基于交叉评价和竞争视野优化的多属性决策方法

借鉴数据包络分析（ＤＥＡ）的交叉评价思想,首先,建立了评价对象以“自身优势最大化”为一致目标时基于交叉评价的多属性决策模型;然后,在重新定义“竞争区间”的概念基础上,用竞争视野优化准则对模型进行修正;最后,通过具体算例表明,该方法公平地体现了评价对象在决策过程中的“发言权”和“能动性”,保证了决策的公正性．     

基于交叉评价和竞争视野优化的多属性决策方法

借鉴数据包络分析（ＤＥＡ）的交叉评价思想,首先,建立了评价对象以“自身优势最大化”为一致目标时基于交叉评价的多属性决策模型;然后,在重新定义“竞争区间”的概念基础上,用竞争视野优化准则对模型进行修正;最后,通过具体算例表明,该方法公平地体现了评价对象在决策过程中的“发言权”和“能动性”,保证了决策的公正性．

     

基于TOPSIS的三支决策评价模型

逼近理想点排序（Technique for order performance by similanrity to ideal solution,TOPSIS）是一种典型的多目标决策评价方法,被广泛应用在供应商选择等问题中。在某些针对生产的评价中,评价对象较多而且对象之间具有层级关系,决策者更关注对象之间的相对类别关系,即：好、中或是差。然而,针对这类问题的评价模型较为缺乏。因此,本文提出一种新的基于TOPSIS的三支决策评价模型。首先,选用层次分析法（Analytic hierarchy process,AHP）计算权重;然后,为了解决对象之间的层级关系,在评价之前增加了一个预分类过程;最后,使用改进的TOPSIS方法对对象进行三支评价。案例分析结果显示本文提出的方法是有效的。     

基于加权α优势关系的多属性决策排序方法*

α优势粗糙集模型利用简单平均法赋权多个阈值α的排序结果,忽视数据集本身信息,导致不同数据集的排序质量差异性较大.针对此问题,文中提出基于加权α优势关系的优势度排序方法.首先运用α优势粗糙集方法详细分析决策对象.在此基础上,为了克服α主观赋权导致多属性决策排序结果中“并列”决策现象存在的不足,依据排序结果采用2种准则赋权α,并融合2种准则下所有对象的综合优势度,进一步细化排序结果.最后在具体算例中对比分析其它排序方法,验证文中方法的可行性和有效性.     

基于扰动优势关系的直觉模糊三支决策方法

针对现有直觉模糊优势关系要求过于严格，以及评价信息损失较大和利用不全的问题，利用直觉模糊集之间的扰动度提出了符合直觉模糊特点的直觉模糊扰动优势关系。进而得到比等价类要求更低的扰动优势类，从而更大程度利用评价信息，紧接着讨论了优势类的相关性质。随后针对现有直觉模糊三支决策方法中的条件概率用实数表示导致不确定信息丢失问题，基于扰动优势关系提出了用直觉模糊数表示的条件概率的计算方法，并且给出了三支决策以及多属性决策规则。通过算例验证了该方法的有效性，并对优势程度和风险规避系数进行了灵敏度分析。     

基于云模型具有语言评价信息的多属性群决策研究

针对多属性群决策中具有语言评价信息偏好的表示与集结的关键问题．研究了基于云模型的决策专家个体偏好表示、偏好集结和方案优选方法．首先采用云模型表示决策者给出的自然语言评价信息，而属性和决策者权重大小则用云的语气运算表示；然后用浮动云进行偏好集结，根据云模型的相对距离进行方案的排序和优选．此方法可充分表达评价语言的模糊性和随机性，具有较大的客观性．     

复杂环境下的平行决策研究

针对复杂环境下决策的不确定性、动态性以及面对大量信息决策不知所措等系列问题,提出了复杂环境下的平行决策研究方法,利用平行决策的分解原理,将复杂决策分解为流决策、平行决策和交叉决策,不仅简化了复杂环境下的决策问题研究,而且从某种程度上能将信息优势适时地转化为决策优势,从而为系统决策获取最终的系统竞争优势提供一定的帮助。     

基于优势关系的多属性决策对象排序研究

多属性决策问题的实质是利用已有的决策信息,通过一定方式对备选方案进行分析、排序、择优和评价,以找到一种简捷方便的排序方法.鉴于此,针对属性值为区间数的多属性决策问题,首先提出区间数向联系数的转化及联系数可能度;然后根据可能度大小提出区间数及决策对象优势关系,并根据优势关系及联系数可能度大小提出几种新的排序算法;最后以实际投票决策问题为例验证了上述排序算法.     

