Small-time scale network traffic prediction based on a local support vector machine regression model

In this paper we apply the nonlinear time series analysis method to small-time scale traffic measurement data. The prediction-based method is used to determine the embedding dimension of the traffic data. Based on the reconstructed phase space, the local support vector machine prediction method is used to predict the traffic measurement data, and the BIC-based neighbouring point selection method is used to choose the number of the nearest neighbouring points for the local support vector machine regression model. The experimental results show that the local support vector machine prediction method whose neighbouring points are optimized can effectively predict the small-time scale traffic measurement data and can reproduce the statistical features of real traffic measurements.

TYRE DYNAMICS MODELLING OF VEHICLE BASED ON SUPPORT VECTOR MACHINES

Various methods of tyre modelling are implemented from pure theoretical to empirical or semi-empirical models based on experimental results. A new way of representing tyre data obtained from measurements is presented via support vector machines （SVMs）. The feasibility of applying SVMs to steady-state tyre modelling is investigated by comparison with three-layer backpropagation （BP） neural network at pure slip and combined slip. The results indicate SVMs outperform the BP neural network in modelling the tyre characteristics with better generalization performance. The SVMsqyre is implemented in 8-DOF vehicle model for vehicle dynamics simulation by means of the PAC 2002 Magic Formula as reference. The SVMs-tyre can be a competitive and accurate method to model a tyre for vehicle dynamics simuLation.

A Multiple Model Approach to Modeling Based on Fuzzy Support Vector Machines

A new multiple models(MM) approach was proposed to model complex industrial process by using Fuzzy Support Vector Machines(F -SVMs). By applying the proposed approach to a pH neutralization titration experiment, F -SVMs MM not only provides satisfactory approximation and generalization property, but also achieves superior performance to USOCPN multiple modeling method and single modeling method based on standard SVMs.

Endpoint Prediction of EAF Based on Multiple Support Vector Machines

The endpoint parameters are very important to the process of EAF steel-making, but their on-line measurement is difficult. The soft sensor technology is widely used for the prediction of endpoint parameters. Based on the analysis of the smelting process of EAF and the advantages of support vector machines, a soft sensor model for predicting the endpoint parameters was built using multiple support vector machines （MSVM）. In this model, the input space was divided by subtractive clustering and a sub-model based on LS-SVM was built in each sub-space. To decrease the correlation among the sub-models and to improve the accuracy and robustness of the model, the sub- models were combined by Principal Components Regression. The accuracy of the soft sensor model is perfectly improved. The simulation result demonstrates the practicability and efficiency of the MSVM model for the endpoint prediction of EAF.

Spatial prediction of landslide susceptibility in western Serbia using hybrid support vector regression(SVR)with GWO,BAT and COA algorithms

In this study,we developed multiple hybrid machine-learning models to address parameter optimization limitations and enhance the spatial prediction of landslide susceptibility models.We created a geographic information system database,and our analysis results were used to prepare a landslide inventory map containing 359 landslide events identified from Google Earth,aerial photographs,and other validated sources.A support vector regression(SVR)machine-learning model was used to divide the landslide inventory into training(70%)and testing(30%)datasets.The landslide susceptibility map was produced using 14 causative factors.We applied the established gray wolf optimization(GWO)algorithm,bat algorithm(BA),and cuckoo optimization algorithm(COA)to fine-tune the parameters of the SVR model to improve its predictive accuracy.The resultant hybrid models,SVR-GWO,SVR-BA,and SVR-COA,were validated in terms of the area under curve(AUC)and root mean square error(RMSE).The AUC values for the SVR-GWO(0.733),SVR-BA(0.724),and SVR-COA(0.738)models indicate their good prediction rates for landslide susceptibility modeling.SVR-COA had the greatest accuracy,with an RMSE of 0.21687,and SVR-BA had the least accuracy,with an RMSE of 0.23046.The three optimized hybrid models outperformed the SVR model(AUC=0.704,RMSE=0.26689),confirming the ability of metaheuristic algorithms to improve model performance.

