Exactly satisfying initial conditions neural network models for numerical treatment of first Painlevé equation

In this paper, novel computing approach using three different models of feed-forward artificial neural networks (ANNs) are presented for the solution of initial value problem (IVP) based on first Painlevé equation. These mathematical models of ANNs are developed in an unsupervised manner with capability to satisfy the initial conditions exactly using log-sigmoid, radial basis and tan-sigmoid transfer functions in hidden layers to approximate the solution of the problem. The training of design parameters in each model is performed with sequential quadratic programming technique. The accuracy, convergence and effectiveness of the proposed schemes are evaluated on the basis of the results of statistical analyses through sufficient large number of independent runs with different number of neurons in each model as well. The comparisons of these results of proposed schemes with standard numerical and analytical solutions validate the correctness of the design models.     

Spatio-temporal evolution of the deformation around the Rio-Patras fault (Greece) observed by synthetic aperture radar interferometry from 1993 to 2017

We analysed the ground deformation across two blocks defined by the Rio-Patras fault from 1993 to 2017 using multi-temporal Synthetic Aperture Radar Interferometry (InSAR) techniques. Our main objective was to contribute to the assessment of seismic hazard near the large city of Patras. Multiple data-sets were used, each one covering different temporal periods. Descending and ascending acquisitions, providing different viewing geometries contribute to fully determine the ground displacement in 3D. The data-sets used are from the European Space Agency’s (ESA) European Remote Sensing (ERS), Environmental Satellite (ENVISAT) and SENTINEL-1 as well as German Aerospace Center (DLR) ’s TERRASAR-X missions. Considering ESA’s missions covering both acquisition geometries and long periods, the southern block, showing lack of a sufficient number of scatterers does not allow the displacement characterization. In contrary, the northern block is characterized by a high number of scatterers having values of maximum likehood ranging from ?3.5 to ?4.3 mm year^?1 for ascending geometry and from ?1.6 to ?2.7 mm year^?1 for the descending one. The fact that both geometries show negative values of displacements are consistent with downlift movement and at the same time the quantitative differentiation probably indicates an horizontal component as well.     

Learning fuzzy controllers in mobile robotics with embedded preprocessing

The automatic design of controllers for mobile robots usually requires two stages. In the first stage, sensorial data are preprocessed or transformed into high level and meaningful values of variables which are usually defined from expert knowledge. In the second stage, a machine learning technique is applied to obtain a controller that maps these high level variables to the control commands that are actually sent to the robot. This paper describes an algorithm that is able to embed the preprocessing stage into the learning stage in order to get controllers directly starting from sensorial raw data with no expert knowledge involved. Due to the high dimensionality of the sensorial data, this approach uses Quantified Fuzzy Rules (QFRs), that are able to transform low-level input variables into high-level input variables, reducing the dimensionality through summarization. The proposed learning algorithm, called Iterative Quantified Fuzzy Rule Learning (IQFRL), is based on genetic programming. IQFRL is able to learn rules with different structures, and can manage linguistic variables with multiple granularities. The algorithm has been tested with the implementation of the wall-following behavior both in several realistic simulated environments with different complexity and on a Pioneer 3-AT robot in two real environments. Results have been compared with several well-known learning algorithms combined with different data preprocessing techniques, showing that IQFRL exhibits a better and statistically significant performance. Moreover, three real world applications for which IQFRL plays a central role are also presented: path and object tracking with static and moving obstacles avoidance.     

The quantification of remote sensing

The paper firstly defined the remote sensing information quantification, analyzed the necessity of developing remote sensing quantification, figured out the application guidelines requirement, and pointed out the importance of quantification research. Then taking the remote sensing application research of CBERS-02 data quantification as the example, the paper described the whole quantification system of “remotely sensed digital signal-radiation information-field parameter inversion”. Finally the paper gave the prospect for the development trend of the quantitative remote sensing.     