基于Vague集模糊推理的多评价指标模糊决策方法

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，有学者已把Vague集用于多评价指标的模糊决策中，但其决策方法在某些时候却难以得到目标。为此，本文提出了一个基于Vague集模糊推理的多评价指标模糊决策方法。在这个方法中，从基于Vague集的模糊推理的观点来看待模糊决策问题。将评价指标和候选方案之间的关系用一组基于Vague集的推理规则来表示，将决策者的要求用一组Vague集来表示，经过模糊推理等过程最后得到决策结果。然后还给出了一个实例说明这种多评价指标模糊决策方法。这个基于Vague集模糊推理的多评价指标模糊决策方法的提出为决策系统提供了一个有用的工具。     

分布式决策中处理冲突的研究

在基于agent的DSS系统中，由于不同的agent具有不同的评价标准，因而必然存在冲突．本文在形式化评价决策任务的基础上，提出了通过利用评价agent改变当前属性位并把有关结果通知其它协商agent来解决冲突的方案，并给出了消除冲突的具体过程．最后，通过具体实例说明了该方法的可行性。     

多品种离散制造决策模型的研究

分析典型多品种离散制造企业的特点和发展趋势,以OA,MRP,PDM和SCM等信息系统积累的大量原始数据为基础,依照总经理-部门经理-车间主任-班组长4级管理层按角色建立单目标决策模型。采用多属性效用函数和层次分析法,建立按客户订单组织生产的多目标决策模型,应用实例计算出决策目标的效用值及客户的决策评价值,从而选择决策评价值最优的客户。     

Integrating learning and decision-making in intelligent manufacturing systems

This paper presents an overview of learning and decision-making in intelligent manufacturing systems. Machine learning techniques applicable to design and manufacturing are reviewed. Issues related to the role of learning in manufacturing decision-making and two related examples are discussed. The architecture, algorithm and implementation of the first prototype of IMAFO, an intelligent supervisory system, which has learning capabilities, are explained.     

A novel approach for combination of individual and group decisions based on fuzzy best-worst method

The process of decision-making in an enterprise may either keep the business on track or derail it. Thus, a senior decision maker often use a group of experts as the supportive team to ensure appropriate decisions. The experts often have different expertise level regarding their knowledge, talent, proficiency, and experience. In this study, we first extend the best-worst method based on the linguistic preferences of decision-makers about importance of attributes. These preferences are converted into triangular fuzzy numbers to be utilized in the linear programming model. That is, in contrast with the original best-worst method in which the preferences towards the attributes are crisp, fuzzy preferences are considered in the proposed method to reflect the imprecise comments of experts. Second, we propose a novel group decision making approach based on the fuzzy best-worst method to combine the opinion of senior decision-maker and the opinions of the experts. Indeed, our model helps the senior decision-maker to make a significant trade-off between democratic and autocratic decision-making styles. From sensitivity analyses on two numerical examples, we show that, when there is conflict between senior decision-maker and group of decision-makers, the consistency of group decision-making (democracy) will increase as it tends to individual decision-making (autocracy).     

考虑偏好与合作的供应链网络设计与优化

提出了考虑核心企业决策偏好与成员企业合作意愿的双目标供应链网络设计与优化问题。应用模糊多目标规划方法,将决策者对各个目标的不精确期望水平考虑到供应链网络的设计与优化模型中。研究了集中决策模式下核心决策者的不同目标偏好与分散决策模式下各组织成员群体决策的合作意愿,对供应链的各个目标及网络优化配置的影响。结果表明,“极大极小”算子体现了核心决策者对各个目标的偏好,但大权重目标以牺牲小权重目标的值为代价的。新的“模糊与”补偿算子能使供应链的各个目标值获得理想的均衡效果,体现了供应网络中核心企业与其他成员企业群体协商决策的管理思想与行为特征。     