Fuzzy rule-based support vector regression system

In this paper, we design a fuzzy rule-based support vector regression system. The proposed system utilizes the advantages of fuzzy model and support vector regression to extract support vectors to generate fuzzy if-then rules from the training data set. Based on the first-order hnear Tagaki-Sugeno （TS） model, the structure of rules is identified by the support vector regression and then the consequent parameters of rules are tuned by the global least squares method. Our model is applied to the real world regression task. The simulation results gives promising performances in terms of a set of fuzzy hales, which can be easily interpreted by humans.

System identification modelling of ship manoeuvring motion based on ?- support vector regression

Based on the ε - support vector regression, three modelling methods for the ship manoeuvring motion, i.e., the white-box modelling, the grey-box modelling and the black-box modelling, are investigated. The 10°/10°, 20°/20° zigzag tests and the 35° turning circle manoeuvre are simulated. Part of the simulation data for the 20°/20° zigzag test are used to train the support vectors, and the trained support vector machine is used to predict the whole 20° / 20° zigzag test. Comparison between the simula- ted and predicted 20° / 20° zigzag test shows a good predictive ability of the three modelling methods. Then all mathematical models obtained by the modelling methods are used to predict the 10°/10° zigzag test and 35° turning circle manoeuvre, and the predicted results are compared with those of simulation tests to demonstrate the good generalization performance of the mathematical models. Finally, the modelling methods are analyzed and compared with each other in terms of the application conditions, the prediction accuracy and the computation speed. An appropriate modelling method can be chosen according to the intended use of the mathematical models and the available data for the system identification.

Data-driven model predictive control for power demand management and fast demand response of commercial buildings using support vector regression

Demand response(DR)of commercial buildings by directly shutting down part of operating chillers could provide an immediate power reduction for power grids.In this special fast DR event,effective control needs to guarantee expected power reduction and ensure an acceptable indoor environment.This study,therefore,developed a data-driven model predictive control(MPC)using support vector regression(SVR)for fast DR events.According to the characteristics of fast DR events,the optimized hyperparameters of SVR and shortened searching range of genetic algorithm are used to improve the control performance.Meanwhile,a comprehensive comparison with RC-based MPC is conducted based on three scenarios of power demand controls.Test results show that the proposed SVR-based MPC could fulfill the control objectives of power demand and indoor temperature simultaneously.Compared with RC-based MPC,the SVR-based MPC could alleviate the time/labor cost of model development without sacrificing the control performance of fast DR events.

Nonlinear model predictive control with relevance vector regression and particle swarm optimization

In this paper, a nonlinear model predictive control strategy which utilizes a probabilistic sparse kernel learning technique called relevance vector regression （RVR） and particle swarm optimization with controllable random exploration velocity （PSO-CREV） is applied to a catalytic continuous stirred tank reactor （CSTR） process. An accurate reliable nonlinear model is first identified by RVR with a radial basis function （RBF） kernel and then the optimization of control sequence is speeded up by PSO-CREV. Additional stochastic behavior in PSO-CREV is omitted for faster convergence of nonlinear optimization. An improved system performance is guaranteed by an accurate sparse predictive model and an efficient and fast optimization algorithm. To compare the performance, model predictive control （MPC） using a deterministic sparse kernel learning technique called Least squares support vector machines （LS-SVM） regression is done on a CSTR. Relevance vector regression shows improved tracking performance with very less computation time which is much essential for real time control.

Comparative study of different machine learning models in landslide susceptibility assessment: A case study of Conghua District, Guangzhou, China

