基于混合数据挖掘模型预测用户流失

用户流失预测问题广泛应用在银行、金融、电信等多种领域。对用户行为进行有效的预测和分析有助于企业的竞争和了解瞬息万变的市场规律。采用3种混合的数据挖掘模型对用户流失问题进行了研究,以形成一个准确高效的用户流失预测模型。这3种模型应用于数据挖掘的两个阶段:聚类阶段和预测分析阶段。在第1阶段中,对用户的数据进行过滤。第2阶段对用户行为进行预测。第1个模型采用了二分k-means算法进行数据过滤和多层感知人工神经网络(MLP-ANN)相结合进行预测。第2个模型采用层次化聚类与MLP–ANN相结合进行预测。第3个模型使用自组织映射(Self-Organizing Maps)与MLP-ANN进行预测。这3种模型预测分析基于真实数据,用户流失率采用3种模型混合计算的方式得出结果并同真实值进行比较。分析结果表明采用多模型的混合数据挖掘模型的数据准确度优于普通的单一模型。     

面向多目标跟踪的PHD滤波多传感器数据融合算法

针对密集杂波环境下单传感器应用高斯混合PHD算法进行多目标跟踪时性能下降的问题,提出一种面向多目标跟踪的PHD滤波多传感器数据融合算法。首先构建了基于高斯混合PHD滤波的多传感器数据融合系统框架,各传感器利用高斯混合PHD滤波算法进行局部状态估计,然后对各传感器的状态估计结果进行关联度计算,最后通过构建自适应混合参数,引入协方差交叉算法对关联状态进行融合。仿真实验表明,与单传感器高斯混合PHD多目标跟踪算法相比,所提算法有效提高了目标数量和状态的估计精度。     

Does military expenditure increase external debt? Evidence from Asia

This article empirically explores the effect of military spending on external debt, using a sample of ten Asian countries over the years from 1990 to 2011. The Hausman’s test suggests that the random-effects model is preferable; however, both random-effects and fixed-effects models are used in this research. The empirical results show that the effect of military spending on external debt is positive, while the effects of foreign exchange reserves and of economic growth on external debt are negative. For developing countries caught in security dilemma, military expenditure often requires an increase in external debt, which may affect economic development negatively.     

图像标注研究及其在情报处理中的应用

图像数据具有直观、信息量丰富等特点。图像标注方法通过获取图像特征,训练语言模型,实现用自然语言自动描述图像信息。简要介绍了图像标注方法的分类及其相关关键技术。研究表明,通过对大规模图像的自动描述,能更好地管理、分析海量图像信息,能高效地对图像进行分类、检索。结合特定的信息处理技术,图像标注可用于发现有价值的情报信息,为国防安全、战略决策等提供信息支撑。     

美国陆军数据战略目标及实施

为深入研究美陆军数据战略目标及实施策略,为我军数据战略研究提供借鉴,文章对美陆军2016年发布的最新《陆军数据战略》进行分析,指出其目标是实现数据的可视化、可获取、可信任、可理解和互操作,并对美陆军数据战略的具体实施策略进行了剖析,指出美国陆军数据战略推动的是美军军事作战理论转型,从"网络为中心"转变为以"数据为中心"作战理念,其核心意图在于以数据优势实现指挥决策优势。     

地籍数据库点线拓扑一致性并行检查方法

针对拓扑检查算法复杂、计算量大,串行计算已远不能满足海量地籍数据高效拓扑检查需求的问题,在分析了点线拓扑关系的并行特点基础上,将界址点的数据划分方法与界址线的QR空间索引方法相结合,实现了界址点与界址线的并行拓扑计算。用某地区实际的界址点集与界址线集对点线拓扑并行检查进行实验。测试结果表明:并行检查算法的并行效率随着进程数的增加而有所衰减,但稳定在30%以上,加速比达到5以上,且相比于Arc GIS效率提升了30倍以上。并行检查方法以工具的方式集成应用于高性能地理计算平台中,应用效果良好。     

Single batch machine scheduling with deliveries

We consider the problem of scheduling a set of n jobs on a single batch machine, where several jobs can be processed simultaneously. Each job j has a processing time p_j and a size s_j. All jobs are available for processing at time 0. The batch machine has a capacity D. Several jobs can be batched together and processed simultaneously, provided that the total size of the jobs in the batch does not exceed D. The processing time of a batch is the largest processing time among all jobs in the batch. There is a single vehicle available for delivery of the finished products to the customer, and the vehicle has capacity K. We assume that K = rD, where and r is an integer. The travel time of the vehicle is T; that is, T is the time from the manufacturer to the customer. Our goal is to find a schedule of the jobs and a delivery plan so that the service span is minimized, where the service span is the time that the last job is delivered to the customer. We show that if the jobs have identical sizes, then we can find a schedule and delivery plan in time such that the service span is minimum. If the jobs have identical processing times, then we can find a schedule and delivery plan in time such that the service span is asymptotically at most 11/9 times the optimal service span. When the jobs have arbitrary processing times and arbitrary sizes, then we can find a schedule and delivery plan in time such that the service span is asymptotically at most twice the optimal service span. We also derive upper bounds of the absolute worst‐case ratios in both cases. © 2015 Wiley Periodicals, Inc. Naval Research Logistics 62: 470–482, 2015     

A sequential scheduling problem with impatient jobs

There are n customers that need to be served. Customer i will only wait in queue for an exponentially distributed time with rate λ_i before departing the system. The service time of customer i has distribution F_i, and on completion of service of customer i a positive reward r_i is earned. There is a single server and the problem is to choose, after each service completion, which currently in queue customer to serve next so as to maximize the expected total return. © 2015 Wiley Periodicals, Inc. Naval Research Logistics 62: 659–663, 2015     

电气火灾统计分析研究

通过对比分析近10年来的火灾统计数据,找出了近几年我国电气火灾发生和发展的特点及规律.根据电气火灾原因分布规律,发现电气线路火灾在电气火灾中占有最大比例;根据电线电缆火灾原因统计数据,分析出发生的电线电缆火灾中,外因引发重大火灾的概率和数量更大.     

对我国维和警察在任务区进行文化传播的思考

文化影响力是一个国家软实力的重要组成部分,对外进行文化传播是塑造一个国家积极正面形象、提高软实力的有效手段。通过探讨维和警察进行文化传播的重要性、任务、方式以及应注意的问题,旨在对中国维和警察及维和警察培训有所裨益。中国维和警察应发挥自身优势积极进行中华文化传播,塑造中国警察的良好形象,打造中国维护世界和平、构建和谐世界、负责任的大国形象。