NON‐LINEARITY IN THE DEFENCE EXPENDITURE – ECONOMIC GROWTH RELATIONSHIP IN TAIWAN

As we enter the 21st Century, technologies originally developed for defense purposes such as computers and satellite communications appear to have become a driving force behind economic growth in the United States. Paradoxically, almost all previous econometric models suggest that the largely defense‐oriented federal industrial R&;D funding that helped create these technologies had no discernible effect on U.S. industrial productivity growth. This paper addresses this paradox by stressing that defense procurement as well as federal R&;D expenditures were targeted to a few narrowly defined manufacturing sub‐sectors that produced high tech weaponry. Analysis employing data from the NBER Manufacturing Productivity Database and the BEA’ s Input Output tables then demonstrates that defense procurement policies did have significant effects on the productivity performance of disaggregated manufacturing industries because of a process of procurement‐driven technological change.     

线性规划优化分析的元模型方法及其比较

线性规划优化分析在经济管理等领域有着广泛的应用。当线性规划约束条件的右端向量在一定范围内变化时,目标函数的最优值是右端向量的一个复杂的分片线性函数,但通常难以给出分析表达式。应用多项式回归、径向基函数、Kriging法及多项式回归 Kriging法这四种元模型方法,能快速预测最优值函数。通过仿真实验,对这四种形式的元模型作较全面的比较分析。数值实验的结果表明,用次数较少的实验设计,后三种方法都具有较高的拟合精度;特别地,多项式回归 Kriging法不仅拟合精度高,而且还能用一个二阶多项式给出最优值函数的一个简明的近似描述。结果表明,元模型方法是研究线性规划优化分析问题的有效途径。     

基于多元回归理论的油液光谱分析诊断方法

利用多元回归理论对光谱数据建立了多元回归诊断模型,并且建立了回归方程以及回归系数的检验方法,给出了异常磨损的界限值,最后通过诊断实例证明了该模型有一定的应用价值。     

基于类成员后向切片的面向对象程序回归测试

程序切片是一种重要的程序分析方法,类成员级粒度的切片技术目前仅仅有Tip提出的类层次切片技术.Tip提出的类层次切片技术其分析基础是Rossie-Friedman的类层次框架,但主要用于面向对象程序的优化,并不适用于回归测试.本文基于Rossie-Friedman的类层次框架提出类成员后向切片方法,并提出一个覆盖类的方法一级的回归测试策略.     

Accuracy assessment of detection performance for sidescan sonars

Sidescan sonars are used in detecting hostile targets on the seabed. An accurate representation of the sensor performance is required to carefully plan and execute searches. We studied several confidence interval methods for assessing the accuracy of detection performance as a function of range from hostile targets. Using simulation, we determined that the best approach for modeling sensor data was piecewise logistic regression with cubic B‐splines at carefully selected knots. This method was demonstrated on real data collected from the CITADEL sea trial. © 2012 Wiley Periodicals, Inc. Naval Research Logistics, 2012     

基于偏最小二乘回归的军用飞机采购价格预测

考虑到军用飞机采购价格样本数据少、难于预测的特点和偏最小二乘回归方法在处理小样本多元数据方面的优势,提出一种基于偏最小二乘回归的军用飞机价格预测方法.偏最小二乘回归首先提取第一、第二主成分对采购价格样本的特异点进行剔除;然后进行变量投影重要度分析来筛选变量;最后,偏最小二乘回归对筛选的变量进行回归建立军用飞机价格预测模型,并对军用飞机价格进行预测.结果表明,在军用飞机价格预测方面,与未筛选变量的回归模型和逐步多元回归相比,经过变量筛选的偏最小二乘回归模型预测的精度更高,更能体现采购价格与飞机性能参数之间的关系.     

回归分析在漏磁定量检测中的应用

通过分析漏磁场,选取法向分量的峰峰值和峰峰值间距作为漏磁通信号的特征量。重点介绍了多元回归分析模型理论、参数估计方法和回归模型的假设检验,得到缺陷宽度、深度与峰峰值和峰峰值间距之间的回归模型,最后利用漏磁数据对回归模型进行了检验,结果表明预测缺陷宽度和深度的误差不超过10%,利用回归分析能够实现漏磁检测的定量化。     

导弹武器系统研制费用估算方法

针对导弹武器系统研制费用相关数据样本量少,变量之间存在严重共线性等问题,提出了一种基于偏最小二乘法的研制费用估算模型。引入库克距离对原始数据进行识别,并剔除异常数据,采用灰色关联度分析法选取相关度高的自变量,提高模型准确性和稳定性。利用偏最小二乘法进行数据拟合,估算出导弹武器系统的研制费用。应用算例的计算结果表明,该方法建立的研制费用估算模型拟合度良好,计算误差在8%以内。     

防空导弹平均速度分析

分析了防空导弹平均速度的计算方法。首先给出了水面舰艇编队防空作战中目指线和自卫线的计算模型,阐述了防空导弹平均速度在其中的重要影响,然后分析了防空导弹速度特性,在此基础上得出满足作战要求的计算方法,最后根据典型弹道参数对防空导弹平均速度进行了仿真计算。     

An approach for predicting digital material consumption in electronic warfare

Electronic warfare is a modern combat mode, in which predicting digital material consumption is a key for material requirements planning (MRP). In this paper, we introduce an insensitive loss function (ε) and propose a ε-SVR-based prediction approach. First, we quantify values of influencing factors of digital equipments in electronic warfare and a small-sample data on real consumption to form a real combat data set, and preprocess it to construct the sample space. Subsequently, we establish the ε-SVR-based prediction model based on “wartime influencing factors - material consumption” and perform model training. In case study, we give 8 historical battle events with battle damage data and predict 3 representative kinds of digital materials by using the proposed approach. The results illustrate its higher accuracy and more convenience compared with other current approaches. Taking data acquisition controller prediction as an example, our model has better prediction performance (RMSE = 0.575 7, MAPE (%) = 12.037 6 and R² = 0.996 0) compared with BP neural network model (RMSE = 1.272 9, MAPE (%) = 23.577 5 and R² = 0.980 3) and GM (1, 1) model (RMSE = 2.095 0, MAPE (%) = 24.188 0 and R² = 0.946 6). The fact shows that the approach can be used to support decision-making for MRP in electronic warfare.