结合遗传算法的LVQ神经网络在声学底质分类中的应用   总被引：9，自引：0，他引：9       下载免费PDF全文

唐秋华  刘保华  陈永奇  周兴华  丁继胜 《地球物理学报》2007,50(1):313-319

学习向量量化（Learning Vector Quantization，LVQ）神经网络在声学底质分类中具有广泛应用. 常用的LVQ神经网络存在神经元未被充分利用以及算法对初值敏感的问题，影响底质分类精度. 本文提出采用遗传算法（Genetic Algorithms，GA）优化神经网络的初始值，将GA与LVQ神经网络结合起来，迅速得到最佳的神经网络初始权值向量，实现对海底基岩、砾石、砂、细砂以及泥等底质类型的快速、准确识别. 将其应用于青岛胶州湾海区底质分类识别研究中，通过与标准的LVQ神经网络的分类结果进行比较表明，该方法在分类速度以及精度上都有了较大提高.  相似文献   

三维地震数据可视化原理及方法   总被引：5，自引：0，他引：5  

张二华  高林  马仁安  杨静宇 《CT理论与应用研究》2007,16(3):20-28

可视化是实现三维地震数据真三维解释的有效方法,本文介绍了三维地震数据可视化的基本原理,论述了用光线投射算法实现可视化的主要步骤,详细推导了合成可视化图像的计算公式,分析了阻光度曲线的物理意义及对可视化图像的调节作用,并用两个实际三维地震数据进行了试验.结果表明该方法能够由原始三维地震数据直接对地质体进行成像,能将分散的、孤立的信息互相联系起来,揭示隐藏在数据中的地质现象和规律.  相似文献   

A Task-Based Ontology Approach to Automate Geospatial Data Retrieval   总被引：1，自引：0，他引：1  

Nancy Wiegand  Cassandra García 《Transactions in GIS》2007,11(3):355-376

This paper presents a task‐based and Semantic Web approach to find geospatial data. The purpose of the project is to improve data discovery and facilitate automatic retrieval of data sources. The work presented here helps create the beginnings of a Geospatial Semantic Web. The intent is to create a system that provides appropriate results to application users who search for data when facing tasks such as emergency response or planning activities. In our task‐based system, we formalize the relationships between types of tasks, including emergency response, and types of data sources needed for those tasks. Domain knowledge, including criteria describing data sources, is recorded in an ontology language. With the ontology, reasoning can be done to infer various types of information including which data sources meet specific criteria for use in particular tasks. The vision presented here is that in an emergency, for example, a user accesses a Web‐based application and selects the type of emergency and the geographic area. The application then returns the types and locations (URLs) of the specific geospatial data needed. We explore the abilities and limitations of the OWL Web Ontology Language along with other Semantic Web technologies for this purpose.  相似文献   

Two-dimensional maps in multi-dimensional worlds: A case of community-based mapping in Northern Thailand     

Robin Roth 《Geoforum》2007,38(1):49-59

Community-based mapping has become a necessary tool for development work worldwide - its adoption is near hegemonic. Mapping community land, however, can have unforeseen consequences in part due to its tendency to render what are complex configurations of social-ecological relationships into two-dimensional form. I argue that one of the key limitations to commonly practiced community-based mapping is the assumption that the spatial organization of resource use and management is an abstract entity that can be mapped independent of the social relations that produce it. This paper uses a case study from Northern Thailand to show how mapping techniques that fix and simplify fluid and complex associations can inadvertently prescribe changes to how residents manage their land, effectively becoming not only a tool for securing land tenure but also a tool for the spatial re-organization of land-use and management.  相似文献   

发展我国知识经济的理论思考     

杨孟著 《广东海洋大学学报》2002,22(5):26-30

发展我国知识经济 ,必须以邓小平“科学技术是第一生产力”思想为理论基石 ,符合社会主义市场经济特征的激励知识创新活动的“经济组织”为基本前提。在此基础上 ,构建起符合我国国情的由相互联系、制约和影响的九大要素为基本框架的知识创新机制 ,是当前社会经济环境条件下的最优制度安排。  相似文献   

