基于LS-SVR岩石爆破块度预测

为了准确预测小样本条件下露天矿山岩石的爆破块度,并得到小样本条件下预测露天矿山爆破块度的有效方法,借助最小二乘支持向量机工具(LS-SVMlab)构建基于最小二乘支持向量机回归(LS-SVR)预测模型并合理优化模型参数。分别使用15组露天矿山爆破数据和35组爆破数据作为小样本容量和正常样本容量,对模型的预测精度进行检验。结果表明:两种样本容量下LS-SVR预测模型的预测结果精度都比同样本容量下人工神经网络(ANN)回归预测的结果精度更高,说明所提出的LS-SVR模型适用于预测露天矿山爆破块度,并且在小样本条件下更具优势。     

我国京津冀和西北五省(自治区)大气环境容量研究

本研究以京津冀和西北五省(自治区)为例,研究处于不同经济发展阶段的区域大气环境容量。利用GEOS-Chem全球大气化学传输模式模拟计算大气污染源排放所带来的环境空气中污染物的浓度,以京津冀和西北五省(自治区)的网格平均地面PM_(2.5)年均浓度达到环境空气质量标准(GB3095—2012)为约束条件,确定出京津冀和西北五省(自治区)SO_2、NO_x、一次PM_(2.5)、VOCs和NH_3五种大气污染物环境容量。结果表明,2013年京津冀和西北五省(自治区)SO_2、NO_x、一次PM_(2.5)、VOCs和NH_3五种大气污染物的排放量均超出大气环境容量。     

小样本数据的支持向量机回归模型参数及预测区间研究

支持向量机是由统计学习理论发展起来的机器学习算法,它从结构风险最小化的角度保证了模型的最大泛化能力.文中运用支持向量机进行小样本数据回归分析研究.首先利用推广性的界理论指导支持向量机回归模型参数的选取,以保证模型具有最大的推广能力;其次,运用基于正态分布和基于t分布的两种区间预测方法进行了预测值的区间估计;最后,利用模拟序列和真实的航空发动机油样光谱分析数据作为实验数据,建立了支持向量机回归分析模型,并与最小二乘法进行了比较.结果表明,所提出的支持向量机模型参数选取和区间估计方法适用于小样本数据的回归分析,具有较高的预测精度.     

基于遗传-支持向量回归的车内稳态噪声声品质预测

为了稳定、精确地评价车内稳态噪声声品质,以车内稳态噪声为研究对象,进行主观评价试验,计算客观心理声学参数并完成了相关性分析。建立基于支持向量回归(Support Vector Regression,SVR)的车内稳态噪声声品质预测模型,并使用遗传算法(Genetic Algorithm,GA)对支持向量回归的超参数进行优化。其后建立基于反向传播神经网络(Back Propagation Artificial Neural Network,BPANN)的声品质预测模型。对比分析发现遗传-支持向量回归(GASVR)模型预测精度高于BP神经网络。结果表明,遗传-支持向量回归适用于车内稳态噪声声品质预测,能够较大提高车内稳态噪声声品质预测精度和工程效率。     

遗传算法对RVM短期风速预测模型的多参数同步优化

该文利用混沌理论中的相空间重构方法,对基于相关向量机的风速预测模型的训练样本进行构建,然而通过混沌理论求出的相空间参数(嵌入维数E和时间延迟τ)往往不是预测模型的最优解。针对预测模型超参数优化问题,提出一种基于遗传算法的多参数优化方法,即对E、τ以及相关向量机核参数σ进行同步优化。该方法首先基于遗传算法搜索相关向量机预测模型参数(E、τ、σ)的全局最优解,进而建立预测模型;然后对待预测风速时间序列进行预测;最后以2组实际风速数据为例进行实验研究,并与对比模型方法(只优化参数σ)进行对比。结果表明:该文模型不仅具有较低的预测误差,而且可提高预测效率,缩短预测时间。     

SVM算法应用于大气污染时间序列预测

支持向量机(SVM)的在大气污染预测中显示出良好的非线性回归预测性能,本文通过建立基于该算法的时间序列模型,通过选取最优超平面,利用RBF核函数来解决在大气预测中线性不可分的问题。并取得了很高的预测精度结果 ,为大气回归预测方面的问题研究提供了一种崭新的思路。     

