结合主成分分析的BP神经网络模型的教学质量评价方法研究

提出结合主成分分析PCA(principalcomponentanalysis)的BP神经网络模型的教学质量评价方法,首先利用主成分分析PCA对多维度教学质量评价指标进行了降维,确保了多维评价指标作为整体进行BP模型训练和测试,然后构建BP神经网络教学质量评价模型,利用其前向反馈计算和误差后向传播的特性,自适应获取评价指标之间的权值。实验证明,该方法可行,解决了传统评价方法的复杂建模问题,避免人为的主观随意度,保证评估结果的有效性。     

伽师及邻近地区GPS地壳形变监测及初步分析

通过对伽师及邻近地区ＧＰＳ监测网的优化布设和两期观测资料的分析,对伽师及邻近地区的地形变特征进行了探讨,认为伽师地区整体上受到正南北向的主压应力,但在喀什和乌恰－乌仁一带存在着较大的剪应力。伽师地区每年相对于北天山（哈萨克斯坦）的运动速度为１９ｍｍ,整个南天山地区发生中强地震的可能性将长期存在。     

重度石漠化区不同土地利用方式下土壤养分特征

本文以云南省蒙自市西北勒乡碧色寨村石漠化土地为研究对象,基于主成分分析法（PCA）研究岩溶石漠化区不同土地利用方式下的土壤养分特征。结果表明:（1）研究区土壤各养分指标变异系数介于0.14~1.76,不同土地利用方式下,土壤养分状况有较大差异;（2）研究区土壤12项养分指标可归结为3个主成分,所提供的信息占全部信息的90.69%,其中PC1主要包含了全磷、有效磷、速效钾和有效锰,PC2主要综合了有机碳、全氮、全钙和有效锌,有效铁对PC3具有较大的贡献。（3）对不同用地类型土壤养分的主成分得分进行排序,由大到小依次为火龙果地>林地>封育草地>玉米地,表明植树造林及火龙果种植等方式能有效改善石漠化区的土壤养分状况。建议对样区的石漠化治理应以封山育土为前提,以生态恢复为目的,通过种植火龙果与修复林地改善样区土壤状况,逐步形成生态环境与社会经济协调发展的石漠化综合治理体系。      

基于主成分分析和贝叶斯正则化方法的神经网络年最大洪峰流量预测模型探讨

针时水文预测建模中输入因子过多而导致神经网络结构规模过大,泛化能力差的问题,利用主成分分析和贝叶斯正则化方法对神经网络进行改进,优化网络结构,从而提高泛化能力。以洮儿河流域镇西站年最大洪峰流量预测为例,研究结果表明,改进的神经网络预测方法与传统的神经网络方法相比,泛化能力有显著提高,而且网络的收敛也比较稳定,实际预测中效果良好。     

成像光谱仪影像的几种处理方法

针对成像光谱仪影像的专题分析,介绍了沿用常规遥感影像分析方法时的原理和新的算法,提出了影像融合方法的应用,说明了这些方法在学术思想上的归属,并简要介绍了各种方法的实验效果。     

珠江流域夏半年降水的预测

采用珠江流域1954～2003年月降水资料,以及前期太平洋海温场和北半球500 hPa高度场月平均资料,利用主分量逐步回归预测模型,对该流域夏半年(4～9月)降水分布进行主分量计算和预测.结果表明:对前25个主分量的预测就能很好地预测珠江流域夏半年降水的变化,2004～2006年预测结果与实况较接近.预测因子取自500 hPa高度场和海温场的主分量,为降水的预测提供大量有用信息.该方法在实际业务中有一定的应用价值.     

États de contraintes et mécanismes d'ouverture et de fermeture des bassins permiens du Maroc hercynien. L'exemple des bassins des Jebilet et des RéhamnaStates of stresses and opening/closing mechanisms of the Permian basins in Hercynian Morocco. The example of the Jebilet and Réhamna Basins

The fracturing analysis in the Permian basins of Jebilet and Rehamna (Hercynian Morocco) and the underlying terranes allowed us to suggest a model for their opening. Three tectonic episodes are distinguished: a transtensional episode NNE–SSW-trending (Permian I), occurring during the opening along sinistral wrench faults N70–110-trending, associated with synsedimentary normal faults; a transpressive episode ESE–WNW-trending (Permian II), initiating the closure, the normal faults playing back reverse faults and the N70 trending faults dextral wrench faults; a compressional episode NNW–SSE (post-Permian, ante-Triassic), accentuating the closure and the deformation and putting an end to the Tardi-Hercynian compressive movements. To cite this article: A. Saidi et al., C. R. Geoscience 334 (2002) 221–226.     

基于主成分和模糊C-均值聚类算法的农业水资源高效利用综合分区

基于农业生态系统环境要素、水的资源属性、水资源的高效利用内涵、生产力水平、土地利用方式、种植结构及种植模式等因子,选取构建农业水资源高效利用综合分区的指标体系(16个定量指标、4个定性指标),采用主成分分析和模糊C-均值聚类算法为区划方法,对川中丘陵区进行量化分区。研究结果将川中丘陵区16个地级市和一个县级市(简阳)分为农业水资源较低利用区、农业水资源低效利用区、农业水资源中等利用区、农业水资源高效利用区和农业水资源较高效利用区5个区,这对南方季节性干旱区水资源利用规划有较强的借鉴作用。     

Automatic estimation of olive tree dendrometric parameters based on airborne laser scanning data using alpha-shape and principal component analysis

The aim of this study is to present an automatic approach for olive tree dendrometric parameter estimation from airborne laser scanning (ALS) data. The proposed method is based on a unique combination of the alpha-shape algorithm applied to normalized point cloud and principal component analysis. A key issue of the alpha-shape algorithm is to define the α parameter, as it directly affects the crown delineation results. We propose to adjust this parameter based on a group of representative trees in an orchard for which the classical field measurements were performed. The best value of the α parameter is one whose correlation coefficient of dendrometric parameters between field measurements and estimated values is the highest. We determined crown diameters as principal components of ALS points representing a delineated crown. The method was applied to a test area of an olive orchard in Spain. The tree dendrometric parameters estimated from ALS data were compared with field measurements to assess the quality of the developed approach. We found the method to be equally good or even superior to previously investigated semi-automatic methods. The average error is 19% for tree height, 53% for crown base height, and 13% and 9% for the length of the longer diameter and perpendicular diameter, respectively.     

Lame surfaces as a generalisation of the triaxial ellipsoid

In modern geodesy the triaxial ellipsoid as a generalisation of the ellipsoid of revolution has a significant position in studying the figure of the Earth. Lame surfaces represent a generalisation of the triaxial ellipsoid. The following paragraphs are devoted to curvatures of the Lame surfaces.