对象的每个指标都设定一组相应的专家主观权重值,以反映专家在不同指标中的重要性程度.其次,依据专家所作出的评价信息,首次提出基于专家个体与群体意见的偏差达到最小(即共识最大)的准则,通过构建最优规划模型求解客观权重.最后将专家主观权重与客观权重有效集结,得到兼顾个体权威与群体共识的综合权重.实例分析说明了该方法的可行性和有效性.     

基于直觉模糊共识模型的多属性群决策方法

决策个体之间的共识达成是提升群决策可信性的重要保证. 为处理极端值导致的决策失效问题,首先将信息进行预处理,然后应用定义的个体与群体之间的共识测度, 构建可以定位与修正非共识决策信息的直觉模糊共识模型, 并建立一种多属性群决策方法,以确保个体信息集结之前达成阈值条件下的共识.通过对投资对象选择的实例研究, 证明了该方法的有效性并选出最优方案.     

考虑非合作行为的社会网络大群体共识决策模型

在社会网络环境下的大群体决策问题当中,决策专家之间的社会网络关系对决策过程和结果的影响至关重要.文章创新地提出一种考虑决策专家社会网络关系和非合作行为的大群体共识决策模型,有效促进大群体共识的达成.首先,根据决策专家的偏好信息和社会网络关系,改进经典Louvain社区发现算法,对大决策群体进行社区划分.其次,运用社会网络分析方法确定决策专家个体和社区的权重.随后,根据决策专家的偏离程度对决策专家非合作行为进行识别,并考虑社会网络关系的影响对非合作行为进行管理,以此构建共识决策模型.最后,通过案例分析来验证所建立共识决策模型的可行性和有效性.文章构建的共识决策模型,不仅在大群体社区划分过程中,创新性地同时考虑决策专家的偏好信息和社会网络关系的影响,并且在非合作行为管理过程中,也考虑到了社会网络关系对非合作行为决策专家偏好调整的影响,使其更适应社会网络决策环境.     

基于Steiner点的非确定语言信息群决策方法研究

本文针对不确定语言信息的群决策问题,提出了一种解决多粒度不确定二元语义语言信息集结与决策的新方法。首先,根据各专家不确定语言短语决策信息,通过相关转化规则,量化为与其对应的二元语义区间数,并将其端点映射到二维坐标系中。其次,运用植物模拟生长算法(PGSA)求出各区间数端点坐标的加权Steiner点(专家群体最优结集点,即群体共识点)。其后,再由最优集结点,给出专家最优集结判断矩阵。从而,可以对决策方案的进行排序,以便给出最优群体决策方案。为了验证此方法的合理性和有效性,本文选择了两个其他学者的研究算例,对其进行了平行的算例研究。最终得到了与其相同的研究结果。     

基于属性关联的不完全风险偏好信息大群体应急决策方法

针对特大突发事件应急决策中大群体专家存在偏好信息不完全的问题,本文提出一种新的不完全风险性信息大群体应急决策方法。首先,利用最优离散拟合方法对决策者的风险偏好因子进行测度并据此对专家聚类;其次,根据不完全偏好矩阵进行属性关联测度,提出了基于风险偏好和属性关联的新的补值模型,得到完全偏好信息矩阵;然后,运用主成分分析方法提取属性主成分,并结合属性权重进行信息集结和方案择优;最后,通过台风“天鸽”事件验证所提方法的可行性和有效性。     

基于云计算的双极二元语义决策模型及其应用

针对评价为语言型且准则权重未知情况下风险型决策信息有效集结的问题,提出一种基于云计算与前景理论的双极二元语义决策模型.首先,将语言型决策信息转换成双极二元语义形式并使用G1—离差最大化法计算各准则的组合权重;其次,利用双极二元语义加权平均算子将各状态、各方案多准则下的决策信息集结为综合双极二元语义决策阵;然后,利用云模型的数字特征公式将综合双极二元语义决策矩阵转化为各状态下各方案的综合云决策矩阵,并结合前景理论分析以确定所有方案的综合云前景值,将其排序并择优.最后,对案例的研究验证了新算法的科学性与适用性.     

