基于结构元理论的模糊多属性群决策方法

主要目的是将结构元理论引入到模糊多属性决策中,以简化传统决策的复杂运算.折衷型群决策方法是经典多属性群决策中最常用的方法之一,本文根据该方法的原理提出两种基于结构元理论的模糊多属性群决策的折衷型方法.同时借助实例进行决策运算.最后与传统方法进行比较,本文所提出的这两种算法对于进一步研究模糊多属性群决策问题有较好的参考作用.     

基于模糊判断矩阵的两阶段群决策方法

针对多属性群决策问题,提出一种两阶段决策分析方法。通过分析积型模糊一致性判断矩阵和模糊判断矩阵的排序向量之间的偏差,建立并求解一个规划模型,得到专家模糊判断矩阵的排序向量。由最小化专家模糊判断矩阵的排序向量与专家群组排序向量的偏差,再次建立并求解一个规划模型,得到反映专家群组偏好的排序向量,从而得出基于模糊判断矩阵的两阶段群决策方法。通过2个算例说明了该方法的可行性与有效性。     

Pythagorean Fuzzy Choquet Integral Based MABAC Method for Multiple Attribute Group Decision Making

In this paper, we define the Choquet integral operator for Pythagorean fuzzy aggregation operators, such as Pythagorean fuzzy Choquet integral average (PFCIA) operator and Pythagorean fuzzy Choquet integral geometric (PFCIG) operator. The operators not only consider the importance of the elements or their ordered positions but also can reflect the correlations among the elements or their ordered positions. It is worth pointing out that most of the existing Pythagorean fuzzy aggregation operators are special cases of our operators. Meanwhile, some basic properties are discussed in detail. Later, we propose two approaches to multiple attribute group decision making with attributes involving dependent and independent by the PFCIA operator and multi‐attributive border approximation area comparison (MABAC) in Pythagorean fuzzy environment. Finally, two illustrative examples have also been taken in the present study to verify the developed approaches and to demonstrate their practicality and effectiveness.     

基于IITFN输入的复杂系统关联MAGDM方法

区间直觉梯形模糊数（Interval-valued intuitionistic trapezoidal fuzzy number,IITFN）是刻画复杂系统不确定性的有效工具. 基于进一步完善的IITFN 运算规则,讨论其局部封闭性. 由此定义IITFN 几何Bonferroni 平均算子,并验证该算子的相关性质. 针对决策者及属性之间均存在关联作用且权重均未知的多属性群决策（Multi-attribute group decision making,MAGDM）问题,提出基于前景混合区间直觉梯形几何 Bonferroni （Prospect hybrid interval-valued intuitionistic trapezoidal fuzzy geometric Bonferroni,PHIITFGB）平均算子 的关联多属性群决策方法. 该方法首先通过依次定义IITFN 的前景效应、前景价值函数和前景价值,获取前景价值矩阵;其次,将前景价值矩阵转化为前景记分函数矩阵,并综合运用基于灰关联深度系数的客观属性权重极大 熵模型和基于2-可加模糊测度与Choquet 积分联合的决策者权重确定模型,获取决策者权重及属性权重;再次,利 用PHIITFGB 算子集结各决策者的方案评估信息,结合决策者权重即可获取相应于各方案的综合前景价值;最后,计算综合前景记分价值函数,基于IITFN 的序关系判别准则确定方案排序. 案例验证决策方法的有效性和可行性.     

动态模糊形式化关系群体决策方法

群体决策问题是决策科学的核心问题之一。基于动态模糊理论,从动态角度研究群体决策问题,提出了一种动态模糊形式化关系决策方法。从个体偏好信息表达、个体偏好数据分析、个体偏好集结、方案选择和意见反馈五个阶段探讨了动态模糊群体决策模型,并通过实例验证了该模型的可行性和合理性。     

基于犹豫模糊集的网络舆情突发事件应急群决策方法

考虑决策者在时间紧急及信息不完备的情况下给出评估值时可能会出现犹豫不决的情况,提出基于犹豫模糊集的网络舆情突发事件应急群决策法.首先,通过犹豫模糊信息熵及交叉熵建立各评价指标的权重确定模型;其次,利用犹豫模糊加权平均算子及得分函数计算各突发事件评价指标的犹豫模糊评估值得分;然后结合各评价指标的权重值及评估值得分,计算出各网络舆情突发事件综合危害性得分,进而辅助应急部门确定各网络舆情突发事件的处置顺序;最后通过案例分析证明了方法的有效性.     

