Efficient multinomial selection in simulation

Consider a simulation experiment consisting of v independent vector replications across k systems, where in any given replication one system is selected as the best performer (i.e., it wins). Each system has an unknown constant probability of winning in any replication and the numbers of wins for the individual systems follow a multinomial distribution. The classical multinomial selection procedure of Bechhofer, Elmaghraby, and Morse (Procedure BEM) prescribes a minimum number of replications, denoted as v*, so that the probability of correctly selecting the true best system (PCS) meets or exceeds a prespecified probability. Assuming that larger is better, Procedure BEM selects as best the system having the largest value of the performance measure in more replications than any other system. We use these same v* replications across k systems to form (v*)^k pseudoreplications that contain one observation from each system, and develop Procedure AVC (All Vector Comparisons) to achieve a higher PCS than with Procedure BEM. For specific small-sample cases and via a large-sample approximation we show that the PCS with Procedure AVC exceeds the PCS with Procedure BEM. We also show that with Procedure AVC we achieve a given PCS with a smaller v than the v* required with Procedure BEM. © 1998 John Wiley & Sons, Inc. Naval Research Logistics 45: 459–482, 1998     

On gamma estimation via matrix kriging

In financial engineering, sensitivities of derivative prices (also known as the Greeks) are important quantities in risk management, and stochastic gradient estimation methods are used to estimate them given the market parameters. In practice, the surface (function) of the Greeks with respect to the underlying parameters is much more desired, because it can be used in real‐time risk management. In this paper, we consider derivatives with multiple underlying assets, and propose three stochastic kriging‐based methods, the element‐by‐element, the importance mapping, and the Cholesky decomposition, to fit the surface of the gamma matrix that can fulfill the time constraint and the precision requirement in real‐time risk management. Numerical experiments are provided to illustrate the effectiveness of the proposed methods.     

水平集方法中速度停止项函数的改进

对速度停止项函数的研究发现,现今的速度停止项采用的单一全局阈值法很难使经典水平集算法得到较准确的分割效果。为此,提出了一种新的速度停止项函数,该函数通过引入变阈值较好的区分了图像的边缘区与同质区,以使采用该速度停止项函数的水平集方程实现在同质区加速演化,在边缘区停止演化的目的。实验结果表明,采用速度停止项函数能够使水平集方法获取更好的分割结果。     

多退化模式下的电子装备可靠性建模

通常加速退化分析中退化失效只考虑或者假设只有一个退化通道,而实际上很多情况下会存在多退化模式.产品的各个退化通道间的关系存在随机性,即任意两个退化通道间不可能只是单一的相关或者独立.在考虑这种相关性的条件下,深入研究了电子产品的性能退化理论和机理,提出了两个多退化模式竞争失效的数学模型,分别阐述了退化通道相关与独立的两种不同情况下产品可靠度评估方法.     

Scheduling combat logistics force replenishments at sea for the US Navy

The Replenishment at Sea Planner (RASP) is saving the U.S. Navy millions of dollars a year by reducing fuel consumption of its Combat Logistics Force (CLF). CLF shuttle supply ships deploy from ports to rendezvous with underway U.S. combatants and those of coalition partners. The overwhelming commodity transferred is fuel, ship‐to‐ship by hoses, while other important packaged goods and spare parts are high‐lined, or helicoptered between ships. The U.S. Navy is organized in large areas of responsibility called numbered fleets, and within each of these a scheduler must promulgate a daily forecast of CLF shuttle operations. The operational planning horizon extends out several weeks, or as far into the future as we can forecast demand. We solve RASP with integer linear optimization and a purpose‐built heuristic. RASP plans Replenishment‐at‐Sea (RAS) events with 4‐hour (Navy watch) time fidelity. For five years, RASP has served two purposes: (1) it helps schedulers generate a daily schedule and animates it using Google Earth, and (2) it automates reports command‐to‐ship messages that are essential to keep this complex logistics system operating.     

Indications and warning in Belgium: Brussels is not Delphi

The terrorist attacks in France and Belgium of 2015–2016 that occurred while these countries were in a heightened state of alert raise questions about indications and warning methodology as well as effectiveness of the blanket-protection deployment of security services assisted even by the military. Response and perhaps even more anticipation may require strategic rethinking in light of the predatory attacks that target the most vulnerable spots of the public space. This study looks at threat analysis in Belgium as conducted through her intelligence fusion centre Coordination Unit for Threat Analysis (CUTA)?????? since its inception in 2006. With a special focus on what is known, at the time of writing, about the terrorist attacks in Paris and Brussels, this study hopes to put into context how the system (mal)functions and will also consider the preventive measures that respond to the threat, and the international aspects which have implications far beyond Belgian borders. Therefore, a case is made for not just a Belgian homeland security framework, but one that fits into an EU-wide security concept.     

舰船总体任务成功性的建模与应用

针对典型舰船的系统组成,进行了全舰任务成功性指标的示例计算,给出了总体指标的层次化表达方式。以舰船任务过程和典型任务剖面为依据,分析了任务可靠性和任务成功性之间的区别与联系,建立了舰船总体任务成功性指标的多阶段整体模型,并对航渡、待机、交战、撤离、返航阶段分别进行了仿真和解析建模。在建模与计算的基础上,通过敏感性分析计算了任务阶段持续时间的单位降低率等指标,为舰船任务成功性问题及其相关研究,提供了一个系统性的分析框架和方法。     

考虑维修时间不确定性的维修任务选择模型

由于维修时间存在不确定性,如何在考虑维修时间不确定性的情况下确定任务间隔期的维修方案是一个值得探讨的问题.给出了一种考虑维修时间不确定性的维修任务选择模型及其求解算法,以在一定置信水平下获得最佳的维修方案.首先,给出了考虑维修时间不确定性的维修任务选择问题的假设条件,并建立了一种非线形的、离散的机会约束规划.其次,给出了一种基于随机模拟的粒子群求解算法,包括粒子的表示、适应度函数、更新公式、算法框架等.最后,给出了具体实例,证明了模型与算法的有效性.该模型非常适用于管理人员在维修时间存在不确定性的情况下作出合理的维修任务选择决策.