空间分析方法、应用模型与GIS的关系   总被引：4，自引：0，他引：4  

马天智  张燕妮 《湖南地质》2003,22(1):70-72

首先阐述了空间分析和应用模型的基本概念，进而从地理信息处理系统的功能入手，分析了空间分析、应用模型和GIS的关系，最后指出加强应用模型与GIS的结合以及增强GIS的基本空间分析功能是增强GIS整体功能的二个最有效的方法．  相似文献   

不同浓度Li2SO4水溶液结构的X射线衍射研究          下载免费PDF全文

房艳  房春晖  高世扬 《盐湖研究》2003,11(2)

用θ～ 2θ型粉末衍射仪反射法精确测量了不同浓度的Li2 SO4水溶液的衍射数据 ,通过数据处理给出了溶液的结构函数和径向分布函数 ,由几何结构模型的最小二乘法精修 ,得到了溶液中阳离子和阴离子第一、二水合层的结构参数。  相似文献   

基于正交投影和广义投影(POCS)算法的研究进展     

姜明  张兆田 《CT理论与应用研究》2003,12(1):51-55

目的 在于提请有关读者关注近年来关于图像重建的凸集投影算法的进展，这一重要的方法及应用。方法 主要讨论了基于正交投影和广义投影的算法。对基于正交投影的算法，并讨论了一般形式的加权松驰格式，这包含了分块格式和同时格式。并以三个定理报道有关的算法收敛性结果。结果 分别包含了相容和不相容条件和弱强收敛下的结果。对基于广义投影的算法，有关的基本概念和例子，基本算法的收敛性结果。结论 报道最近关于引入松弛系数的工作和在CT图像重建中的应用。  相似文献   

大地电磁自适应正则化反演算法   总被引：36，自引：11，他引：36       下载免费PDF全文

陈小斌  赵国泽  汤吉  詹艳  王继军 《地球物理学报》2005,48(4):937-946

针对大地电磁正则化反演中正则化因子的选取困难问题提出了自适应正则化反演算法（Adaptive Regularized Inversion Algorithm, ARIA）. 在该算法中， ①提出了一种新的数据方差处理方法：数据方差规范化，使得数据方差的大小只对数据的拟合发生影响，不对数据目标函数和模型约束目标函数的权重产生影响，从而减少了正则化因子取值的影响因素；②提出了粗糙度核矩阵的概念，并给出了由基本结构插值基函数计算粗糙度核矩阵的公式，使得模型目标函数的构建更为简便、直接；③根据数据目标函数、模型约束目标函数和正则化因子之间的关系，提出了两种正则化因子自适应调节方法. 本文详细阐述了最平缓模型约束下的大地电磁一维连续介质反演的ARIA实现，以几个算例的分析比较来说明ARIA的有效性.  相似文献   

Space-time mapping of soil salinity using probabilistic bayesian maximum entropy     

A. Douaik  M. van Meirvenne  T. Tóth  M. Serre 《Stochastic Environmental Research and Risk Assessment (SERRA)》2004,18(4):219-227

The mapping of saline soils is the first task before any reclamation effort. Reclamation is based on the knowledge of soil salinity in space and how it evolves with time. Soil salinity is traditionally determined by soil sampling and laboratory analysis. Recently, it became possible to complement these hard data with soft secondary data made available using field sensors like electrode probes. In this study, we had two data sets. The first includes measurements of field salinity (EC_a) at 413 locations and 19 time instants. The second, which is a subset of the first (13 to 20 locations), contains, in addition to EC_a, salinity determined in the laboratory (EC_2.5). Based on a procedure of cross-validation, we compared the prediction performance in the space-time domain of 3 methods: kriging using either only hard data (HK) or hard and mid interval soft data (HMIK), and Bayesian maximum entropy (BME) using probabilistic soft data. We found that BME was less biased, more accurate and giving estimates, which were better correlated with the observed values than the two kriging techniques. In addition, BME allowed one to delineate with better detail saline from non-saline areas.  相似文献