An evaluation of Guided Regularized Random Forest for classification and regression tasks in remote sensing

New Earth observation missions and technologies are delivering large amounts of data. Processing this data requires developing and evaluating novel dimensionality reduction approaches to identify the most informative features for classification and regression tasks. Here we present an exhaustive evaluation of Guided Regularized Random Forest (GRRF), a feature selection method based on Random Forest. GRRF does not require fixing a priori the number of features to be selected or setting a threshold of the feature importance. Moreover, the use of regularization ensures that features selected by GRRF are non-redundant and representative. Our experiments based on various kinds of remote sensing images, show that GRRF selected features provides similar results to those obtained when using all the available features. However, the comparison between GRRF and standard random forest features shows substantial differences: in classification, the mean overall accuracy increases by almost 6% and, in regression, the decrease in RMSE almost reaches 2%. These results demonstrate the potential of GRRF for remote sensing image classification and regression. Especially in the context of increasingly large geodatabases that challenge the application of traditional methods.     

岩体三维节点偶对分析及其应用

本文讨论了节点偶对分析的三维扩展。节点偶对分析是针对摩擦滑动节理单元的约束边界进行的序列矢量判定。在三维节理单元的分析中,几何约束和相应的力学判据极为复杂,采用节点偶对等效结合力方法才能迎刃而解。文中对三维转向节理模型的分析得到合理的结果,它表明本文所提出的方法可成功地应用于节理岩体的有限元分析。     

非线性洋面温度反演

本文从辐射方程出发，简述洋面温度与亮度温度之间的非线性关系，进行非线性洋面温度反演的方案设计，用正演算法 计算出非线性洋面温度反演公式的回归系数，对样进行检验。     

Design and Strength Analysis of A Spherical Connector for Lifting Subsystem in Deep Sea Mining System

1 .IntroductionThe lifting systemis composed of pipes andtheir connectors .It is not onlythe lifting channel formanganese nodule betweenthe miningship andintermediate bin,but alsothe supporting massfor deepsea miningequipment and cables .Sothe reliability…     

Elasto-Plastic Analysis of Tubular Joints of Offshore Platforms by Finite Element Method

The plastic node method is reformulated by the variational principle and is applied to elasto-plastic finite element analysis of tubular joints, eventually including the effect of internal and external gussets, stiffener rings, etc., if necessary. Four different joints are studied here in detail for the elasto-plastic behavior, the strain at the hot spot, the strain concentration factor around the intersection line, and the propagation of the plastic region with loading up to collapse in order to determine the ultimate strength, safety factor, and development of the plastic field. The present results are in good agreement with the experimental results.     

神经网络反演散射计风场算法的研究

建立了一个神经网络反演卫星散射计海面风场的B-P算法,给出了一个神经网络反演风场的模型,并利用该反演算法和模型对实际卫星散射计数据进行了海面风场反演试验,对风向的多解性利用圆中数滤波方法进行排除.对神经网络训练和检验数据集分别采用ERS-1/2散射计数据和欧洲中期天气预报(ECMWF)提供的风场作为配准点数据.把反演的风速和风向与CMCD4和ECMWF的风场作了比较,它们吻合得比较好;研究表明神经网络反演海面风场是可行和高效的.     

Hilbert变换在海浪波高与周期联合分布函数中的应用

Longuet-Higgins(1983)[1]导出了波高与周期的联合分布函数,此分布函数虽然与实际数据符合良好,但存在很大的缺陷,如:由此分布函数得出的波高分布为形式较为复杂的非Rayleigh分布,很难应用于工程计算中。孙孚(1988a)[2]应用射线理论导出了一种波高与周期联合分布,虽然弥补了Longuet-Higgins的一些缺陷,但推导过程过于复杂。本文在窄谱假定下通过应用Hilbert变换方法得出新的分布函数并与前两者比较,表明Hilbert变换的方法不但简便,而且完全克服Longuet-Higgins的不足,可以方便的应用于工程计算中。本文也为Hilbert变换的方法在工程中的应用提供了理论依据。     

基于分块分形编码的多姿态、表情人脸图像检索

利用图像分形编码中定义域块和最小均方误差一一对应的特点，提出了1种基于分形编码的多姿态、表情的人脸图像检索方法。该方法将待检索图像分割为相同大小的值域块，然后将每一值域块按给定的定义域块进行分形编码，得到最小均方误差，计算该最小均方误差与图像库中最小均方误差的欧氏距离。将待检索图像所有值域块的欧氏距离求平均，此平均欧氏距离较小的几幅图像即为检索出的图像。实验证明该方法能够准确地检索出图像库中存储的同一人的不同姿态、表情的图像。     

盐碱水NaCl浓度和碱度对银鲫(Carassius auratus gibelio)幼鱼毒性的初步研究

通过对银鲫(Carassiusauratusgibelio)幼鱼(L=3.56±0.28cm)的NaCl浓度(pH=8.80±0.10)及碱度(pH=8.84±0.26)的急性毒性试验，用概率单位法求得其24，48，96h的半致死浓度(LC50值)NaCl浓度分别为11.53、10.77、8.58g/L；碱度分别为98.74、79.49、64.19mmol/L。在此基础上采用水生毒理联合效应相加指数法进行了氯化钠与碳酸氢钠浓度的联合毒性实验(浓度=11)，结果在96h内二者的关系全部为协同作用,且其协同性逐渐减弱并趋向于相加作用。     

浪流作用下系泊船舶撞击力和系缆力试验研究

以某25万吨矿石码头工程为例,分别进行了单流、单浪和浪流共同作用下,系泊船舶撞击力和系缆力试验。研究了不同水位、不同船舶载度、不同浪流夹角,单流、单浪和浪流共同作用时对船舶撞击力和系缆力的影响。分析了该码头工程护舷和缆绳的布置情况,为工程设计提供了依据。