药物效用鉴定的序贯抽样检验方法和条件推导

给出了制定药物效用鉴定的序贯抽样检验方案,对未用的同类药品进行随机抽样,利用抽样结果,对剩下的N-n个样品的性能进行推断,得到判断药品是否失效的抽样方法以及有效的抽样截断方案,在减小抽样量的前提下,准确的判断药物是否有效.并对该序贯抽样性能的优劣与固定样本最优检验方法进行了比较,得到在犯同样错误的前提下,序贯抽样检验的样本量比固定样本最优检验的样本量小的多.     

基于最小均方插值的码元同步算法研究

从软—硬件协同设计的角度出发 ,提出了软件无线电系统中码元同步的一种实现方案。该方案以信号插值为理论基础 ,用软件实现整个码元同步过程。其特点是以估计性能更佳的最小均方滤波器替代传统的多项式插值滤波器 ,并利用软件实现时可以进行大批量数据缓存的优势 ,提出能量检测算法 ,以克服半码元周期传输延迟时出现的高误码率问题     

Estimating the point availability with right‐censored data

The point availability of a one‐unit system at a specified time is defined as the probability that the component is operating at that time. When both operating time and repair time are subject to random (right) censorship, we propose an asymptotic nonparametric approach for constructing confidence intervals for the point availability of the system. The technique is based on the fact that a product limit estimator converges to a Gaussian process. The method is also extended to finding confidence intervals for the point availability of a complex system using the δ‐Method. © 1999 John Wiley & Sons, Inc. Naval Research Logistics 46: 119–127, 1999     

基于磨损量的数学模型及其数值模拟与分析

通过建立及讨论摩擦片磨损量的数学模型,用随机数学的方法给出了该模型的概率分布,并初步讨论了该分布的一些基本特征,通过数值模拟还给出了其独特的分布特征,如与正态分布的关系与区别,从而也为摩擦片失效分析提供了新的模型与方法.     

Attrition through a partially coordinated area defense

An area defense consists of several groups that act independently, i.e., do not communicate with each other. Each group has a fixed number of defenders and a controller that allocates these defenders optimally against the individual attackers comprising an attack. We analyze the effectiveness of this partially coordinated defense against a simultaneous attack of known size in which all attackers are considered to be equally lethal. © 2004 Wiley Periodicals, Inc. Naval Research Logistics, 2005.     

光电坐标传感器在光幕靶中的应用

针对光电报靶系统的标校问题,以及可见光光幕靶光电接收器检测灵敏度的一致性和与海量数据的高速采集问题,采用大发射角的LED发光管,设计了光电开关电路和高速采样保持电路,实现了基于光电开关和取样电阻网络的光电坐标传感器,提高了系统的检测灵敏度和一致性,降低了系统设计的难度和成本。试验证明：该方法精度较高,具有良好的应用前景。     

Externality of Defense Expenditure in the United States: A New Analytical Technique to Overcome Multicollinearity

Abstract

This study estimates a three-sector Feder–Ram model using US annual data for 1965–2014 to confirm the externality of defense expenditure in the United States. Although the model is often used in the literature to scrutinize whether this effect exists, a flaw intrinsic to this model is the appearance of multicollinearity. In this study, I introduced novel techniques, namely: the standardization and estimation of a simple slope, to estimate the model. The results are as follows. First, I prove that the multicollinearity problem can be resolved by standardization. Second, externality, which is judged to conventionally exist, is not found. Third, increases in defense expenditure bring about positive but limited economic growth when the ratio of private to defense expenditure in the previous year ranges from 5.09 to 6.82%. By re-estimating the model, this study contributes to developing the Feder–Ram model within the related literature.     

Nonparametric bayesian lifetime data analysis using dirichlet process lognormal mixture model

We propose a nonparametric Bayesian lifetime data analysis method using the Dirichlet process mixture model with a lognormal kernel. A simulation‐based algorithm that implements the Gibbs sampling is developed to fit the Dirichlet process lognormal mixture (DPLNM) model using rightly censored failure time data. Five examples are used to illustrate the proposed method, and the DPLNM model is compared to the Dirichlet process Weibull mixture (DPWM) model. Results indicate that the DPLNM model is capable of estimating different lifetime distributions. The DPLNM model outperforms the DPWM model in all the examples, and the DPLNM model shows promising potential to be applied to analyze failure time data when an appropriate parametric model for the data cannot be specified. © 2013 Wiley Periodicals, Inc. Naval Research Logistics, 2013     

引入块内码元频数抽样的块内频数检测识别方案

为识别链路层比特流是否加密,以未加密与加密数据在随机统计特性上的差异为依据,利用随机性检测的方法对加密比特流进行识别.在不同比特流长度条件下对3种典型随机性检测方法的识别率进行了比较研究.针对3种检测方法均对长度较短的未加密比特流识别率较低的问题,在块内频数检测的基础上,提出了基于块内码元频数抽样的比特流预处理方案,以及块内频数检测最优分块长度选择方案,并对预处理方案对识别率的影响进行了分析.实验结果表明,提出的方案可以显著提高块内频数检测对未加密比特流的识别率.     

作战准备车辆装备质量分层抽样方法研究

针对当前我军车辆装备质量全面技术普查过程中存在的问题，探索一种新的作战准备车辆装备质量评估方法——抽样评估法，综合运用简单随机抽样和分层抽样，提出作战准备车辆装备质量抽样的样本量确定方法和子样本量分配方法，最后示例说明该方法的应用。