网络中心战及其对装备精确保障的几点启示

介绍了网络中心战的产生背景及发展历史,研究归纳了网络中心战的概念及内涵,分析了网络中心战原理,探讨了网络中心战对实现装备精确保障的一些启示,提出了我军在实现装备精确保障过程中借鉴网络中心战理论的构想及应注意的问题.     

Approximating nondominated sets in continuous multiobjective optimization problems

Many important problems in Operations Research and Statistics require the computation of nondominated (or Pareto or efficient) sets. This task may be currently undertaken efficiently for discrete sets of alternatives or for continuous sets under special and fairly tight structural conditions. Under more general continuous settings, parametric characterisations of the nondominated set, for example through convex combinations of the objective functions or ε‐constrained problems, or discretizations‐based approaches, pose several problems. In this paper, the lack of a general approach to approximate the nondominated set in continuous multiobjective problems is addressed. Our simulation‐based procedure only requires to sample from the set of alternatives and check whether an alternative dominates another. Stopping rules, efficient sampling schemes, and procedures to check for dominance are proposed. A continuous approximation to the nondominated set is obtained by fitting a surface through the points of a discrete approximation, using a local (robust) regression method. Other actions like clustering and projecting points onto the frontier are required in nonconvex feasible regions and nonconnected Pareto sets. In a sense, our method may be seen as an evolutionary algorithm with a variable population size. © 2005 Wiley Periodicals, Inc. Naval Research Logistics, 2005.     

一种能量高效和均衡的无线传感器网络分簇数据融合算法

在无线传感器网络中,如果传感器节点之间的能耗不均衡,一些能耗进度较快的节点会过快失效,继而导致网络过早无法正常工作。为了解决分簇无线传感器网络在数据收集过程中所存在的节点之间能耗不均衡问题,提出了一种新的分簇数据融合算法。该算法将网络划分为大小不等的栅格,并根据剩余能量使簇首分别在每个栅格的节点中轮转。簇首消耗的能量越多,其所在的栅格也越大,栅格内有更多节点参与簇首的轮换以分担能量负载。通过该方式,算法能够提高节点的能耗均衡程度。另外,考虑到无线传感器网络的能量受限,算法还采取了一系列措施以节约能量。仿真实验结果表明,算法在能量使用效率、网络生命周期以及能耗均衡程度三个方面都具有较好的性能。     

Development of cost effective personnel armour through structural hybridization

The objective of the present study is to develop cost effective thermoplastic hybrid laminate using Dyneema® HB50 and Tensylon®HSBD 30A through structural hybridization method. Laminates having 20 mm thickness were fabricated and subjected to 7.62 × 39 mm mild steel core projectile with an impact velocity of 730 ± 10 ms⁻¹. Parameters such as energy absorption, back face deformation and rate of back face deformation were measured as a function of hybridization ratio. It was observed that hybrid laminate with 50:50 ratio (w/w) of Tensylon® and Dyneema® with Tensylon® as front face showed 200% more energy absorption when compared to 100% Tensylon® laminate and showed equal energy absorption as that of expensive 100% Dyneema® laminate. Moreover, hybrid laminate with TD50:50 ratio showed 40% lower in terms of final back face deformation than Dyneema® laminate. Rate of back face deformation was also found to be slow for hybrid laminate as compared to Dyneema® laminate. Dynamic mechanical analysis showed that, Tensylon® laminate has got higher stiffness and lower damping factor than Dyneema® and hybrid laminates. The interface between Tensylon® and Dyneema® layers was found to be separating during the penetration process due to the poor interfacial bonding. Failure behaviour of laminates for different hybridization ratios were studied by sectioning the impacted laminates. It was observed that, the Tensylon® laminate has undergone shear cutting of fibers as major failure mode whereas the hybrid laminate showed shear cutting followed by tensile stretching, fiber pull out and delamination. These inputs are highly useful for body armour applications to design cost effective armour with enhanced performance.     

一种应用于超大数据库的人脸识别方法

针对数据库中待识别人脸数目巨大,计算困难的问题,提出了一种基于小波变换和主成分分析的人脸识别方法。该方法首先对数据库中的人脸进行小波变换,然后对小波变换后的图像进行主成分分析提取特征,将特征送入BP神经网络进行训练、识别。经过对比实验,结果表明：该方法可以在保证较高识别率的前提下,大大降低数据维数,从而该方法可以应用于超大数据库的人脸识别。     

判决特征选择的快速人脸识别算法

为了在确保识别精度的条件下提高人脸识别的速度,提出了判决特征选择算法(SVM-DFS).针对多类分类问题,判决特征选择算法根据统计学习理论使用支持向量机来实现特征选择,根据全概率定理把特征选择和多类分类集成到一个统一框架.在UMIST和FERET人脸数据库上的实验表明:SVM-DFS算法可以用来挑选对分类最有用的特征,这些挑选出来的特征具有明显的物理意义.使用判决特征选择方法不但可以加快分类器的响应速度,而且不降低分类器的泛化能力.     

一种新的Gabor小波支持向量机人脸识别算法

提出了一种新的基于Gabor小波特征重组的支持向量机人脸识别方法。该方法首先计算5个尺度和8个方向的Gabor小波变换结果,再把不同人脸中的同一尺度和方向的变换结果进行特征重组,得到40个新特征矩阵,分别利用PCA方法降维去噪,最后构造40个支持向量机分类器并采用选票决策机制决定识别结果。实验结果表明,该方法不仅拓宽了主元分析法中累积方差贡献率可选范围,并在一定程度上解决了核参数选择难的问题,同时取得了理想识别效果。     

星箭分离相对位姿摄影测量方法

提出一种基于视觉的星箭分离相对位姿测量方法。在相机内参数已知的情况下,将相机安装于运载火箭,并在卫星上固连不少于6个合作标志,利用相机对合作标志实时成像;基于单目位姿估计的基本原理,采用高效n点渗透与正交迭代结合的方式解算卫星与火箭之间的相对位姿关系。仿真实验结果、半实物仿真实验结果证明了所提测量方法的可行性和准确性。     

结合多视角学习与一致性表征的人脸伪造检测

现有的人脸伪造检测方法通常在已知域上表现较好,但面临过拟合的风险,在应对未知场景时无法保持良好的检测能力。为解决此问题,提出一种结合多视角学习与一致性表征的人脸伪造检测框架。为捕获更全面的伪造痕迹,将输入图像转换为两种互补视角并采用双流骨干网络进行多视角特征学习。引入一致性度量,以补丁级监督的方式明确约束不同视角输出的局部特征的相似度。为提高检测精度,采用特征分解策略进一步优化伪造特征,减少不相关因素的干扰,并以伪造特征空间的决策作为最终的预测结果。在基准数据集上进行的大量实验表明,所提出的方法优于现有的主流模型,具备良好的跨域泛化能力。     

基于分块的伪Zernike矩归一化的人脸识别方法

以改进的伪Zemike矩相关知识为背景,提出了一种新颖的人脸识别方法。该方法通过将人脸分块,降低了光照条件、人脸表情等外在因素对人脸识别的影响。首先将人脸图像分块并重组矩阵的行和列,然后计算重组后人脸图像的伪Zemike矩,并对其进行归一化处理,最后采用最小邻近分类器进行判别。实验结果表明,该方法对于人脸光照、姿态和表情变化均具有良好的鲁棒性。在前人的研究基础上,进一步探讨了伪Zemike矩在人脸识别方面的应用。