Machine learning is currently one of the research hotspots in the field of landslide prediction.To clarify and evaluate the differences in characteristics and prediction effects of different machine learning models,Conghua District,which is the most prone to landslide disasters in Guangzhou,was selected for landslide susceptibility evaluation.The evaluation factors were selected by using correlation analysis and variance expansion factor method.Applying four machine learning methods namely Logistic Regression(LR),Random Forest(RF),Support Vector Machines(SVM),and Extreme Gradient Boosting(XGB),landslide models were constructed.Comparative analysis and evaluation of the model were conducted through statistical indices and receiver operating characteristic(ROC)curves.The results showed that LR,RF,SVM,and XGB models have good predictive performance for landslide susceptibility,with the area under curve(AUC)values of 0.752,0.965,0.996,and 0.998,respectively.XGB model had the highest predictive ability,followed by RF model,SVM model,and LR model.The frequency ratio(FR)accuracy of LR,RF,SVM,and XGB models was 0.775,0.842,0.759,and 0.822,respectively.RF and XGB models were superior to LR and SVM models,indicating that the integrated algorithm has better predictive ability than a single classification algorithm in regional landslide classification problems.

Unconfined compressive strength prediction of soils stabilized using artificial neural networks and support vector machines

This study aims to improve the unconfined compressive strength of soils using additives as well as by predicting the strength behavior of stabilized soils using two artificial-intelligence-based models.The soils used in this study are stabilized using various combinations of cement,lime,and rice husk ash.To predict the results of unconfined compressive strength tests conducted on soils,a comprehensive laboratory dataset comprising 137 soil specimens treated with different combinations of cement,lime,and rice husk ash is used.Two artificial-intelligence-based models including artificial neural networks and support vector machines are used comparatively to predict the strength characteristics of soils treated with cement,lime,and rice husk ash under different conditions.The suggested models predicted the unconfined compressive strength of soils accurately and can be introduced as reliable predictive models in geotechnical engineering.This study demonstrates the better performance of support vector machines in predicting the strength of the investigated soils compared with artificial neural networks.The type of kernel function used in support vector machine models contributed positively to the performance of the proposed models.Moreover,based on sensitivity analysis results,it is discovered that cement and lime contents impose more prominent effects on the unconfined compressive strength values of the investigated soils compared with the other parameters.

A predictive model of the relationship between hematology,urine,clinical examination and the occurrence of depression risk are established based on machine learning

Background:Depression is a kind of emotional disorders caused by a variety of factors,with the accelerating pace of life,people in life and work facing competition pressure is increasing,the incidence of depression is increasing year by year,so the in-depth study of the pathogenesis of depression,and the development of depression risk prediction model is becoming increasingly important.Method:This study data is derived from the 2017–2018 follow-up data from the National Health and Nutrition Examination Survey database,a publicly available database using a multi-stage,hierarchical,clustered,probability sampling design to determine a nationally representative sample of non-institutionalized US civilians.Participants completed home interviews,laboratory measurements,and a physical examination.Details of the survey design have been published previously.This study evaluated the risk factors for the occurrence of depression from this study from multiple variables such as age,sex,and combined complications.Four machine learning algorithms(logistic regression,Lasso regression,support vector machine,random forest)were used to establish predictive classification models and compare the area under the subject operating feature curve and accuracy.The dataset was validated using a 10-fold cross-validation.Result:We excluded the invalid samples for 815 included samples,of which 570 cases were divided into the validation set and 245 cases were divided into the training set.The area under the curve(AUC)of Nomogram establishing risk of depression based on logistic regression was 0.73.Among the three machine learning models,the Lasso regression-based model AUC was 0.548,a mean AUC for support vector machines was 0.695,and a random forest AUC of 0.613.The support vector machines-based model predicted the best performance compared to other machine models.Conclusion:Random forest-based prediction models are able to assist clinicians in providing decision support when it is difficult to give an exact diagnosis.The model has good clinical utility and facilitates clinicians to identify high-risk patients and perform individualized treatment.The established four models of logistic regression,Lasso regression,support vector machine,and random forest all have good predictive power.

Month ahead average daily electricity price profile forecasting based on a hybrid nonlinear regression and SVM model:an ERCOT case study

With the deregulation of the electric power industry, electricity price forecasting plays an increasingly important role in electricity markets, especially for retailors and investment decision making. Month ahead average daily electricity price profile forecasting is proposed for the first time in this paper. A hybrid nonlinear regression and support vector machine(SVM) model is proposed. Offpeak hours, peak hours in peak months and peak hours in off-peak months are distinguished and different methods are designed to improve the forecast accuracy. A nonlinear regression model with deviation compensation is proposed to forecast the prices of off-peak hours and peak hours in off-peak months. SVM is adopted to forecast the prices of peak hours in peak months. Case studies based on data from ERCOT validate the effectiveness of the proposed hybrid method.

