Multiscale quality assessment of Global Human Settlement Layer scenes against reference data using statistical learning

A method for quality assessment of the Global Human Settlement Layer scenes against reference data is presented. It relies on two settlement metrics; the local average and gradient functions that quantify the notions of settlement density and flexible settlement limits respectively. They are both utilized as generalization functions for increasing the level of abstraction of the sets under comparison. Generalization compensates for inaccuracies of the automatic target extraction method and can be computed at multiple scales. The comparison between the target built-up layers and the reference data employs an ordered multi-scale, linear regression computing the goodness of fit measure R²$R^2$. An optimized assessment procedure is investigated in a pilot study and is further employed in a big data exercise. A newly introduced quality metric returns the agreement between automatically extracted built-up from a set of 13605 scenes and the MODIS 500 urban layer, that was found too be as high as 91% for selected sensors. A final experiment attempts a performance increase at lower scales by correlating the target layer with automatically selected training subsets. At 50 m the adjusted R²$R^2$ increases by 3% with a mean squared error improvement of 2% compared to the performance achieved without statistical learning. The experiment suggests that the GHSL assessment at a global scale can be carried out based on limited high resolution reference data of minimal spatial coverage.     

软件可靠性预测中不同核函数的预测能力评估

基于核函数回归估计理论的软件可靠性预测建模引起诸多研究者的兴趣.此类研究中,核函数选择问题尤为重要.然而目前还很少有针对所给软件失效数据进行核函数选择或者构建核函数的工作.在14个常用软件失效数据集上应用配对t-检验对基于核函数理论的软件可靠性预测模型中核函数选择问题进行研究.使用的核函数回归估计方法包括核主成分回归算法、核偏最小二乘回归算法、支持向量回归算法、相关向量回归算法;核函数包括高斯核函数、线性核函数、多项式核函数、柯西核函数、拉普拉斯核函数、对称三角核函数、双曲正割核函数、平方正弦基核函数.实验结果表明:不同类型的核函数在不同数据集上表现差异较大,高斯核函数在所有数据集上表现较为稳定,预测结果最好.     

Consumer credit risk: Individual probability estimates using machine learning

Consumer credit scoring is often considered a classification task where clients receive either a good or a bad credit status. Default probabilities provide more detailed information about the creditworthiness of consumers, and they are usually estimated by logistic regression. Here, we present a general framework for estimating individual consumer credit risks by use of machine learning methods. Since a probability is an expected value, all nonparametric regression approaches which are consistent for the mean are consistent for the probability estimation problem. Among others, random forests (RF), k-nearest neighbors (kNN), and bagged k-nearest neighbors (bNN) belong to this class of consistent nonparametric regression approaches. We apply the machine learning methods and an optimized logistic regression to a large dataset of complete payment histories of short-termed installment credits. We demonstrate probability estimation in Random Jungle, an RF package written in C++ with a generalized framework for fast tree growing, probability estimation, and classification. We also describe an algorithm for tuning the terminal node size for probability estimation. We demonstrate that regression RF outperforms the optimized logistic regression model, kNN, and bNN on the test data of the short-term installment credits.     

基于PLSR的中山市水资源压力演变特征与趋势

以珠江三角洲腹地城市中山市为研究目标,分析城市社会经济发展多个指标对水资源压力的影响,并利用偏最小二乘回归（PLSR）方法对1991年以来中山市水资源压力的演变特征和趋势进行分析和预测。结果表明,节水水平和第三产业发展是中山市水资源压力的主要影响因素。1991-2011年间,中山市的水资源压力整体上呈先降后升的变化趋势,并将可能在今后20年的时间内保持上升趋势。中山市水资源压力与人均GDP之间则呈现出N形环境库尔兹涅曲线特征,表明随着经济发展到一定程度,中山市水资源压力将有所下降,但同时也面临着重新上升的压力。     

河流健康评价的回归支持向量机模型及应用

建立河流健康评价指标体系、分级标准及回归支持向量机（ SVR ）河流健康评价模型,并以云南省文山州清水河健康评价为例进行研究。首先,利用层次分析法（ AHP ）从水文水资源、物理结构、水质、水生生物和社会服务功能5个方面遴选出13个评价指标,构建3个层次的河流健康评价指标体系和5个等级的分级标准;其次,基于SVR原理,利用随机生成和随机选取的方法,在等级标准阈值间构造5种不同容量大小的训练样本和检验样本,提出5种不同容量方案的SVR河流健康评价模型,设计合理的输出模式,并构建具有良好性能的RBF（radial basis function neural network ）回归模型作为对比模型,利用模型随机5次运行的平均相对误差绝对值、最大相对误差绝对值和运行时间对各方案模型性能进行评价;最后,利用达到期望精度的SVR模型对实例进行评价分析。结果表明：①无论是训练样本还是检验样本,5种方案的SVR模型的预测精度和泛化能力均优于 RBF模型。在相同参数设置条件下,SVR模型随着样本容量的增加其精度和泛化能力变化不大;而RBF模型随着样本容量的增加其精度和泛化能力均有提高。表明SVR模型具有较高的精度和泛化能力,可以用于河流健康评价,尤其在小样本情况下,SVR模型的精度和泛化能力是RBF模型不可比拟的。②5种方案的SVR模型对清水河2011-2012年3次调查的评价结果均为健康,但已接近于亚健康。     

