金融时间序列指标判别框架：以特质波动率为例

基于拐点集合判别的TBUD方法主要思路是分析拐点集合间的关系，并在高维空间进行划分，从而搭建判别模型，并将分析框架应用在特质波动率等若干指标上，利用实证数据得到结论。应用TBUD判别框架可以发现，特质波动率等指标无法对拐点集合进行清晰划分，因而并不具有预测能力。     

The use of compensatory and non-compensatory multi-criteria analysis for small-scale forestry

Small-scale farm forestry has the potential to offer many benefits both to landholders and the wider community. As with all changes in land-use practices, there are associated benefits and costs and these are not uniformly distributed. They have varying impacts on the different values, aspirations, goals and objectives that exist within the community. Furthermore, the community does not consider these values, aspirations, goals and objectives of equal importance. The degree of concern can vary from minor to high and overriding all other considerations. When evaluating farm forestry options it is necessary to address all of these concerns. This paper examines the combined use compensatory and non-compensatory multi-criteria analyses to evaluate forestry options, in a case study for the Darling Downs region of Queensland, Australia. These aggregation techniques are found to be highly complementary and together provide a comprehensive analysis. The compensatory technique provides a sound measure of overall performance of a forestry system, whereas the non-compensatory technique alerts decision-makers to presence of particularly poor performance with respect to individual criteria. The compensatory technique used is simple and understandable even for those with non-mathematical backgrounds. This analysis can identify and aid communication of the relative benefits and costs, and trade-offs, between economic, environmental and social considerations.     

支持向量机在水质评价中的应用

介绍了支持向量机算法的原理，建立了基于支持向量机的水质评价多层次分类检测模型，通过提取水质评价标准中的物质成分为特征参数，利用几个SVM分类器的串联组合，实现对水质的分类和识别，同时，引入类权重因子，解决训练样本类别数量不平衡而导致的错分问题，实验结果显示该方法提高了水质评价的准确性和效率。     

距离倒数和克里克方法在土壤养分制图中的比较研究

空间插值方法以及模型参数的选择是制约插值精度的重要因素。为此,使用普通克里克、普通对数克里克和距离倒数加权方法对三峡库区王家沟小流域内的土壤养分(有机质、全氮、全磷)进行插值,研究了权重指数、邻域样本数目和变异函数模型对插值结果的影响,并用交叉验证的方法对这几种插值方法进行了比较。结果显示,距离倒数加权对于土壤有机质和全氮制图具有最高的精度,对数克里克对于全磷的模拟则是最优的。     

基于可见光机器视觉的棉花伪异性纤维识别方法

为提高皮棉质量和皮棉中异纤的检测精度,提出了一种基于机器视觉的棉花伪异性纤维识别方法。皮棉经过开松装置被制成薄棉层,检测通道两侧的相机对棉层进行拍摄,并将采集到的棉层及异纤和伪异纤图像保存到工控机,通过图像分块及阈值分割等算法,提取伪异纤目标区域,统计获取区域的数个颜色、形状和纹理特征,基于特征数据,分别使用BP神经网络、一对一有向无环图策略线性核函数支持向量机和径向基核函数支持向量机对两大类棉花杂质进行分类识别。实验结果表明,99.15%的伪异纤目标可被准确识别,径向基核函数支持向量机在棉花异纤和伪异纤分类识别中,总分类正确率为95.60%,能够满足在线检测的要求。     

基于全站仪的工程侵蚀快速监测方法研究

对工程侵蚀的监测需要快速和精确。随着硬件的不断发展,特别是无棱镜全站仪的发展,使得使用全站仪来监测工程侵蚀量成为可能。采用最新型的无棱镜全站仪,设计了一套测量方法,对某公路边坡进行了监测。并根据监测的数据通过克里金插值和基于约束的Delaunay剖分方法建立其三维模型,从而达到计算工程边坡体积的目的。通过多次监测,最后达到工程侵蚀量监测的目标。     

基于数据库的温室环境决策支持系统的设计与实现

用Delphi6．0编写构建了温室环境的决策支持系统。系统中的知识库、模型库和数据库以数据库为基础，采用Database Desktop来设计，有助于系统对知识、模型和相关数据的管理。对系统决策的过程采用基于数据库的方法进行编写，解决了温室环境智能决策过程中推理困难的问题，同时提高了决策的准确程度。     

基于随机森林回归算法的小麦叶片SPAD值遥感估算

使用机器学习中的随机森林(RF)回归算法构建小麦叶片SPAD值遥感反演模型。以2010—2013年江苏地区试验点稻茬小麦3个生育期(拔节、孕穗、开花)的叶片为材料,结合我国自主研发的环境减灾卫星HJ-1对研究区域进行同步监测,分析了各生育期叶片SPAD值与8种植被指数间的相关性;以0.01水平下显著相关的植被指数作为输入参数,使用RF回归算法构建了每个生育期的小麦SPAD反演算法模型,即RF-SPAD模型,以支持向量回归(SVR)和反向传播(BP)神经网络算法构建的SVR-SPAD模型和BP-SPAD模型作为比较模型,以R2和均方根误差(RMSE)为指标,分析了每个生育期3个模型的学习能力和回归预测能力,结果表明:RF-SPAD模型在3个生育期都表现出最强的学习能力,R2和RMSE在拔节期分别为0.89和1.54,孕穗期分别为0.85和1.49,开花期分别为0.80和1.71;RF-SPAD模型在3个生育期的回归预测能力都高于BP-SPAD模型,高于或接近于SVR-SPAD模型,R2和RMSE在拔节期分别为0.55和2.11,孕穗期分别为0.72和2.20,开花期分别为0.60和3.16。     

Neural network ensemble residual kriging application for spatial variability of soil properties

High quality, agricultural nutrient distribution maps are necessary for precision management, but depend on initial soil sample analyses and interpolation techniques. To examine the methodologies for and explore the capability of interpolating soil properties based on neural network ensemble residual kriging, a silage field at Hayes, Northern Ireland, UK, was selected for this study with all samples being split into independent training and validation data sets. The training data set, comprised of five soil properties: soil pH, soil available P, soil available K, soil available Mg and soil available S,was modeled for spatial variability using 1) neural network ensemble residual kriging, 2) neural network ensemble and 3) kriging with their accuracies being estimated by means of the validation data sets. Ordinary kriging of the residuals provided accurate local estimates, while final estimates were produced as a sum of the artificial neural network (ANN) ensemble estimates and the ordinary kriging estimates of the residuals. Compared to kriging and neural network ensemble,the neural network ensemble residual kriging achieved better or similar accuracy for predicting and estimating contour maps. Thus, the results demonstrated that ANN ensemble residual kriging was an efficient alternative to the conventional geo-statistical models that were usually used for interpolation of a data set in the soil science area.