微胶囊相变材料改良粉砂土的导热系数及预测模型

【目的】针对季节冻土地区渠道冻融破坏,分析微胶囊相变材料(microencapsulated phase change materials,mPCM)改良粉砂土层渠基的温度场,对改良粉砂土的导热系数进行研究。【方法】以mPCM为改良剂,掺入渠基粉砂土形成mPCM改良粉砂土;对mPCM改良粉砂土进行导热系数实验和内部结构表征;采用多元线性回归和支持向量机(support vector machine,SVM)方法分别建立mPCM改良粉砂土的导热系数预测模型。【结果】mPCM改良粉砂土导热系数与含水率、干密度、mPCM掺量有关,且受冰水相对含量、冰水相变潜热、mPCM相变潜热和mPCM填充密实作用的影响,具有明显的温度效应;mPCM改良粉砂土导热系数的变化与实验温度和mPCM相变温度有关,可分为快速降低、缓慢降低和逐步上升3个阶段;多元线性回归和SVM模型均能较好地拟合预测mPCM改良粉砂土的导热系数,但SVM模型更适用于表征mPCM改良粉砂土导热系数各影响因素间的非线性关系。【结论】mPCM改良粉砂土的导热系数提高能够有效调控渠基土温度场,减轻渠道冻害,且SVM模型能更加准确地进行导热系数预测。

基于灰狼优化支持向量机回归与SHAP值的锡冶炼能耗预测

锡冶炼过程综合能源消耗占整个锡生产过程90%,存在很大节能潜力。针对锡冶炼过程综合能耗机理模型难以建立、导致预测准确度不高的问题,提出灰狼优化的支持向量机回归(GWO-SVR)模型用于锡冶炼过程综合能耗的预测,并以某锡冶炼厂为例,将所提模型与SVR、RF(随机森林)、BP(反向传播神经网络)、LR(线性回归)模型进行比较。结果表明,GWO-SVR模型可获得最理想的预测结果,在预测精度上相比于其他机器学习算法有着巨大优势。此外,使用SHAP值从全局解释和单样本解释两个方面解释所建立的GWO-SVR模型,可视化特征对输出的贡献,增加了GWO-SVR的可解释性,并以此制定可靠的节能策略。

基于逻辑回归和支持向量机耦合模型的滑坡易发性分析

滑坡灾害的发生具有累进性,进行滑坡易发性评价是防灾减灾的前提。以四川省旺苍县为例,使用频率比法判断12个滑坡影响因子的各分级区间滑坡敏感性,经波段集统计确定11个滑坡影响因子作为滑坡易发性评价因子,通过建立逻辑回归-支持向量机(logistic regression-support vector machine,LR-SVM)耦合模型,搭建滑坡易发性评价体系,完成旺苍县滑坡易发性评价并进行模型精度比较。研究结果表明:逻辑回归-支持向量机耦合模型的评价指标结果均优于逻辑回归模型,易发性分区结果更合理,预测精度更高;在低易发区选取非滑坡点为提高滑坡易发性评价性能作用明显;研究区内道路、高程和NDVI对滑坡发育的敏感性较强;高易发区主要分布于低海拔的水系和道路两侧。

