多传感器数据融合技术与应用

研究了多传感器数据融合理论的相关算法及其在多传感器系统中的应用，分析了数据融合技术目前在应用方面存在的问题；针对应用证据理论（D-S方法）解决多传感器条件下的数据融合过程中存在的失效问题，给出了修正合成规则；通过实例对其进行了验证。     

基于网络爬虫的地名数据库维护方法

目前,我国地名数据库建设存在大、中颗粒度地名集中,小颗粒度地名较为缺乏,地名资料陈旧、时效性较低,简称、别名等非标准地名信息和地名的相对位置信息缺失等问题.而地名数据库的更新维护工作主要通过人工测绘手段完成,存在周期长、成本高、效率低等缺点.针对这一问题,本文以现有地名数据库和空间关系词汇为基础,基于Google搜索引...     

基于卷积神经网络的速度大脉冲识别方法研究

含速度大脉冲的强地震动具有复杂的特性,人工提取速度大脉冲特征的方法较繁琐,故利用卷积神经网络（CNN）在图像特征自动提取方面的优势,提出基于卷积神经网络图像识别的速度大脉冲识别方法。基于美国太平洋地震工程研究中心NGA-West1数据库提供的强地震动记录,筛选出6 000条非脉冲记录和91条含有速度大脉冲的强地震动记录。采用在原始记录中加入高斯噪声和过采样的方法,使2类记录样本数量达到均衡。利用本文建立的卷积神经网络模型对2类记录速度时程图进行特征自动提取和分类识别,结果显示测试集准确率为99%,表明本文卷积神经网络模型能够自动提取速度大脉冲特征,进而复现已有结果。将本文方法与传统方法进行了对比,结果表明,对含有多个速度脉冲的强地震动记录的识别,本文方法优于传统方法,具有较高的可靠性、鲁棒性、灵活性。     

顺层斜坡溃屈机制与早期识别研究

本文采用物理机制模型、数值模拟和理论计算相结合,分析研究了顺层斜坡滑移-弯曲变形机制,提出了顺层斜坡产生滑移-弯曲变形的地质和力学条件、临溃状态判别与早期识别标志。研究认为:岩层倾角20是滑移-弯曲变形产生的必要地质条件。斜坡前缘岩层弯曲隆起是临溃状态的早期判识标志。岩层倾角、单层厚度、临界坡长和溃屈深度之间相互制约和影响。岩层倾角越大,越易产生溃屈,且溃屈层数和深度越大;斜坡临界坡长与岩层倾角呈负幂函数变化规律;层间黏结作用产生的共弯效应影响弯曲岩层的整体抗弯刚度,从而制约溃屈深度并对斜坡最终溃屈状态起着决定性作用。该成果对于早期防范和识别地质灾害具有重要价值。     

Classification of rainfall into small- and large-scale events by statistical pattern recognition

Scale properties of daily areal rainfall in south-eastern Norway are investigated, and the events are classified into small- and large-scale events by statistical pattern recognition. The coefficient of variation and the standard deviation, computed from all precipitation gauges for one event, are considered to be mutually independent and are assigned gamma densities. The two statistical parameters form a feature vector which is used as the discriminatory variable in the classification algorithm. Empirical and theoretical semivariograms were fitted to the classified sets of events, and the parameters of the semivariogram (nugget, sill and range) were investigated for each set. Different values for all parameters were found, and the differences in range, describing the scale of the phenomena, were further investigated by the use of cross validation with the MSIE (mean squared interpolation error) criterion. Optimal range of daily small-scale precipitation was found to be 16 km (19 km without nugget effect), and 33 km (70 km without nugget effect) for daily large-scale precipitation. These optimal values for range, however, proved to be of small consequence for the estimated areal precipitation using kriging interpolation. Areal precipitation was computed for catchments of size 50 km² and 1200 km², and insignificant differences in the computed areal precipitation were found when applying the class-specific semivariograms instead of the mean semivariogram calculated from all events regardless of class. However, when areal reduction factors (ARFs) were derived from the analytical expressions of the class-specific semivariograms, considerable differences were found for the ARF curves of the two precipitation types. The difference became more marked for precipitation events of low probability of occurrence.     

关于多元化经营的探讨

论述了多元化经营的战略思想,分析了多元化经营陷入误区的几种表现,提出了发展多元化经营的前提条件。     

海南地区东三段水下分流河道砂体的识别与预测

研究区构造高部位三角洲前缘储层发育程度较差,对储层成因及岩性油气藏分布规律研究有待深入.针对储层成因与分布等问题,本文运用层序地层对比与砂体成因分析等手段,发现研究区在北西低、南东高、沟谷相间的古地貌背景下,东三段发育了三角洲前缘水下分流河道砂体.以砂体的成因信息为线索,依据砂体的地球物理响应特征,运用种子点追踪与沿层属性提取等手段预测了三角洲前缘水下分流河道砂体的分布.预测结果表明,古地貌控制了水下分流河道砂体的展布,水下分流河道砂体的上倾尖灭部位是开展岩性油气藏勘探的有利目标.     

The recognition of ocean red tide with hyper-spectral-image based on EMD

A new technique is introduced in this paper regarding red tide recognition with remotely sensed hyper-spectral images based on empirical mode decomposition （EMD）, from an artificial red tide experiment in the East China Sea in 2002. A set of characteristic parameters that describe absorbing crest and reflecting crest of the red tide and its recognition methods are put forward based on general pictre data, with which the spectral information of certain non-dominant alga species of a red tide occurrence is analyzed for establishing the foundation to estimate the species. Comparative experiments have proved that the method is effective. Meanwhile, the transitional area between red-tide zone and non-red-tide zone can be detected with the information of thickness of algae influence, with which a red tide can be forecast.     

滑坡危险性等级区划方法研究

以四川省地理环境条件为研究背景,根据相关单位提供的资料,对四川省滑坡危险性等级进行了区划研究。将地形地貌、地层岩性、断裂构造、河流水系、降雨量、地震烈度等6项作为滑坡的主要影响因素,采用模式识别方法进行滑坡危险性等级区划,对算法中所涉及到的危险系数计算公式、因子权重分析、阈值选取等进行了一系列控制试验,验证了算法的可行性以及降低算法中存在的不确定性。采用“识别率”和“改变率”2个准则来判断“分类结果作为新的训练集”,即RTS试验的收敛性,从而给出识别率高、改变率稳定的分类结果,以及能合理反映识别结果的最佳参数。通过3次逐级识别分类,将四川省滑坡危险度划分为7个等级,区划结果与实际滑坡发生情况吻合。本文方法同样适用于其它地区的滑坡危险性等级区划。     

Analysis of multivariate point distributions and chemical grouping of rocks

Large sets of rock compositions can be grouped by the analysis of corresponding point distributions in multidimensional space, where the separate dimensions represent the chemical variables. The point density around each composition is estimated in a small, multivariate, rectangular interval. Establishment of the identity of specimens contained in the interval, and systematic comparison of the point densities surrounding each of them, leads to the recognition of density maxima, which represent the statistical modes of the rock types present in the set. The remaining specimens by the same operations can be assigned to the groups formed. Experimental results are given for two sets, one comprising a wide variety of metasedimentary and metavolcanic rocks from the ore-bearing Skellefte district and adjacent parts of V?sterbotten, Sweden, and the other representing a less variable population of basic rocks from Norrbotten, Sweden. Linear discriminant analysis and existing geological information indicate that the groups obtained are statistically and geologically valid.