《连续系统建模》的计算机辅助学习与考核系统

本文介绍了一个用于《连续系统建模》学习与考核的计算机辅助教学课件的功能和设计原理,重点介绍了系统动力学模型图的知识表达和建模行为的有效性度量的方法。     

基于ICA的多姿态人脸表示

将独立成分分析(ICA)应用于多姿态人脸识别。对比分析了ICA和主成分分析(PCA)两种人脸识别方法的差异,并重点研究了多姿态人脸的独立成分(IC)表示。在基于权向量幅值的方法基础上,引入了基于比例因子的IC核选择的新方法。实验表明,新方法有利于提高识别的准确率和识别的效率。     

弹道目标微多普勒特性基于逆Radon变换的稀疏表示

作为识别空间弹道目标的有效方法,微多普勒特性提取对于雷达系统的时频分辨率提出了很高的要求,因此,要求雷达系统具有更高的采样频率。作为近年来新兴的技术手段,在远低于奈奎斯特采样定理的采样频率下,压缩感知技术可以对具有稀疏特性的信号实现高精度还原。对空间弹道目标时频分布进行逆Radon变换,在变换后的IRT域内获得时频分布的稀疏表示,从而可以借助压缩感知技术有效降低采样频率的要求。     

关于半鞅的可料表示性

利用鞅空间H1的泛函表示定理、泛函分析中的Hahn-Banach定理、半鞅向量随机积分的Girsanov定理,获得了半鞅可料表示性的特征。由于使用的是半鞅的向量随机积分,它推广了经典的结论。     

采用区分性幅相联合字典学习的低截获概率信号分离方法

为解决采用字典学习的信号分离方法存在的相位信息缺失和子字典交叉表示问题，提出一种区分性幅相联合字典学习方法。该方法针对相位信息缺失问题，构建了幅相联合字典模型；针对混合信号在联合字典上投影时存在的交叉表示问题，基于区分性字典学习思想提出在字典学习过程目标函数中加入交叉表示抑制项。仿真结果表明：幅相联合字典能够充分表示典型低截获概率信号的幅相信息，交叉表示抑制项能有效抑制信号间的交叉表示，算法具有良好的分离性能。     

Minimal LST representations of MAP(n)s: Moment fittings and queueing approximations

A Markovian arrival process of order n, MAP(n), is typically described by two n × n transition rate matrices in terms of rate parameters. While it is straightforward and intuitive, the Markovian representation is redundant since the minimal number of parameters is n² for non‐redundant MAP(n). It is well known that the redundancy complicates exact moment fittings. In this article, we present a minimal and unique Laplace‐Stieltjes transform (LST) representations for MAP(n)s. Even though the LST coefficients vector itself is not a minimal representation, we show that the joint LST of stationary intervals can be represented with the minimum number of parameters. We also propose another minimal representation for MAP(3)s based on coefficients of the characteristic polynomial equations of the two transition rate matrices. An exact moment fitting procedure is presented for MAP(3)s based on two proposed minimal representations. We also discuss how MAP(3)/G/1 departure process can be approximated as a MAP(3). A simple tandem queueing network example is presented to show that the MAP(3) performs better than the MAP(2) in queueing approximations especially under moderate traffic intensities. © 2016 Wiley Periodicals, Inc. Naval Research Logistics 63: 549–561, 2016     

L1-analysis稀疏重构在阵列信号恢复及波达角估计中的应用

通过适当的空域稀疏化构造了可对阵列接收信号进行冗余稀疏表示的阵列流形矩阵,建立了相应的L1-analysis稀疏重构模型用于恢复阵列接收信号,重点证明了该流形矩阵是满足L1-analysis 稀疏重构条件的紧框架,从理论上保证了将L1-analysis 稀疏重构用于阵列接收信号恢复及波达角估计问题的合理性,并推导出信号恢复误差的理论上界。利用在微波暗室环境中采集的实测数据,结合MUSIC算法进行实验验证,结果表明基于L1-analysis 稀疏重构的信号恢复对提高低信噪比环境下的波达角估计性能是有效的。     

Modeling of unsupervised knowledge graph of events based on mutual information among neighbor domains and sparse representation

Text event mining, as an indispensable method of text mining processing, has attracted the extensive attention of researchers. A modeling method for knowledge graph of events based on mutual information among neighbor domains and sparse representation is proposed in this paper, i.e. UKGE-MS. Specifically, UKGE-MS can improve the existing text mining technology's ability of understanding and discovering high-dimensional unmarked information, and solves the problems of traditional unsupervised feature selection methods, which only focus on selecting features from a global perspective and ignoring the impact of local connection of samples. Firstly, considering the influence of local information of samples in feature correlation evaluation, a feature clustering algorithm based on average neighborhood mutual information is proposed, and the feature clusters with certain event correlation are obtained; Secondly, an unsupervised feature selection method based on the high-order correlation of multi-dimensional statistical data is designed by combining the dimension reduction advantage of local linear embedding algorithm and the feature selection ability of sparse representation, so as to enhance the generalization ability of the selected feature items. Finally, the events knowledge graph is constructed by means of sparse representation and l₁ norm. Extensive experiments are carried out on five real datasets and synthetic datasets, and the UKGE-MS are compared with five corresponding algorithms. The experimental results show that UKGE-MS is better than the traditional method in event clustering and feature selection, and has some advantages over other methods in text event recognition and discovery.     

SAR微动目标的稀疏贝叶斯成像方法

SAR微动信息能够反映出目标的属性信息,其微动图像可作为雷达目标识别的一种重要手段。基于SAR微动目标回波的稀疏特性,建立了在过完备词典下的稀疏表示模型,提出一种新的稀疏贝叶斯重构方法——方差成分扩张压缩,该方法仅赋予有重要意义的信号元素不同的方差分量,拥有更少的参数。仿真结果表明,方差成分扩张压缩方法能较精确地估计出SAR目标微动参数,同时能够获得低信噪比条件下较好的微动目标像。     

某型导弹智能维修训练系统设计

智能维修训练系统是智能教学训练系统在故障维修领域的应用。以某型导弹武器系统为对象阐述了智能维修训练系统的设计和实现,研究了该系统的总体结构以及知识表示、学生模型、推理机制、仿真环境的实现方法。