用神经网络建立反后坐装置参数对其性能的影响模型

详细分析火炮反后坐装置影响因素基础上,用人工神经网络建立了完整的反后坐装置参数对其性能的影响模型,运用算例证明了神经网络在反后坐装置中应用的可行性。所提出的提灌法使网络的学习更加灵活,收敛更快。     

C~3I系统的决策时延分析

决策是C~3I 系统的核心问题之一。用Petri 网理论研究C~3I 系统的决策问题已取得了长足的进展。根据决策过程各阶段之所需时间具有随机性及不独立性的特点,以变迁发射时间不独立的随机Petri 网作为决策时延的建模与分析工具,并给出了这种随机Petri 网模型的一般分析方法。     

用于态势估计的贝叶斯网络方法

态势估计系统需要对大量的不确定性知识进行处理,不确定性知识表示和推理是态势估计中的研究热点.利用贝叶斯网络技术,可以实现对不确定性知识的处理.为此讨论了贝叶斯网络理论,详细分析了态势估计的功能模型,提出事件检测是态势估计的核心和起点,研究了用于态势估计的贝叶斯网络的构建方法.该方法充分考虑贝叶斯网络的几项基本要素,可以解决态势估计领域中贝叶斯网络的构建问题.贝叶斯网络技术在态势估计领域具有广阔的前景,将极大地推动态势估计系统的发展.     

On lifetimes in random environments

For a component operating in random environment, whose hazard rate is assumed to be the realization of a suitable increasing stochastic process, conditions are found such that its lifetime is increasing in likelihood ratio (ILR). For the lifetimes of two components of the same kind some comparisons based on partial stochastic orders are presented. Some applications to the case of repairable components are finally provided. © 1998 John Wiley & Sons, Inc. Naval Research Logistics 45: 365–375, 1998     

基于PMC模型的神经网络

在计算机系统中有许多诊断算法,其中针对PMC模型有0-1规划的诊断算法,这个诊断算法是NP完全的,是在多项式时间内不可解的。然而利用神经网络的高度并行性这个特点,就可以在很短的时间内解出结果。主要分析了系统诊断模型PMC的症候特征,得到其充要条件,提出了新的算法,该算法具有高度的并行性,神经网络的发展为此提供了用模拟电路来实现算法的可能性,并进行了模拟验证。     

一种高超声速飞行器在线反馈滤波算法

高超声速飞行器是近年来各国大力发展的新概念飞行器,针对其飞行运动轨迹难以进行高精度跟踪这一问题,结合神经网络强大的自适应和自学习能力,提出了一种高超声速飞行器在线反馈滤波算法.其核心是在当前统计模型的基础上,利用BP神经网络与卡尔曼滤波相结合进行滤波器设计,实现对高超声速飞行器高精度跟踪.最后通过仿真试验进行比较,验证...     

基于卷积神经网络的卫星网络协调态势评估方法

为充分发掘利用海量卫星网络数据,提高决策效率,加强空间频轨资源获取与储备的分析手段,尤其是对地球静止轨道资源的协调获取问题,提出基于机器学习算法的卫星网络态势评估策略。通过对卫星网络协调因素进行特征分析,选择卷积神经网络(Convolution Neural Network, CNN)为目标算法模型,并建立算法模型的训练数据集及Label规则,采用分裂信息增益度量方法对数据进行降维处理,建立CNN评估模型,并进行了验证分析。结果表明,CNN模型对卫星网络协调态势评估问题测试的正确率高达80%以上,具有较高的评估效能。随着数据量的增多,CNN评估效果逐步提升,是一种在卫星网络协调态势分析、资源储备的有效评估方法。     

Gabor-CNN for object detection based on small samples

Object detection models based on convolutional neural networks (CNN) have achieved state-of-the-art performance by heavily rely on large-scale training samples. They are insufficient when used in specific applications, such as the detection of military objects, as in these instances, a large number of samples is hard to obtain. In order to solve this problem, this paper proposes the use of Gabor-CNN for object detection based on a small number of samples. First of all, a feature extraction convolution kernel library composed of multi-shape Gabor and color Gabor is constructed, and the optimal Gabor convolution kernel group is obtained by means of training and screening, which is convolved with the input image to obtain feature information of objects with strong auxiliary function. Then, the k-means clustering algorithm is adopted to construct several different sizes of anchor boxes, which improves the quality of the regional proposals. We call this regional proposal process the Gabor-assisted Region Proposal Network (Gabor-assisted RPN). Finally, the Deeply-Utilized Feature Pyramid Network (DU-FPN) method is proposed to strengthen the feature expression of objects in the image. A bottom-up and a top-down feature pyramid is constructed in ResNet-50 and feature information of objects is deeply utilized through the transverse connection and integration of features at various scales. Experimental results show that the method proposed in this paper achieves better results than the state-of-art contrast models on data sets with small samples in terms of accuracy and recall rate, and thus has a strong application prospect.     

深度神经网络指导下的无线覆盖预测算法

为保证新一代移动无线网络能够根据实时覆盖情况动态地调节小区天线参数,需要实现高效且准确的无线覆盖预测。传统的求解方法通过精确的场强预测判断天线参数的优劣,虽然精度很高但需要大量的计算资源,无法满足5G和后5G移动网络通过实时覆盖预测进行射频参数动态调整的实际需求。现采用基于深度神经网络的算法对给定天线参数的覆盖效果进行预测,以取代对目标区域的精确场强预测。数值结果表明:该方法能够在保持计算准确性的同时显著减少计算量,为5G动态网络规划提供基础性参考数据。     

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.