基于GWO的SVM在红外甲烷传感器测量误差分析中的应用

针对传统支持向量机回归模型应用在红外甲烷传感器测量数据处理时出现预测精度低的问题,提出了一种基于灰狼优化算法的支持向量机回归模型。该模型在传统支持向量机的基础上,利用灰狼优化算法自适应搜索特征空间来选择最佳特征组合,经过循环比较,能快速、准确地搜索到最优的惩罚因子C与gamma参数。用实验室研制的红外甲烷传感器对0～5.05%浓度范围的标准甲烷气体进行测量后,建立了3种SVM回归模型,并进行对比。结果表明,采用灰狼优化算法建立的支持向量机回归模型其绝对误差和相对误差小,精度高。     

R_2O-MO-Al_2O_3-SiO_2玻璃配方与热膨胀系数关系的支持向量回归研究

不同配方的玻璃一般具有不同的热膨胀系数.根据R2O-MO-Al2O3-SiO2(R为碱金属元素,M为碱土金属元素)系统玻璃在不同氧化物组成(SiO2,MgO,CaO,SrO,BaO,Na2O和K2O)下的热膨胀系数实测数据集,应用基于粒子群算法(PSO)寻优的支持向量回归(SVR)方法,建立了玻璃的不同配方与其热膨胀系数关系的SVR预测模型,并与基于BPNN神经网络模型的预测结果进行了比较.结果表明:对于相同的训练样本和检验样本,支持向量回归的玻璃的热膨胀系数模型始终比BPNN模型具有更高的预测精度;增加训练样本数有助于提高所建SVR预测模型的泛化能力;基于留一交叉验证法(LOOCV)的SVR预测的均方根误差(RMSE)、平均绝对误差(MAE)和平均绝对百分误差(MAPE)均为最小.本研究表明:SVR是一种预测不同配方玻璃的热膨胀系数的有效方法.     

Logistic 组稀疏回归模型的 Bayes 建模及变分推断

在工程应用中,如数据挖掘、成本预测以及风险预测等,Logistic 回归是一类十分重要的预测方法．当前,大部分 Logistic 回归方法都是基于优化准则而设计,这类回归方法具有参数调试过程繁琐、模型解释性差、估计子没有置信区间等缺点．本文从 Bayes 概率角度研究 Logistic 组稀疏性回归的建模与推断问题．具体来说,首先利用高斯-方差混合公式提出 Logistic 组稀疏回归的 Bayes 概率模型;其次,通过变分 Bayes 方法设计出一个高效的推断算法．在模拟数据上的实验结果表明,本文所提出的方法具有较好的预测性能．     

基于互信息PSO-LSSVM的SO2浓度预测

针对火电厂SO2污染物排放问题,提出了一种基于互信息的粒子群寻优(PSO)最小二乘支持向量机(LSSVM)模型预测方法,通过筛选出与SO2实测入口浓度相关性较高的辅助变量,将其作为模型的输入,实现对主导变量SO2浓度的预测。利用互信息筛选出的辅助变量相比于机理分析、皮尔逊相关性筛选出的辅助变量具有更高的相关性。利用互信息筛选出的辅助变量作为LSSVM模型的输入以及粒子群法确定LSSVM的参数,不仅缩短了计算时间,还提高了预测精度。将该方法应用到某火电厂的SO2浓度软测量中,利用现场数据进行仿真,结果表明预测精度较高,相对误差较低,预测趋势更贴近实际值,减小了实际值与预测值的误差(均方根误差为2.485,平均相对误差为0.2603%),为现场的SO2浓度提前控制提供了软件技术支持。     

The Impact of Air Pollution on a Regional Economy

A study was made to determine a more comprehensive method of estimating the impact of an air pollutant on a region's economy. To do this, a Leontief input-output model of Clinton County, Pennsylvania was employed. Economic and related changes were simulated with the model by making appropriate changes and/or additions to the parameters of the model, i.e., the technical coefficients and elements of the external income input vector. In this specific application, the technical coefficients were represented by Direct Cost Response Functions in which the technical coefficient was a function of pollutant concentration. These functions were derived for the coefficients of all sectors whose expenditure pattern was affected by the pollutant. With these functions, it was possible to modify the base model to reflect the effect of different levels of pollutant concentration in the region. Economic impact studies yielding the direct and indirect changes in expenditures in all sectors of the model were then carried out showing the cost of air pollution damages to the region.     

