多特征空间下的支持向量机及其在图像识别中的应用

分别在主成分分析(PCA)、独立成分分析(ICA)和线性鉴别分析(LDA)所构造的特征空间下用模糊支持向量机(FSVM)进行人脸识别。同时,提出了一种改进的FSVM方法,即利用FSVM和多叉决策树相结合的思想来设计人脸分类器,从而使FSVM分类器的速度得到了大幅度的提高。通过在ORL人脸库上的实验结果表明,该算法是有效的。     

Dynamic learning,pricing, and ordering by a censored newsvendor

We address the problem of determining optimal ordering and pricing policies in a finite‐horizon newsvendor model with unobservable lost sales. The demand distribution is price‐dependent and involves unknown parameters. We consider both the cases of perishable and nonperishable inventory. A very general class of demand functions is studied in this paper. We derive the optimal ordering and pricing policies as unique functions of the stocking factor (which is a linear transformation of the safety factor). An important expression is obtained for the marginal expected value of information. As a consequence, we show when lost sales are unobservable, with perishable inventory the optimal stocking factor is always at least as large as the one given by the single‐period model; however, if inventory is nonperishable, this result holds only under a strong condition. This expression also helps to explain why the optimal stocking factor of a period may not increase with the length of the problem. We compare this behavior with that of a full information model. We further examine the implications of the results to the special cases when demand uncertainty is described by additive and multiplicative models. For the additive case, we show that if demand is censored, the optimal policy is to order more as well as charge higher retail prices when compared to the policies in the single‐period model and the full information model. We also compare the optimal and myopic policies for the additive and multiplicative models. © 2007 Wiley Periodicals, Inc. Naval Research Logistics, 2007     

Integrated production scheduling and preventive maintenance planning for a single machine under a cumulative damage failure process

This paper finds the optimal integrated production schedule and preventive maintenance plan for a single machine exposed under a cumulative damage process, and investigates how the optimal preventive maintenance plan interacts with the optimal production schedule. The goal is to minimize the total tardiness. The optimal policy possesses the following properties: Under arbitrary maintenance plan when jobs have common processing time, and different due dates, the optimal production schedule is to order the jobs by earliest due date first rule; and when jobs have common due date and different processing times, the optimal production schedule is shortest processing time first. The optimal maintenance plan is of control limit type under any arbitrary production schedule when machine is exposed under a cumulative damage failure process. Numerical studies on the optimal maintenance control limit of the maintenance plan indicate that as the number of jobs to be scheduled increases, the effect of jobs due dates on the optimal maintenance control limit diminishes. © 2007 Wiley Periodicals, Inc. Naval Research Logistics, 2007     

基于支持向量机的战套器材组配决策研究

通过交叉验证找出影响战套组配的3个重要参数的取值,并构建飞机的战套器材组配决策模型,最后利用libsvm工具包对某型军用飞机的战套组配的可行性进行了分析。结果表明：基于支持向量机的战套器材组配决策是可行的。     

坦克炮火力威力评价的多指标灰色关联决策模型

为了对坦克炮火力威力进行评估,提出一种新的解决方法.针对坦克炮火力威力评价中需要进行多属性、多指标决策的特点,利用在"奖优罚劣"原则基础上建立的[-1,1]线性变换算子,寻求决策方案的正、负理想方案,计算评价方案与正、负理想方案的关联度,建立了坦克炮火力威力评价的灰色关联度决策模型.计算实例的结果表明,该模型计算简捷、分辨程度较高、稳定性也好,可应用于坦克炮火力威力评价.     

基于模糊折衷理论的目标威胁度综合评价模型

由于海洋环境的复杂性和水声信道的特殊性,多目标跟踪过程中的目标威胁评估一直是水声信号处理领域的突出难题.目标威胁度是目标分配的重要依据,必须综合考虑目标的多种特征信息.针对水下声自导系统,提出了目标威胁度评估指标体系,构建隶属度函数对各个指标进行了量化,并建立了基于模糊折衷的目标威胁度综合评价模型.仿真结果证明该方法能有效节省航程,为提高水下航行器的作战效能提供了有效途径.     

Optimal timing of switches between product sales for sports and entertainment tickets

Like airlines and hotels, sports teams and entertainment venues can benefit from revenue management efforts for their ticket sales. Teams and entertainment venues usually offer bundles of tickets early in their selling horizon and put single‐event tickets on sale at a later date; these organizations must determine the best time to offer individual tickets because both types of ticket sales consume the same fixed inventory. We model the optimal a priori timing decision for a seller with a fixed number of identical tickets to switch from selling the tickets as fixed bundles to individual tickets to maximize the revenue realized before the start of the performance season. We assume that bundle and single‐ticket customers each arrive according to independent, nonhomogeneous Markovian death processes with a linear death rate that can vary over time and that the benefit from selling a ticket in a package is higher than from selling the ticket individually. We characterize the circumstances in which it is optimal for the seller to practice mixed bundling and when the seller should only sell bundles or individual tickets, and we establish comparative statics for the optimal timing decision for the special case of constant customer arrival rates. We extend our analytical results to find the optimal time for offering two groups of tickets with high and low demand. Finally, we apply the timing model to a data set obtained from the sports industry. © 2007 Wiley Periodicals, Inc. Naval Research Logistics, 2008     

多核异构冗余模型设计与可靠性分析

为进行电磁仿生研究,提高复杂电磁环境下控制系统运行的可靠性,在一种新型计算机系统结构框架的基础上,提出了多核异构冗余模型,设计了互关总线协议,实现了相应的容错策略,进而进行了异构双机冗余系统的实验,并利用马尔可夫过程模型分析了系统的电磁抗扰能力。实验表明,该模型能够有效地提高系统可靠性,满足相关仿生研究的设计要求。     

网络中心化决策优势建模及分析*

决策优势能力是判断军事信息系统体系结构设计优劣的一个重要依据。对网络中心化决策优势能力评估进行了研究,给出了决策优势的能力模型,并利用信息熵理论建立了决策知识的数学描述;将信息系统体系结构转换为抽象的决策网络,并根据任务划分和群决策机制自动生成决策子网;建立了基于拓扑结构的网络复杂性模型;综合决策知识和网络复杂性,建立了决策子网和整个决策网络的决策优势能力评估模型。最后,结合应用案例分析验证了方法的有效性。     

陆军战斗决心方案评估方法研究

战斗决心方案评估是陆军指挥员及指挥机关组织战斗过程中的一项重要工作。研究评估方法为陆军部队行动选择战斗决心方案提供依据。对战斗决心方案的评估,根据决心方案的战术手段、作战目标选择、战斗部署等三项主要内容,建立评估指标体系和评估数学模型,得出综合评估结果。该量化分析的评估方法提高了决策的精确性。