TIMING OF REDD CONSTRUCTION BY FALL CHINOOK SALMON IN THE HANFORD REACH OF THE COLUMBIA RIVER

Spawning habits of fall Chinook salmon in the Hanford Reach of the Columbia River have been documented with annual aerial surveys since 1948. We developed a series of models analysing these data, exploring the influence of environmental factors on the timing of redd construction. These models included a logistic regression and a dynamic modelling approach, with combinations of day of year (as a surrogate for environmental cues such as day length), water temperature and discharge as potential explanatory factors. Results of these analyses indicate that day of year was the strongest predictor of the timing of redd construction, but with significant modifying effects of water temperature and discharge. The dynamic modelling approach provides substantial advantages over a traditional logistic regression, including (1) the ability to treat data collected at non‐synchronous time intervals in a consistent fashion and (2) the ability to easily implement complex functions (e.g., threshold responses) relating behaviour to environmental cues. Evaluation of the series as a whole indicates that the median date of redd construction has increased over time, from approximately day 299 in 1950 to day 307 in 2010, as has the temperature on Oct 1 (16.3 °C–18.1 °C). The degree to which these changes are caused by climate change or dam operations is uncertain, however. Copyright © 2013 John Wiley & Sons, Ltd.     

逐段回归近似的卫星遥测数据挖掘算法与仿真

卫星长期运行过程中积累的大量遥测数据蕴涵有宝贵的卫星状态变化信息,挖掘变化特征对发现卫星状态异常变化和诊断卫星运行过程故障具有重要意义.围绕在轨卫星遥测数据分析以及遥测的故障诊断相似性查找问题,提出了一种基于逐段回归近似(PRA)的卫星遥测时序数据相似性挖掘算法.算法首先通过对卫星遥测数据挖掘实现数据的降维处理,以减少数据量;其次通过建立多维空间索引树,并在索引树中通过相似阈值判断进行查找,以获得给定时序数据的相似序列.理论分析和仿真实测卫星电源分系统的时序遥测数据实验表明,该算法对遥测数据序列可有效地进行降维处理,并保持数据趋势性;建立的相似序列为提高在轨卫星数据分析和故障诊断的有效性和正确性提供了依据.     

多维度等级评分模型优化技术

研究了多维度等级评分模型的训练学习优化技术.为了解决不同用户之间的评分标注所存在的不一致性,提出两种简单、有效的模型训练优化技术,包括基于容忍度的样本选择方法和基于排序损失的样本选择方法.另外,为了充分利用不同特征的用户评分标注之间的相关性,提出了一个面向属性的协同过滤技术以改善多维度等级评分模型.在两个公开的英语和汉语真实餐馆评论数据集上进行实验验证,实验结果表明,所提出的方法有效地改善了等级评分的性能.     

高斯过程回归方法综述

高斯过程回归是基于贝叶斯理论和统计学习理论发展起来的一种全新机器学习方法,适于处理高维数、小样本和非线性等复杂回归问题。在阐述该方法原理的基础上,分析了其存在的计算量大、噪声必须服从高斯分布等问题,给出了改进方法。与神经网络和支持向量机相比,该方法具有容易实现、超参数自适应获取以及输出具有概率意义等优点,方便与预测控制、自适应控制、贝叶斯滤波等相结合。最后总结了其应用情况并展望了未来发展方向。     

基于LASSO-LARS的软件复杂性度量属性特征选择研究

针对软件可靠性早期预测中软件复杂性度量属性维数灾难问题,提出了一种基于最小绝对值压缩与选择方法(The Least Absolute Shrinkage and Select Operator,LASSO)和最小角回归(Least Angle Regression,LARS)算法的软件复杂性度量属性特征选择方法。该方法筛选掉一些对早期预测结果影响较小的软件复杂性度量属性,得到与早期预测关系最为密切的关键属性子集。首先分析了LASSO回归方法的特点及其在特征选择中的应用,然后对LARS算法进行了修正,使其可以解决LASSO方法所涉及的问题,得到相关的复杂性度量属性子集。最后结合学习向量量化(Learning Vector Quantization,LVQ)神经网络进行软件可靠性早期预测,并基于十折交叉方法进行实验。通过与传统特征选择方法相比较,证明所提方法可以显著提高软件可靠性早期预测精度。