One-to-one disjoint path covers on multi-dimensional tori

The multi-dimensional torus is one of the most popular underlying topologies for massively parallel systems. In this study, we consider a non-bipartite n-dimensional torus where n≥2 and prove that for 1≤m≤2n, m vertex disjoint paths exist that cover all vertices between any two distinct vertices. In other words, we construct the one-to-one m-disjoint path cover of a non-bipartite torus for any m where 1≤m≤2n.     

An anticipation mechanism for the shortest path problem based on Physarum polycephalum

In this paper, we put forward an anticipation mechanism for the existing Physarum-inspired shortest path finding method. The Physarum-based shortest path finding model can be implemented by an iterative algorithm and has wide applications in many fundamental network optimization problems. In this paper, we mainly focus on the Physarum-inspired shortest path tree model. Normally, we stop the program when the difference between two consecutive iterations is less than a predefined threshold. However, we do not know how to set the specific value for the threshold variable. In order to find out the optimal solution, we need to set the threshold as a very small number. This in turn will consume a lot of time. From this point of view, this algorithm lacks an efficient and reliable mechanism to judge when the optimal solution will be found. In this paper, we introduce an anticipation mechanism to address this issue. Numerical examples are used to demonstrate its reliability and efficiency.     

Optimal boundary control of coupled parabolic PDE–ODE systems using infinite-dimensional representation

The optimal boundary control problem is studied for coupled parabolic PDE–ODE systems. The linear quadratic method is used and exploits an infinite-dimensional state-space representation of the coupled PDE–ODE system. Linearization of the nonlinear system is established around a steady-state profile. Using appropriate state transformations, the linearized system has been formulated as a well-posed infinite-dimensional system with bounded input and output operators. It has been shown that the resulting system is a Riesz spectral system. The linear quadratic control problem has been solved using the corresponding Riccati equation and the solution of the corresponding eigenvalue problem. The results were applied to the case study of a catalytic cracking reactor with catalyst deactivation. Numerical simulations are performed to illustrate the performance of the proposed controller.     

基于Catmull-Rom插值算法光栅分辨率测试系统改进

为了减小探测器采集及软件处理导致的系统误差,提高光栅分辨率检测精度,利用半宽度法设计了一套满足李特洛条件的阶梯光栅分辨率检测系统。搭建了系统的光路,介绍了提高分辨率的方法,重点分析了探测器像元尺寸对系统分辨率测试精度的影响,提出了在LabVIEW软件中如何根据离散光谱信号并利用Catmull-Rom插值构造出连续光谱,提高半宽度法检测的精度。实验结果表明,在高分辨率测试系统中,通过软件算法对离散信号进行拟合分析,能有效的解决由像元尺寸造成的系统误差。     

二维圆环结构中弹性波传播的谱单元分析

为研究弹性波在结构中的波场特征,推导建立一种任意四边形二维谱单元,将其应用于二维圆环结构中的波传播行为模拟.以矩形平板结构中弹性导波传播分析为例,通过与传统有限元分析结果对比,验证所建立谱单元的有效性.有裂纹和无裂纹二维圆环结构谱单元模拟结果表明:弹性波在圆环结构中传播会发生频散;圆环结构表面的裂纹对瑞利波的传播影响最大;根据其反射波包位置可以确定损伤位置.     

谐波分析光谱角制图高光谱影像分类

目的 针对光谱角制图(SAM)分类算法对高光谱像元光谱曲线的局部特征和其辐射强度不敏感,而且易受噪声和维数灾难影响,致使分类效率低和精度较差等缺陷,将谐波分析(HA)技术引入到SAM高光谱影像分类中,提出一种基于谐波分析的光谱角制图(HA-SAM)高光谱影像分类算法.方法 利用HA技术将高光谱影像从光谱维变换到能量谱特征维空间,并提取低次谐波分量及特征系数(谐波余项、相位和振幅),用特征系数组成的向量代替光谱向量,对高光谱影像进行SAM分类.结果 将SAM和HA-SAM同时应用于EO-1卫星的Hyperion高光谱影像分类,通过对比和分析,验证了HA-SAM的优越性,再选择AVIRIS(airborne visible infrared imaging spectrometer)高光谱影像对HA-SAM进行验证,结果表明该算法具有较强的普适性.结论 HA-SAM提高了传统SAM高光谱影像分类的效率和精度,而且适用性较强具有良好的应用前景.     

空间欠采样太赫兹时域光谱成像方法

文章针对传统太赫兹时域光谱成像技术存在的扫描时间长以及数据存储量大等问题,提出了一种基于压缩感知理论的空间欠采样太赫兹时域光谱成像方法。首先通过扫描电机获得目标非等间隔欠采样信号,然后利用压缩感知方法来重构缺失像素点的太赫兹信息。实验结果显示,当压缩比为0.5时,所重构的太赫兹信号与全采样条件下的信号相关性可达99.95%。通过对压缩重建图像的显示分析,时域图像中的缓变区域和频谱成像中的低频信号恢复效果较好。该方法为快速太赫兹光谱成像提供了一种有效的技术手段。     

Mutual spectral residual approach for multifocus image fusion

Multifocus image fusion is the process of obtaining a single image from multiple partially focused images such that the newly formed image consists of the well-defined information extracted from each source image. This paper proposes the use of saliency of the source images based on Mutual Spectral Residual. Spectral Residual brings out the unique/salient features of an image in frequency domain. The idea of proposed mutual spectral residual is to emphasize the relative unique features of a source image with respect to the other source images. The relative unique features are utilized to form saliency maps for each source image. These saliency maps can clearly indicate the focused and defocused parts of an image. Based on the saliency maps obtained, the image fusion takes place in spatial domain. Visual inspection and quantitative evaluation of the fused images obtained by the proposed method, using different evaluation metrics, demonstrate its effectiveness over several existing image fusion methods.     

基于谱残差和多分辨率分析的显著目标检测

根据人类视觉系统的特点,提出一种融合谱残差和多分辨率分析的显著目标检测方法。该方法通过在不同尺度上计算图像的亮度、颜色以及方向特征的谱残差,构建多分辨率显著性图谱序列,然后用线性插值方法将不同分辨率的特征显著图叠加得到3个特征显著图,再利用k均值聚类算法将每个特征显著图聚为两类,选择聚类中心距离最大的特征显著图作为最终的显著图,最后经过动态阈值处理获得图像的显著目标区域。基于自然图像的显著目标检测实验结果表明,该方法具有较强的稳定性和实用性,得到较为满意的检测结果。     

基于谱聚类与混合模型的SAR图像多尺度分割

针对谱聚类方法应用于合成孔径雷达（SAR）图像分割时Laplace矩阵的特征值和特征向量难以计算的问题,结合SAR图像在多个尺度的统计信息,给出了一个包含顶点凝聚、初始分割和分割细化3个步骤的SAR图像多尺度分割方法。首先,用一个顶点数不断减少的凝聚图序列来逼近从SAR图像得到的图;然后应用谱聚类方法对最粗尺度的凝聚图进行分割得到初始分割结果;最后根据SAR图像的统计性质,利用基于混合模型估计的分类后验概率将初始分割结果逐尺度进行细化得到SAR图像的最终分割。实验结果表明了方法的有效性。