A Coordinate-Descent-Based Approach to Solving the Sparse Group Elastic Net

Group sparse approaches to regression modeling are finding ever increasing utility in an array of application areas. While group sparsity can help assess certain data structures, it is desirable in many instances to also capture element-wise sparsity. Recent work exploring the latter has been conducted in the context of l₂/l₁ penalized regression in the form of the sparse group lasso (SGL). Here, we present a novel model, called the sparse group elastic net (SGEN), which uses an l_∞/l₁/ridge-based penalty. We show that the l_∞-norm, which induces group sparsity is particularly effective in the presence of noisy data. We solve the SGEN model using a coordinate descent-based procedure and compare its performance to the SGL and related methods in the context of hyperspectral imaging in the presence of noisy observations. Supplementary materials for this article are available online.     

一种基于图像特征提取的浮选回收率预测算法

针对矿物浮选过程中的一类回收率预测问题,提出了一种基于泡沫图像特征提取的预测算法.该算法采用最小二乘支持向量机(LSSVM)建立预测模型,通过施密特正交化对核矩阵进行简约,利用核偏最小二乘方法(KPLS)进行LSSVM参数辨识,以此构造具有稀疏性的LSSVM,有效地减小了算法的计算复杂度.为检验模型泛化及预测能力,为多个泡沫特征信息引入预测模型,采用泡沫图像特征提取方法提取泡沫颜色、速度、尺寸、承载量及破碎率特征.实验结果表明,该预测算法对浮选回收率具有良好预测效果.     

Application of AERMOD for short-term air quality prediction with forecasted meteorology using WRF model

Many methods are available for air quality forecasting based on statistical and back trajectory models which require past time series data. Future air quality prediction through models is the best tool to make rational decisions by policy maker. Limited work has been done on air quality forecasting using dispersion models which require better meteorological boundary conditions. The Weather Research and Forecasting (WRF) and American Meteorological Society/Environmental Policy Agency Regulatory Model (AERMOD) models have not yet been combined for air quality forecasting. Here, a case study has been carried out to forecast air quality using onsite meteorological data from WRF model and a dispersion model named AERMOD. Prior to the use of AERMOD, a comprehensive emission inventory has been prepared for all the sources in the study region Chembur of Mumbai city. Chembur has been notified as the “air pollution control region” by local authority due to high levels of air pollution caused by the presence of four major industries, six major roads in addition to a crematorium and a biomedical waste incineration facility. The WRF–AERMOD system was applied for prediction of concentration levels of pollutants SO₂, NO _x and PM₁₀. A reasonable agreement was obtained when predicted values were compared with observed data. Results of the study indicated that forecasting of air quality can be carried out using AERMOD with forecasted meteorological parameters derived from WRF without any requirement of past time series air quality data. Such kind of forecasting method can be used for air quality management of any region by policy makers.     

COVID19: Forecasting Air Quality Index and Particulate Matter (PM2.5)

Urbanization affects the quality of the air, which has drastically degraded in the past decades. Air quality level is determined by measures of several air pollutant concentrations. To create awareness among people, an automation system that forecasts the quality is needed. The COVID-19 pandemic and the restrictions it has imposed on anthropogenic activities have resulted in a drop in air pollution in various cities in India. The overall air quality index (AQI) at any particular time is given as the maximum band for any pollutant. PM2.5 is a fine particulate matter of a size less than 2.5 micrometers, the inhalation of which causes adverse effects in people suffering from acute respiratory syndrome and other cardiovascular diseases. PM2.5 is a crucial factor in deciding the overall AQI. The proposed forecasting model is designed to predict the annual PM2.5 and AQI. The forecasting models are designed using Seasonal Autoregressive Integrated Moving Average and Facebook’s Prophet Library through optimal hyperparameters for better prediction. An AQI category classification model is also presented using classical machine learning techniques. The experimental results confirm the substantial improvement in air quality and greater reduction in PM2.5 due to the lockdown imposed during the COVID-19 crisis.     