基于二元语义TAC积分算子的语言型多属性群决策方法

针对属性之间存在模糊关联的语言型多属性群决策问题,给出了二元语义TAC(Two-Additive Choquet)积分算子的定义,分析和证明了算子的有关性质,并提出了相应的决策方法。该方法首先将各专家提供的语言短语形式的属性权重信息、属性关联信息与属性评价信息转化为二元语义形式,然后利用二元语义TAC积分算子将转化后的属性相关信息集结为各专家的方案评价值,并进一步集结专家意见获得方案的综合评价值,从而确定其排序。最后,通过实例分析和方法比较说明了所给方法的有效性和优点。研究结果表明,该方法具有属性关联刻画细致、计算过程简单且无信息损失、决策结果可解释性强等优点,为求解属性之间存在模糊关联的语言型多属性群决策问题提供了一种新的途径。     

三角模糊偏好下冲突型多属性群决策方法研究

针对三角模糊偏好下冲突型群决策问题,本文提出一种新的决策方法。在冲突消解阶段,用三角模糊数表示决策专家偏好,定义两三角模糊数型偏好矢量间的相似度,通过计算专家对各个方案的偏好矢量与各方案的群偏好矢量间的相似度,以此为基础定义专家的冲突测度。给出阈值和协商机制调控专家的冲突测度,直到所有的专家的冲突测度都小于给定阈值,进入决策阶段。在决策阶段,利用三角模糊数的期望函数确定属性权重,计算各个方案群偏好矢量与理想方案偏好矢量之间的加权相似度,由加权相似度大小排列决策,选出最优方案。最后给出案例应用,利用Matlab画出各方案的冲突测度图,数值结果表明本文方法的可行性及有效性。     

A Direct Approach to Group Decision Making with Uncertain Additive Linguistic Preference Relations

In this paper, we study the group decision-making problem in which the preference information given by experts takes the form of uncertain additive linguistic preference relations. We define the concept of uncertain additive linguistic preference relation, and introduce a formula based on possibility measure for comparing two uncertain linguistic preference values. We introduce some aggregation operators such as the uncertain linguistic averaging (ULA) operator and uncertain linguistic weighted averaging (ULWA) operator, etc. Based on the ULA and ULWA operators, we develop a direct approach to group decision making with uncertain additive linguistic preference relations without loss of information. Finally, an illustrative numerical example is given to verify the developed approach.     

Linguistic group decision-making: opinion aggregation and measures of consensus

Group decision-making is a crucial activity, necessary in many aspects of our civilization. In many cases, due to inherent complexity, experts cannot express their opinion or preferences using exact numbers, thus resorting to a qualitative preference such as linguistic labels. Another complicating factor is the fact that very seldom all individuals in a group share the same opinion about the alternatives. This creates the need to aggregate all the differing individual opinions into a group opinion. Moreover, it is desirable to be able to assess the level of agreement among the experts; termed consensus. This paper presents a methodology for aggregating experts’ judgements, presented as linguistic labels, into a group opinion with a measure of the group consensus. The aggregation model allows weighted experts to express a degree of optimism or upward bias in their opinions. Then the paper presents two models of calculating the consensus based on the individual expert opinions and the group aggregated opinion.     

A consistency and consensus-based method to group decision making with interval linguistic preference relations

Preference relations are a powerful tool to address decision-making problems. In some situations, because of the complexity of decision-making problems and the inherent uncertainty, the decision makers cannot express their preferences by using numerical values. Interval linguistic preference relations, which are more reliable and informative for the decision-makers’ preferences, are a good choice to cope with this issue. Just as with the other types of preference relations, the consistency and consensus analysis is very importance to ensure the reasonable ranking order by using interval linguistic preference relations. Considering this situation, this paper introduces a consistency concept for interval linguistic preference relations. To measure the consistency of interval linguistic preference relations, a consistency measure is defined. Then, a consistency-based programming model is built, by which the consistent linguistic preference relations with respect to each object can be obtained. To cope with the inconsistency case, two models for deriving the adjusted consistent linguistic preference relations are constructed. Then, a consistency-based programming model to estimate the missing values is built. After that, we present a group consensus index and present some of its desirable properties. Furthermore, a group consensus-based model to determine the weights of the decision makers with respect to each object is established. Finally, an approach to group decision making with interval linguistic preference relations is developed, which is based on the consistency and consensus analysis. Meanwhile, the associated numerical examples are offered to illustrate the application of the procedure.     

