供应商选择定量模型的探讨

文章综合层次分析法和基准对比法的优点,选定时间、质量、成本、服务、柔性为关键决策因素,以加权相对偏差距离最小为目标,建立了简单易操作的供应商选择定量模型.     

有人/无人机混合编队有限干预式协同决策

针对Leader-Follower异构型有人/无人机混合编队协同决策系统具有递阶分布式决策结构、决策信息分散以及通信约束等特点,在智能体模糊认知图(ABFCM)和动态模糊认知图(DFCM)的理论基础上,提出了一种有限干预式协同决策机制。通过构建层次化的Follower平台自主决策模型,实现了该平台与外部系统良好的交互能力,体现了自主决策的"动态性"。通过设计Leader平台的3种干预策略,满足了不同层次的决策需求,体现了干预过程的"有限性"。仿真结果表明:有限干预协同决策模型能够适应外部环境的动态变化,充分发挥Follower平台的自主决策能力;而不同层次的有限干预介入既减轻了Leader平台的控制负荷,又保证了决策的有效性和可行性,可为解决其他同类复杂系统的协同决策问题提供理论依据和方法参考。     

Special issue introduction: Approaching spatial uncertainty visualization to support reasoning and decision making

While research on uncertainty and decision-making has a long history across several disciplines, recent technological developments compel researchers to rethink how to best address and advance the understanding of how humans reason and make decisions under spatial uncertainty. This introduction presents a visual summary graphic to provide an overview of each article in this special issue. Upon viewing these visual summaries, the reader will find that each of these articles covers different topics in the uncertainty visualization domain, offering complementary research in this field. Extending this body of research and finding new ways to explore how these visualizations may help or hinder the analytical and reasoning process of humans continues to be a necessary step towards designing more effective uncertainty visualizations to support reasoning and decision-making.     

Visually supported reasoning under uncertain conditions: Effects of domain expertise on air traffic risk assessment

This article investigates the impact that domain expertise has on risk assessment when analyzing uncertain geographical and sensor data. The differences between novice and expert air traffic operators were examined taking into account the performance of identifying and classifying threatening targets, the time needed to carry out such classifications, and the confidence reported for each decision. The results show that confidence was significantly higher for the expert group. This was supported by the after-test questionnaire because none of the novice participants reported being more confident with the visualizations of uncertainty provided. No significant differences regarding time and performance were found between the groups, even if experts needed, on average, more time to make a decision. Based on the collected logs, the experienced participants more often accessed the detailed information for each object presented by the tool tip. Both the time taken and the data accessed might indicate that experts had better situation awareness. Finally, the experts reported higher workload values related to performance.     

一种基于模糊决策的矩形目标提取算法

航空图片中的城市建筑物屋顶一般为矩形或平行四边形,能准确而快速地提取矩形,无论在军事上还是民用上都具有非常重要的意义.针对从航空图像中自动提取矩形建筑物目标的问题,提出了一种基于模糊决策的矩形目标提取方法.首先根据直线提取方法得到的直线特征集生成假设矩形空间,进而采用模糊数学方法进行证据融合得到决策信息,并对生成的假设矩形进行选择与验证,得到矩形目标结构特征.实验结果表明,该算法避免了固定阈值的设定,适应性强,鲁棒性好,有较强的实际应用价值.      

基于改进共生生物搜索算法的空战机动决策

针对现代空战机动决策问题,提出了一种基于改进共生生物搜索（SOS）算法的空战机动决策方法。首先,分析了传统基本机动动作库存在的不足,对其进行了改进和扩充,设计了11种常用的基本机动动作;然后,综合考虑角度、距离、速度、高度和战机性能优势,构造了战机机动决策优势函数;最后,针对传统共生生物搜索算法在收敛速度、收敛精度以及局部最优上存在的缺陷,将轮盘赌选择方法、动态变异率和梯度思想引入到传统算法当中,对算法有效性和算法性能进行了仿真分析。仿真结果表明,改进的共生生物搜索算法在收敛速度、收敛精度以及跳出局部最优上更具优势,能够满足空战机动决策需求。      

数据挖掘技术

数据挖掘技术是继网络之后的又一个技术热点,本文从数据挖掘的概念出发,根据数据挖掘的特点对其进行了分类,在对数据挖掘的重点方法和一般数据挖掘过程进行了阐述的基础上,分析总结了WEB数据挖掘方法和流程。在文章的最后对数据挖掘的发展还做了预测。     

基于数据仓库的高尔夫决策支持系统设计与实现

以数据仓库技术为基础,结合联机分析处理技术构建高尔夫决策支持系统。系统通过建立数据仓库对来自不同数据源的半结构化数据进行存储,采用联机分析处理技术对数据进行多侧面、多角度的分析,为决策人员做出决策提供强大的辅助支持。     

基于启发式蚁群算法的协同多目标攻击空战决策研究

协同多目标攻击空战决策是现代战机在超视距条件下进行协同空战的关键技术之一。它是寻求一个优化分配方案,将目标分配给各友机,力求使攻击效果最优。本文在对协同多目标攻击战术进行深入分析的基础上,提出了一种用于空战决策的启发式蚁群算法,该算法通过求解友机导弹对目标的最优分配来确定空战决策方案。仿真实验表明所提出的启发式蚁群算法对最优解的搜索效率明显优于基本蚁群算法,是一种求解协同多目标攻击空战决策问题的有效算法。