基于贝叶斯网的课程内容设置决策系统的构建方法

提出了一种基于贝叶斯网的课程内容设置决策系统的构建方法,解决职业教育在课程内容安排上的实时性决策问题。首先依据校企联合课程内容需求构成给定的、具有特征属性的条件概率,然后根据对市场所需专业知识的观察与统计等方法来寻求最有可能的贝叶斯网络模型,最后利用信息独立理论,通过贝叶斯学习得到新的贝叶斯网络。     

基于贝叶斯网学生模型的教学决策方法

智能教学系统(Intelligent Tutoring System缩写ITS)的一个很重要的问题是当学生在学习中遇到困难需要帮助时，系统怎样决策，怎样给予学生恰当的反馈和帮助。本文论述一个模仿教师辅导单个学生解答练习题的智能教学系统的决策方法。该方法以贝叶斯网为学生模型，根据学生模型上提供的启发信息，对解图空间进行搜索，以获取最佳教学决策。     

作战辅助决策多智能体系统体系结构

针对现代战争中作战节奏越来越快、决策问题越来越复杂、越来越多的问题无法抽象成数学模型等特点,设计一种分层的基于多智能体的作战指挥辅助决策系统。系统分为决策层、决策辅助层和数据平台层,以通用信息处理平台为支撑,提供情报分析处理、方案评估、计划推演等功能,直接面向用户进行决策交互;并采用协同机制、驱动和知识学习机制等多智能体技术,确保系统反应快速灵活,决策实时正确,实现人机智能结合。     

舰艇智能兵力决策CBPN模型与实现研究

智能兵力作战决策支持是计算机生成兵力构建的重难点和核心内容,传统海战智能兵力作战决策系统难以满足决策知识空间增加对系统决策正确性和灵活性的要求,研究将Petri网建模方法与CXBR上下文推理方法相结合,提出了智能兵力CBPN图形化决策建模方法,依据舰艇智能兵力作战决策过程,分层构造了舰艇智能兵力作战行为模型,并建立了舰艇智能兵力决策支持的CBPN模型,实现了业务层和软件代码层解耦,最后构建了舰艇智能兵力的作战决策知识库.工程实现结果证明新方法能显著提高系统开发效率和智能兵力决策的灵活性,满足复杂作战仿真系统智能兵力作战决策支持需求.     

模糊Petri网在非结构化决策支持中的应用研究

提出了一种建立非结构化决策支持的模糊Petri网模型（简称XFPN).CXFPN结合了模糊集合理论和Petri网理论的基本特点,是对基本模糊Petri网的进一步扩充。文中以促销决策支持为例,描述了非结构化决策问题到CXFPN模型建立,以及决策支持推导的相关问题。应用这种模型,对一类基于规则的决策系统的设计、分析和维护等变得容易了。     

基于知识的指控系统智能决策关键技术研究

着眼于知识在指挥控制中的作用机理,以提升军队指挥控制系统智能决策的科学性、智能化和适应性为目标,设计基于知识的指挥控制系统智能决策框架结构,采用基于本体的知识表示技术构建决策任务空间知识体系,研究面向情景空间的智能化知识服务技术,提出基于产生式规则的指挥实体静态决策推理模型和基于动态贝叶斯网的动态决策推理模型,旨在为未来我军智能化指挥控制系统的论证和建设提供理论与技术准备。     

基于World Wide Web的决策支持模型研究

文中通过对基于Ｗｏｒｌｄ Ｗｉｄｅ Ｗｅｂ（ＷＷＷ）上建立决策支持电子环境的研究，利用中介代理的概念，在用户和技术的拥有者之间架起了一座桥梁，构成了决策网，从而使ＷＷＷ上的决策技术得到共享。讨论了其结构、性能和各种功能，为进一步研究ＷＷＷ上的决策支持提供了一条途径。     

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。     

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．     

网络安全智能决策系统设计

随着云计算、物联网、大数据等新兴技术日渐成熟,网络环境也变得日益复杂.面对海量安全数据,人力已经难以详尽分析,导致做出的决策具有局限性、安全事件响应速度慢以及处置不及时等问题.文章立足于网络安全智能决策,在现有研究的基础上开展系统设计和研究工作.提出了网络安全智能决策系统的整体架构,设计了网络安全智能决策引擎,能够对网...     