遥感数据时空融合技术在农作物监测中的适应性研究

受卫星回访周期及云的影响,大范围研究区同一时期的Landsat卫星数据很难获取,因而国内外学者提出了遥感影像时空融合技术。以石河子为实验区,利用STARFM(Spatial and Temporal Adaptive Reflectance Fusion Model)模型融合生成了高时空分辨率TM影像,对不同作物类型真实反射率与融合影像反射率作相关性分析,分析了遥感数据时空融合技术在新疆农作物监测中的适用性。结果表明:利用STARFM模型模拟得到的融合影像与真实影像间的相关性较高,但当地物类型发生变化时,融合影像与真实影像间将存在明显的差异。地物类型变化作物融合影像反射率与真实影像反射率间的相关性较小。     

松材线虫病害高光谱时序与敏感特征研究

采用高光谱仪ASD FieldSpec Pro FR,连续观测了健康和发病马尾松针叶的时序高光谱,分析了松材线虫病害光谱的时序特征、敏感时期和敏感特征。结果表明:与健康马尾松相比,病害马尾松时序光谱差异较大;病害首先造成红边区域内光谱反射率减低,然后再出现红边蓝移的2阶段光谱变化规律;感染松材线虫的马尾松9月初已经出现了病态植被典型的光谱特征;近红外平台内最大的一阶微分值、红边内一阶微分的总和(SDr)与蓝边内一阶微分的总和(SDb)的比值等是指示病害发生的显著性高光谱特征。     

基于遥感变化检测的石漠化信息自动提取

滇黔桂地区被划定为限制开发区后,石漠化的研究变得越来越热,而信息提取是这些研究的重要内容。当前石漠化信息提取主要依据静态指标进行,鉴于静态方法的不足,在动态机理剖析的基础上,综合考虑石漠化的静态景观及其动态属性,以贵州和云南交界区域为实验区,1992年和2001年两个时相的TM/ETM+影像为数据源,研究遥感变化检测方法在石漠化信息自动提取中的应用。在几何校正和辐射校正的基础上对两个时相的影像实施差值变化检测,将实验区分为变化区和无变化区两类,根据石漠化机理进一步将变化区分为石漠化区和逆石漠化区,完成石漠化信息识别,经验证Kappa系数为0.854。结果表明:遥感变化检测方法对石漠化有较好的识别效率和精度,能够为石漠化的综合防治提供科学依据。     

波谱匹配支持的遥感专题地物自适应提取

为贴合地物表现的多样性和复杂性,提出一种波谱匹配支持下的遥感影像专题地物自适应提取方法,经过专题地物端元选取、波谱匹配、影像自动分割、"整体-局部"的空间转换,以及局部针对性、精细化地迭代逼近等一系列相互衔接的算法,全面、准确地提取遥感影像上的专题地物。通过在ETM+影像上水体和裸地的提取实验,并与最大似然法和SVM分类结果比较,证明了该方法对多样性专题地物提取的有效性和普适性。     

全链路成像光谱仪信噪比仿真

研究成像光谱仪优化问题,由于光谱成像受到环境噪声影响,传感器精度达不到要求,传统信噪比优化仿真方法,通常只考虑传感器本身的特性,没有综合考虑地物的光谱特性、辐射传输对其影响,导致传感器信噪比很难满足要求。为消除噪声提出了全链路成像光谱仪信噪比仿真方法,以叶面积指数反演应用为背景,从地面植被反射率信号出发,考虑大气辐射传输和传感器能量转换过程,建立了全链路成像光谱仪信噪比仿真模型,并通过具体实例进行验证和分析。理论分析和仿真结果表明:方法是对成像光谱仪信噪比仿真的一种全新而有益的尝试,具有很好的扩展性,传感器的研制设计提高性能指标,并缩短研制周期,为设计提供了参考。     

面向Internet的分布式遥感影像切割算法

为了实现遥感影像的网络快速发布,提出了一种高效的影像金字塔模型的构建算法,影像的切割与重采样均在内存中运算完成,尽可能地减少I/O操作,从而提高其执行效率。提出了面向Internet的分布式遥感影像的切割算法,并给出了基于B/S架构和基于C/S架构的两种实现方式。为了保证算法的效率与分布式结构,利用C++与Java联合编程进行实现。通过实例对算法性能进行测试,证明了算法的可操作性、实用性和高效性。