概率对偶犹豫模糊PROMETHEE多属性群决策算法

为解决犹豫模糊环境中由随机性和不确定性对实际决策造成偏差的多属性群决策问题,提出一种基于概率对偶犹豫模糊PROMETHEE的多属性群决策算法。构建各决策专家的概率对偶犹豫模糊信息矩阵;运用最大离差法与熵值法确定各决策专家与各指标属性的客观权重,结合改进的得分函数与偏离函数得到专家的综合决策评价信息矩阵;进而通过概率对偶犹豫模糊集与PROMETHEE结合的决策算法得到最终决策结果。将该算法运用于航空灾难事故应急响应方案评估的算例分析中,通过与TOPSIS、VIKOR及PDHFS决策算法的计算结果进行对比,验证了概率对偶犹豫模糊PROMETHEE多属性群决策算法的有效性与可靠性。     

动态直觉模糊多属性决策的VIKOR扩展方法

隐变量是观察不到或虚拟的变量,直接利用数据驱动的学习方法难以有效地发现隐变量,因而需要结合概率图结构分析的方法。针对基于结构分析的隐变量发现方法中难以确定隐变量个数和位置的问题,提出一种基于结构分解和因子分析的隐变量发现算法(S-FAHF)。S-FAHF算法利用联合树算法生成具较强依赖关系的变量子集,利用因子分析思想,通过求变量子集的特征值和累积贡献率确定变量子集中隐变量的个数,利用负荷矩阵确定隐变量的位置,最后利用打分函数测试所发现的隐变量的有效性。通过算法比较和实验结果表明,该方法能准确地确定贝叶斯网络中隐变量的个数及位置。     

三角直觉模糊决策的权重函数方法

研究了属性值为三角直觉模糊数的多属性决策问题,提出了一种基于权重函数的决策方法。给出了三角直觉模糊数的定义、运算法则和截集;定义了三角直觉模糊数关于隶属函数和非隶属函数的精确值和模糊度,以及精确值的指标和模糊度的指标,给出了三角直觉模糊数的排序方法,并将其应用到属性值为三角直觉模糊数的多属性决策问题中;给出了属性值为三角直觉模糊数的多属性决策的步骤;通过数值算例分析和验证了该方法的有效性。     

Fuzzy Algorithm for Group Decision Making With Participants Having Finite Discriminating Abilities

A fuzzy inference-based algorithm with rules using the Nash solution is proposed for group decision making considering the finite discriminating abilities of real decision makers (DMs). It provides a solution that can capture and incorporate the imprecision of real people at declaring their preferences, and hence, it reflects more faithfully the DMs' opinions. The algorithm is applied to a purchase project of a storage area network with two DMs and three options. It shows how the algorithm can provide a unique solution whereas customary crisp methods are either unable to do it or reveal a risk of choosing, in 16.5% of the cases, an option that does not match with the preferences declared by the group of DMs as a whole. The algorithm aims for processes where the options are difficult to evaluate, circumstance that makes clear that human beings cannot provide unreal crisp values, and that the solution changes if preference information is only partially taken.      

基于Vague集的模糊决策方法

目前在智能领域中对Vague集的研究已越来越广泛与深入．并运用于决策问题中．为了更加有效地进行模糊决策，提出了一个基于Vague集的模糊决策方法．在这个方法中，对约束条件，从它出现的可能性和不出现的可能性以及未知是否出现的可能性三个方面去综合处理．使得决策更加准确和有效．还给出了一个实例说明这种基于Vague集的模糊决策方法．这个基于Vague集的模糊决策方法的提出，为决策系统提供了一个有用的工具．     

A Maximum Consensus Improvement Method for Group Decision Making Under Social Network with Probabilistic Linguistic Information

Neural Processing Letters - Group decision-making (GDM) requires consensus building, because an outcome from a consensual decision is indispensable to implement a highly acceptable solution. This...     

A Consensus Model for Group Decision Making With Incomplete Fuzzy Preference Relations

Two processes are necessary to solve group decision making problems: A consensus process and a selection process. The consensus reaching process is necessary to obtain a final solution with a certain level of agreement between the experts; and the selection process is necessary to obtain such a final solution. In a previous paper, we present a selection process to deal with group decision making problems with incomplete fuzzy preference relations, which uses consistency measures to estimate the incomplete fuzzy preference relations. In this paper we present a consensus model. The main novelty of this consensus model is that of being guided by both consensus and consistency measures. Also, the consensus reaching process is guided automatically, without moderator, through both consensus and consistency criteria. To do that, a feedback mechanism is developed to generate advice on how experts should change or complete their preferences in order to reach a solution with high consensus and consistency degrees. In each consensus round, experts are given information on how to change their preferences, and to estimate missing values if their corresponding preference relation is incomplete. Additionally, a consensus and consistency based induced ordered weighted averaging operator to aggregate the experts' preferences is introduced, which can be used in consensus models as well as in selection processes. The main improvement of this consensus model is that it supports the management of incomplete information and it allows to achieve consistent solutions with a great level of agreement.     