基于四种算法比较分析Venlo型玻璃温室气温季节预报模型

利用2021年2月27日-2023年3月4日南京信息工程大学Venlo型玻璃温室内、外气象观测数据,基于多元回归(Multiple regression,MR)、BP人工神经网络(BP artificial neural networks,BPANN)、随机森林(Random forest,RF)和支持向量机(Support vector machine,SVM)构建温室内日平均气温、日最低气温和日最高气温的季节预报模型,并进行验证。结果表明:温室内日平均气温、日最低气温季节预报模型的拟合精度明显高于日最高气温季节预报模型;各模型对春、夏、秋季温室内气温的拟合精度高于冬季。对于日平均气温和日最低气温季节预报模型而言,4种算法构建的春、夏、秋季预报模型的拟合精度均较高,RF模型模拟效果更为稳定,其模拟值与实际观测值决定系数(R^(2))均值均在0.94以上,均方根误差(RMSE)、绝对误差(MAE)均值在1.5℃以内;对于日最高气温季节预报模型,RF模型对春、夏、秋季的拟合精度整体高于其他模型,R^(2)均值均在0.75以上。MR模型对冬季室内气温的拟合精度较好,更适用于预测冬季温室内气温。综合而言,选择RF模型预报春、夏、秋季的玻璃温室内气温,选择MR模型预报冬季玻璃温室内气温较为可行。

核泄漏事故风险评估中的概率分析及预测

文章利用逻辑回归模型(logistic regression model,LRM)、线性判别模型(linear discriminant model,LDM)和支持向量机(support vector machine,SVM)3种统计模型,从核反应堆的内部和外部因素2个方面评估其在核泄漏事故中所体现的相关安全性能。针对每种模型,利用数理统计理论探究核反应堆相关影响因素与其发生核泄漏事故的概率。研究发现核反应堆外部因素有主导内部因素的趋势并在整个核泄漏事故风险中占有举足轻重的地位。文章提供的模型分析与预测结果可为核反应堆工程师及其相关决策者在核反应堆的选址、设计及建设运营等方面提供参考。

基于3种机器学习算法构建宫颈癌术后尿潴留风险预测模型

目的:运用决策树、逻辑回归和支持向量机构建宫颈癌根治性切除术后尿潴留风险预测模型并比较性能,为评估及预防宫颈癌术后尿潴留提供参考依据。方法:回顾性收集459例宫颈癌根治性切除术病人的临床资料,采用决策树、支持向量机和逻辑回归3种机器学习方法构建宫颈癌根治性切除术后尿潴留风险预测模型,采用准确性、召回率、精确率、F1指数和受试者工作特征(ROC)曲线下面积(AUC)评价模型性能。结果:共纳入病人的年龄、疾病分期、体质指数等8个变量。选择80%的数据集(367例)作为训练集,20%的数据集(92例)作为验证集,结果显示,决策树在训练集和验证集中准确率、召回率、精确率、F1指数和AUC都比支持向量机和逻辑回归更优,说明决策树在构建宫颈癌术后尿潴留风险预测模型中具有较高的准确率及较好的泛化性能;支持向量机在训练集中准确率、召回率、精确率、F1指数和AUC都比逻辑回归更优。同时,在验证集中,支持向量机的召回率和F1指数比逻辑回归更优,但是支持向量机的准确率、精确率和AUC却比逻辑回归差,说明支持向量机在宫颈癌术后尿潴留数据集中的泛化能力比逻辑回归差。结论:决策树在构建宫颈癌根治性切除术后尿潴留风险预测模型中具有较高的性能及较好的泛化能力,可为相关临床决策提供指导建议。

基于高光谱技术的场地土壤重金属污染快速调查研究

为了准确预测场地土壤重金属分布状况,实现土壤重金属污染快速调查,以某废弃助剂厂填埋区土壤为研究对象,基于高光谱数据,利用单变量回归模型、偏最小二乘回归模型和支持向量机模型估算土壤重金属Cr、Ni、Cu、Zn、Cd、Pb、As和Hg的含量。结果表明,土壤光谱反射率与各重金属含量均呈负相关;偏最小二乘回归模型和支持向量机模型对8种重金属的预测精度均优于单变量回归模型,偏最小二乘回归模型为Cd、Pb、Cr和Ni的最佳估算模型,支持向量机模型为Cu、As、Zn和Hg的最佳预测模型;研究区土壤重金属反演结果在趋势上与实验室分析结果基本一致,高值区和极值点分布亦较为吻合,能够圈定存在重金属污染风险的区域,同时提供技术支撑,实现场地土壤重金属污染的快速调查。