基于不同粒度语言判断矩阵的群体一致性分析方法

针对群决策中基于不同粒度语言判断矩阵形式偏好信息的群体一致性问题,提出了一种分析方法。首先,给出有关不同粒度语言判断矩阵和二元语义等若干定义,通过转换函数将不同粒度语言判断矩阵一致化为由二元语义表示的判断矩阵;然后,通过定义专家与群偏好的偏差矩阵以及各专家的总体偏差指标,给出了专家群体一致性的判别方法及专家群体判断不一致的调整方法;最后,通过一个算例说明了该方法的有效性。     

An approach to group decision making based on interval multiplicative and fuzzy preference relations by using projection

This paper presents a consensus model for group decision making with interval multiplicative and fuzzy preference relations based on two consensus criteria: (1) a consensus measure which indicates the agreement between experts’ preference relations and (2) a measure of proximity to find out how far the individual opinions are from the group opinion. These measures are calculated by using the relative projections of individual preference relations on the collective one, which are obtained by extending the relative projection of vectors. First, the weights of experts are determined by the relative projections of individual preference relations on the initial collective one. Then using the weights of experts, all individual preference relations are aggregated into a collective one. The consensus and proximity measures are calculated by using the relative projections of experts’ preference relations respectively. The consensus measure is used to guide the consensus process until the collective solution is achieved. The proximity measure is used to guide the discussion phase of consensus reaching process. In such a way, an iterative algorithm is designed to guide the experts in the consensus reaching process. Finally the expected value preference relations are defined to transform the interval collective preference relation to a crisp one and the weights of alternatives are obtained from the expected value preference relations. Two numerical examples are given to illustrate the models and approaches.     

Consensus reaching via a GDSS with fuzzy majority and clustering of preference profiles

An interactive DSS for consensus reaching is presented. Experts provide their testimonies as fuzzy preference relations. The consensus reaching process is supervised by a moderator (super-expert). A degree of consensus, based on the concept of a fuzzy majority given as a linguistic quantifier is employed. Algorithms of cluster analysis are used to find groups of experts having similar preferences.     

Projection method for multiple criteria group decision making with incomplete weight information in linguistic setting

Multiple criteria group decision making (MCGDM) problems have become a very active research field over the last decade. Many practical problems are often characterized by MCGDM. The aim of this paper is to develop a new approach for MCGDM problems with incomplete weight information in linguistic setting based on the projection method. Firstly, to reflect the reality accurately, a method to determine the weights of decision makers in linguistic setting is proposed by calculating the degree of similarity between 2-tuple linguistic decision matrix given by each decision maker and the average 2-tuple linguistic decision matrix. By using the weights of decision makers, all individual 2-tuple linguistic decision matrices are aggregated into a collective one. Then, to determine the weight vector of criteria, we establish a non-linear optimization model based on the basic ideal of the projection method, i.e., the optimal alternative should have the largest projection on the 2-tuple linguistic positive ideal solution (TLPIS). Calculate the 2-tuple linguistic projection of each alternative on the TLPIS and rank all the alternatives according to the 2-tuple linguistic projection value. Finally, an illustrative example is given to demonstrate the calculation process of the proposed method, and the validity is verified by comparing the evaluation results of the proposed method with that of the technique for order preference by similarity to ideal solution (TOPSIS) method.     

群决策中基于判断相似度的专家聚类及群体意见集结方法

针对大规模群决策问题,提出了一种基于专家意见相似度的群体判断信息逐步集结规划的方法。首先利用备选方案序关系向量的灰色关联度和夹角余弦构造两两专家判断信息的组合相似度;其次以判断相似度为标准,采用一种广度邻居搜索算法对专家进行聚类;然后以判断偏差最小为目标,构造非线性的约束规划模型对每一类专家意见进行集结,从而获得类内专家的集结信息;最后从专家数量最多的类别开始,依次对每类专家集结后的判断信息进行再次集结,从而获得最终的评判结果。该方法将大规模的复杂群决 策转化为低复杂度的多阶段专家信息集结问题,并保证了群体结果的一致性。算例分析验证了方法的可行性和有效性。     

多属性群决策算法及一致性分析研究

在多属性群决策中 ,集结群体意见之前必须先对群体的决策数据进行一致性分析 ,以确保群体作出的决策符合客观实际 .提出了群决策的三种三维层次模型 ;用欧几里得距离 ( Euclidean Distance)表示个人决策中方案的评价值 ;然后设置一致性指标值α,作为群体数据一致性的判断依据 ;提出了满足一致性基础上的一种群决策方法 ;最后用实例说明了算法的使用步骤 .