基于改进直觉模糊熵和信息集成算子的多准则群决策方法

针对直觉模糊环境下准则权重和决策者权重完全未知的群决策问题,提出了一种基于改进直觉模糊熵和信息集成算子的多准则群决策方法.首先,借助直觉模糊数、语言变量法和定量指标值转化公式,将决策者的初始评价准则值规范化;其次,引入改进的直觉模糊熵度量方法确定准则权重和决策者权重;进一步对直觉模糊决策矩阵用直觉模糊加权平均算子和直觉模糊有序加权平均算子进行信息集成,利用新的得分函数对备选方案排序择优.从理论上论证了该方法的可行性,结合算例验证了该方法的有效性.     

Error Analysis Methods for Group Decision Making Based on Hesitant Fuzzy Preference Relation

Hesitant fuzzy preference relation (HFPR) is an effective way to depict the decision makers’ preferences over the objects (alternatives or attributes) in the process of group decision making. Each component of the HFPR is characterized by several possible values and can express the decision makers’ hesitant information comprehensively. To make a decision with the HFPR, it is very necessary to find a proper technique for deriving the priority weights from the HFPR. In this paper, we use the error analysis as a tool to develop several straightforward methods for the priorities of the HFPR. We first define the expected value and the average value of each hesitant fuzzy element in the HFPR. Then based on the error analysis, we come up with the interval midpoint method, the average value method, and the difference method to derive the priority weights from the HFPR. After that, we discuss the relations among these methods, and utilize them and the possibility degree formula to develop an approach to decision making with the HFPR. Finally, we demonstrate the effectiveness and practicality of our approach through a case study concerning the investment problem in liquor enterprise.     

基于Vague集的多准则模糊决策方法

基于Vague集的模糊决策方法的提出，为决策系统提供了一个有用的工具．对模糊条件下的多准则决策问题，指出了采用Vague集进行多准则模糊决策的现有计分函数的不足，根据Vague集的性质提出了二种新的方案选择方法：记分函数法和加权记分函数法。对已有的Vgue集记分函数法进行了分析与联系，并通过例子阐明本文方法的有效性和优越性．     

直觉对偶犹豫模糊集在多属性群决策中的应用

基于直觉对偶犹豫模糊集的定义,结合标准距离测度公式,给出了直觉对偶犹豫模糊集的Hamming距离测度公式、Euclidean距离测度公式等。给出了用以度量两个对偶模糊信息之间相关关系的相关系数、加权相关系数的公式及其相关性质。给出了用以度量直觉对偶犹豫模糊集模糊性的熵的定义,并给出了熵的计算公式。基于直觉对偶犹豫模糊集的距离测度、相关系数、熵给出了一种新的直觉对偶犹豫模糊集的多属性群决策方法,并通过实例说明了该方法的有效性。     

区间犹豫模糊M-对称平均及其群决策模型

区间犹豫模糊集是特殊的犹豫模糊集,可以更准确地刻画决策信息。而Maclaurin对称平均算子能够考虑多个输入参数值间的相互关系。基于Maclaurin对称平均算子,在区间犹豫模糊环境下,提出了一种区间犹豫模糊Maclaurin对称平均信息集成算法。定义了区间犹豫模糊Maclaurin对称平均(IVHFMSM)算子;讨论了IVHFMSM算子的四个优良性质以及几种特殊表达形式;基于提出的区间犹豫模糊加权Maclaurin对称平均(IVHFWMSM)算子,构建了区间犹豫模糊Maclaurin对称平均多属性群决策算法;通过实例发现,IVHFWMSM算子性质优良,具有多选择性且更加合理可行。     

基于信息熵的模糊多属性决策供应商选择方法

提出了一种针对供应商选择最优决策问题的基于信息熵的模糊多属性决策方法。针对供应商的多属性决策问题,确定属性集,利用信息熵求出各属性权重,运用模糊数排序方法对方案的模糊效用值进行排序,以确定最优方案。最后以某企业为例做了实例分析,将此方法应用于对这五个供应商进行评分排序,并从中选择出最为合适的供应商,表明此方法行之有效。