Making Decisions on Innovation: Meetings or Networks?

Within some streams of thinking in the management of innovation and product development, the crux is the manager's active engagement in the evaluation, selection and control of the various activities through gate and portfolio meetings in which information is presented and decisions are made that manage innovation projects at a distance. This traditional managerial perspective regards the meetings as (important) ‘obligatory passage points’ but cannot explain a number of observations that reveal few decisions being made at those meetings. A network process perspective on the management of innovation is derived as an alternative to the normative linear view. This alternative perspective makes it possible to explain how innovation projects actually consist of myriad actions, negotiations, and micro‐decisions in the effort to create strong networks, leaving few decisions for the official gate and portfolio meetings. Through the analysis of two cases, this paper demonstrates how project managers work to stabilize the network in order to involve numerous human and non‐human actors and to encourage more and more of them into joining the network. Successfully establishing stable networks and successfully filling the templates for their projects leaves little room – and requires little intervention – for decision makers at portfolio meetings, where approvals are sought rather than decisions made. This study explains how gate and portfolio management meetings are, in some instances, better viewed as checkpoints rather than as decision meetings, how decision making is displaced from the meetings, and how the use of gate and portfolio management systems have created a number of mandatory templates which must be dealt with by the project managers. These mandatory documents function as boundary objects between and among the different worlds of the actors involved and establish new obligatory passage points in the management process; thus boundary objects become transformed into obligatory passage points. Implications for managers and research are outlined, including methods of dealing with the management of product innovation projects when the focus shifts from planning, preparations and decision making toward the co‐creation of technology and markets and involves interessement of human and non‐human actors.     

基于集散决策体系结构的智能车辆自主导航

智能车辆的体系结构作为智能车辆系统的基础,在构建智能车辆前必须得到合理的设计。为保证智能车辆系统的实时性和智能性,提出了基于集散决策的智能车辆体系结构。该结构由信息感知、规划决策、执行3个基本模块组成,其中规划决策分为低层次的分散决策和高层次的集中决策;分散决策对各种环境信息进行并行处理以得到各局部决策结果,集中决策对各分散决策结果进行综合判断并做出最终决策。按照以上设计思想,对道路环境下的智能车辆体系结构进行了仿真,同时实际构建了智能车辆车道识别及跟踪系统的体系结构。并进行了系统设计及实车试验。仿真结果表明,智能车辆能够根据实际环境信息做出合理决策,顺利完成车道跟踪、车距保持、换道行驶等任务。试验结果表明,在该体系结构控制下的智能车辆系统能够准确、可靠地完成车道识别、车道跟踪及车速保持任务。     

Combating discrimination using Bayesian networks

Discrimination in decision making is prohibited on many attributes (religion, gender, etc…), but often present in historical decisions. Use of such discriminatory historical decision making as training data can perpetuate discrimination, even if the protected attributes are not directly present in the data. This work focuses on discovering discrimination in instances and preventing discrimination in classification. First, we propose a discrimination discovery method based on modeling the probability distribution of a class using Bayesian networks. This measures the effect of a protected attribute (e.g., gender) in a subset of the dataset using the estimated probability distribution (via a Bayesian network). Second, we propose a classification method that corrects for the discovered discrimination without using protected attributes in the decision process. We evaluate the discrimination discovery and discrimination prevention approaches on two different datasets. The empirical results show that a substantial amount of discrimination identified in instances is prevented in future decisions.     

Using Patterns to Capture Architectural Decisions

Throughout the software design process, developers must make decisions and reify them in code. The decisions made during software architecting are particularly significant in that they have system-wide implications, especially on the quality attributes. However, architects often fail to adequately document their decisions because they don't appreciate the benefits, don't know how to document decisions, or don't recognize that they're making decisions. This lack of thorough documentation. This paper provides information about a decision's rationale and consequences, architecture patterns can help architects better understand and more easily record their decisions.     