Accelerating Large-Scale Statistical Computation With the GOEM Algorithm

Large-scale data analysis problems have become increasingly common across many disciplines. While large volume of data offers more statistical power, it also brings computational challenges. The orthogonalizing expectation–maximization (EM) algorithm by Xiong et al. is an efficient method to deal with large-scale least-square problems from a design point of view. In this article, we propose a reformulation and generalization of the orthogonalizing EM algorithm. Computational complexity and convergence guarantees are established. The reformulation of the orthogonalizing EM algorithm leads to a reduction in computational complexity for least-square problems and penalized least-square problems. The reformulation, named the GOEM (generalized orthogonalizing EM) algorithm, can incorporate a wide variety of convex and nonconvex penalties, including the lasso, group lasso, and minimax concave penalty penalties. The GOEM algorithm is further extended to a wider class of models including generalized linear models and Cox's proportional hazards model. Synthetic and real data examples are included to illustrate its use and efficiency compared with standard techniques. Supplementary materials for this article are available online.     

一种新的预测冰蓄冷空调负荷的ARMAX模型辨识方法

基于系统辨识理论,提出一种新的预测冰蓄冷中央空调平均负荷的外源自回归滑动平均(ARMAX)模型辨识方法.首先根据空调负荷历史数据构建次日平均负荷的ARMAX模型;然后基于不同的室外最高温度建立自适应ARMAX温度区间模型,该模型由几组参数时变的子模型组成,子模型参数由在线回归算法辨识.测试数据表明,所提出的ARMAX温度区间模型与传统的ARMAX模型相比具有较高的预测精度,而且室外最高温度差异越大,效果越明显,可用于冰蓄冷中央空调的优化控制.     

基于支持向量机的柴油机噪声品质客观评价参量权重分析

以一台6缸柴油机为研究对象,采用分类对偶比较法对采集到的目标机型在多工况下的辐射噪声品质进行主观评价试验,同时选取并计算了可以描述其声音特性的5个客观评价参量,引入支持向量机,建立了柴油机噪声品质预测模型,并借助噪声测试样本验证预测模型的准确性。然后以柴油机噪声品质预测模型为基础构建起客观评价参量的权重分析模型,分析柴油机噪声品质客观评价参量对主观评价结果的影响权重。研究表明,柴油机噪声品质主要受响度和粗糙度两个客观评价参量的影响。此次分析对高声品质柴油机的设计起到了指导性的作用。     

京津冀视域下的区域旅游文创产品发展策略

目的将地区因素引入到城市的文创产品设计中,并建立复杂性分析,提升文创设计水平。在京津冀一体化的基础上,以文创产品为依托,促进地区形象的展现与经济的发展,为文创产品的发展提出参考性建议。方法以京津冀地区特色为主要依据,结合京津冀地区的历史文化,促进地区文化与文创产品的融合与发展。充分发挥京津冀一体化优势,加强各地区文化之间的联系。以具体产品为例,分析其标准、作用、感受等方面的因素。探讨提高文创设计水平的方法。结论通过综合分析文创产品现状,发现京津冀旅游文创产品在发展中的短板,在京津冀一体化发展的基础上,提出对素材的获取、信息的连接及传递等方面的建议。提升地区文创产品水平,进一步有效地提升区域形象带动经济的发展。     

城市大气污染源追踪“广义判识”与Nudging源 同化集成技术途径

提出了城市大气污染源追踪“广义判识”综合应用平台、模式源同化及其卫星遥感应用等新技术。“广义判识”综合应用平台包括气溶胶源主因子分析方法、气溶胶周期变化谱分析法、城市冠层大气污染变化规律同位相特性分析、追溯远距离空气污染源的合成风场相关矢量法、后向轨迹示踪法和边界层影响足痕分析法;另外,为解决长期以来大气污染模式中排放源不确定性的关键技术难点,采用源同化牛顿逼近Nudging技术,获取具有季节、月变化动态变化特征的SO2、NO2区域反演源排放清单。将卫星遥感资料应用在同化模型,探索空气污染预报模式的卫星遥感产品应用技术,卫星遥感—地基观测综合分析平台亦可广泛地应用于城市污染源追踪、城市雾和城市热岛的研究,并提出多圈层水—土—气综合分析方法是一种追踪水污染源的探索性尝试