基于Orness 测度约束的多阶段灰色局势群决策模型

研究多阶段灰色局势群决策模型。从决策专家各阶段的评价信息质量分析入手,给出了评价阶段质变和量变的定义;基于各阶段的评价信息和Orness测度,构建以相邻阶段信息偏差最小为目标的时间权重模型,分析了在保持最优局势不变的情况下Orness测度的取值范围,为决策专家Orness取值提供参考;研究基于群体差异最小的决策专家权重模型,提出一种多阶段灰色局势群决策评价信息集结方法。最后,通过一个具体的算例说明了该方法的有效性和可行性。     

Intelligent multi-criteria fuzzy group decision-making for situation assessments

Organizational decisions and situation assessment are often made in groups, and decision and assessment processes involve various uncertain factors. To increase efficiently group decision-making, this study presents a new rational–political model as a systematic means of supporting group decision-making in an uncertain environment. The model takes advantage of both rational and political models and can handle inconsistent assessment, incomplete information and inaccurate opinions in deriving the best solution for the group decision under a sequential framework. The model particularly identifies three uncertain factors involved in a group decision-making process: decision makers’ roles, preferences for alternatives, and judgments for assessment-criteria. Based on this model, an intelligent multi-criteria fuzzy group decision-making method is proposed to deal with the three uncertain factors described by linguistic terms. The proposed method uses general fuzzy numbers and aggregates these factors into a group satisfactory decision that is in a most acceptable degree of the group. Inference rules are particularly introduced into the method for checking the consistence of individual preferences. Finally, a real case-study on a business situation assessment is illustrated by the proposed method.     

分布式计算中可扩展的并行I/O数据分配策略研究

为了提高分布式异构环境中磁盘写文件的效率，并满足系统可扩展性要求，在数据并行I／O分配存储方面提出了可用百分比决策（APD）以及分段选择与可用百分比决策相结合（CSSAPD）二种自适应数据分配策略，实验结果表明了所提出新策略的有效性．     

企业核心竞争力的动态不确定多尺度决策研究

针对传统企业核心竞争力的评价以静态、定性为主的缺陷,从动态不确定的角度,通过引入偏差变量的方法建立不确定性偏好排序的统一模型,提出了综合考虑区间数关联度和方案序的决策者权重方法.构建企业核心竞争力动态不确定多尺度评价模型,并进行了算例实证.结果表明该方法可以对企业核心竞争力进行动态和定量的评价,更具有科学性.     

集对分析在不确定性智能决策中的应用

语言是思维的表达，智能决策是基于确定性与不确定性对立统一思维的一类高级决策。文章综述集对分析在纯自然语言决策，自然语言与数学混合语言决策，区间数决策和直觉模糊决策，集对分析粗糙集决策，联系数与马尔可夫链相结合的决策，赵森烽?克勤概率的贝叶斯决策，偏联系数的决策和同异反综合集成决策等方面的应用。特点是把基于确定性的决策建模与不确定性系统分析相结合，把系统宏观层次的分析与微观层次的分析相结合，把两种或多种决策方法综合集成，根据不确定性的具体情况给出决策建议，因而是一种立足于全局的智能决策，并认为集对分析的不确定性智能决策过程，在本质上是把决策系统中的信息能转换成智能的过程。     

Agent decision-making in open mixed networks

Computer systems increasingly carry out tasks in mixed networks, that is in group settings in which they interact both with other computer systems and with people. Participants in these heterogeneous human-computer groups vary in their capabilities, goals, and strategies; they may cooperate, collaborate, or compete. The presence of people in mixed networks raises challenges for the design and the evaluation of decision-making strategies for computer agents. This paper describes several new decision-making models that represent, learn and adapt to various social attributes that influence people's decision-making and presents a novel approach to evaluating such models. It identifies a range of social attributes in an open-network setting that influence people's decision-making and thus affect the performance of computer-agent strategies, and establishes the importance of learning and adaptation to the success of such strategies. The settings vary in the capabilities, goals, and strategies that people bring into their interactions. The studies deploy a configurable system called Colored Trails (CT) that generates a family of games. CT is an abstract, conceptually simple but highly versatile game in which players negotiate and exchange resources to enable them to achieve their individual or group goals. It provides a realistic analogue to multi-agent task domains, while not requiring extensive domain modeling. It is less abstract than payoff matrices, and people exhibit less strategic and more helpful behavior in CT than in the identical payoff matrix decision-making context. By not requiring extensive domain modeling, CT enables agent researchers to focus their attention on strategy design, and it provides an environment in which the influence of social factors can be better isolated and studied.