基于深度学习和三支决策的DDoS攻击检测算法

针对软件定义网络(Software Defined Ntwork,SDN)中的分布式拒绝服务(Distribute Denial of Service,DDoS)攻击检测的方法少、现存方法入侵检测率低的问题,提出了一种基于深度学习和三支决策的入侵检测算法.首先使用深度信念网络对SDN的流表项进行特征提取,然后利用基于三支决策理论的入侵检测模型进行DDoS攻击的入侵检测,对于正域和负域的数据直接进行分类,对于边界域中的数据使用K近邻算法重新进行分类.仿真实验结果表明,与其他入侵检测模型相比,所提算法的入侵检测效率更高.     

Social learning with heterogeneous agents and sequential decision making

In this paper, we consider the problem of social learning in a network of agents where the agents make decisions sequentially by choosing one of two hypotheses on the state of nature. Each agent observes a signal generated according to one of the hypotheses and knows the decisions of all the previous agents in the network. The network contains two types of agents: rational and irrational. A rational agent makes a decision by not only using its private observation but also the decisions of each of the agents which already made decisions. To that end, the agent employs Bayesian theory. An irrational agent makes a decision by ignoring the available information and by randomly choosing the hypothesis. We analyze the asymptotic performance of a system with rational and irrational agents where we study rational agents that use either a deterministic or random decision making policies. We propose a specific random decision making policy that is based on the social belief and the private signals of the agents. We prove that under mild conditions the expected social belief in the true state of nature tends to one if the rational agents use the proposed random policy. In a network with rational agents that use deterministic policy, the conditions for convergence are stricter. We provide simulation results on the studied systems and compare their performance.     

三支决策与决策粗糙集融合模型

Paw lak粗糙集模型没有对正域、边界域和负域赋予语义,不能进行再决策,而三支决策对边界域赋予了新的语义,可以对边界域做出进一步刻画,对于边界域的进一步划分,依据属性的重要性,使满足条件的样本划入再决策域,不满足条件的样本继续保留在边界域中,降低了边界域样本处理的失误率.本文在对概率粗糙集模型、三支决策粗糙集的理论、贝叶斯理论的决策过程和决策粗糙集模型进行研究的基础上,提出了一种三支决策与决策粗糙集融合模型,与Paw lak-三支决策模型相比,其划分损失更小,处理结果更优.该模型运用三支决策理论对决策粗糙集的边界域赋予延迟决策的语义,对于延迟决策再运用三支决策理论进行迭代操作,对边界域样本进一步处理.在迭代的过程中,依据属性的重要程度将属性排序,从而客观的得到迭代过程中每次优先依据哪个属性进行划分.实验结果表明,该模型比单一运用决策粗糙集模型进行决策代价小,三支决策通过迭代对边界域处理的正确率有所提高,这为准确决策提供了一种新的方法.     

Decisions in software development projects management. An exploratory study

Given the importance of software in today's world, the development of software systems is a key activity that requires complex management scenarios. This article explores the implications of hard decisions in the context of software development projects (SDPs). More in deep, it focuses on the emotional consequences of making hard decisions in IT organisations. Complex SDPs involve a great variety of actors. This fact entails morale, feelings and emotions, which play an important role for communication, interaction and, ultimately, decision making. The aim of the article is twofold. First (Study 1), to identify which are the most important hard decisions in SDPS. Second (Study 2), to study the influence of emotions on decision-making processes (Study 2). Findings show the complex emotional consequences and difficulties that managers must face in hard decision-making processes.     

多阶段三支决策垃圾短信过滤模型

提出了一种多阶段三支决策垃圾短信过滤模型。该模型使用不同的信息粒度对短信进行表示,运用序列决策（即多阶段、多步骤决策）,在不同的决策阶段基于不同的信息粒度分别进行三支决策,有效地避免了当信息粒度太大或信息量不足时进行不合理的决策,对于不能满足当前决策条件的信息,可以通过补充足够的粒度信息作进一步的决策。最后通过实验证明了该模型的合理性和有效性。     

A New Approach to Estimation of the Effectiveness of Control Decisions under Conditions of Risk in ACS's

A new approach to the decision making in automatic control systems (ACS) under conditions of a risk is suggested, which reduces to the use of a risk function as an equivalent criterion along with the initial one. It is assumed that only the bounds of changes of uncertainties are known, but any statistical characteristics are unavailable. A formalized procedure of making guaranteed decisions is worked up and their existence is proved under constraints that are common in the mathematical theory of games.