检索结果-内蒙古大学图书馆

Performance Evaluation of support vector regression machine Models in Water Level Forecasting

Procedia Computer Science 2024年 234卷 436-447页

作者： Lemuel Clark Velasco Alyssa Jenn Estose Melcris Opon Emily Tabanao Floremie Apdian Mindanao State University-Iligan Institute of Technology Iligan City The Philippines Premiere Research Institute of Science and Mathematics – Center for Computational Analytics and Modelling Mindanao State University at Naawan Naawan Misamis Oriental The Philippines

Understanding and predicting water level rise is crucial for effective water resource management, flood control, disaster risk reduction, and adaptation to climate change. This study utilize the use of support vector regression machine (SVRM) models in predicting the water level of Mandulog River in the Philippines. To evaluate its predictive capability, two data architectures, various kernels, and parameters were examined to find the optimal configuration. Multiple kernels were compared for accurate pattern discovery, and parameter selection was performed to enhance predictive accuracy. The SVRM models achieved the lowest Mean Average Percentage Error (MAPE) of 2.186%, Root-Mean Squared Error (RMSE) of 0.00601 during the dry season, and MAPE of 2.226% and RMSE of 0.00602 during the rainy season. Both models were deemed suitable for watershed level forecasting.

关键词： Performance Analysis support vector machines support vector regression machine Watershed Level Forecasting Water Level Forecasting

来源：评论

学校读者我要写书评

暂无评论

Interfacial Friction Prediction in a Vertical Annular Two-Phase Flow Based on support vector regression machine

引用

WATER 2021年第24期13卷 3609页

作者： Liu, Qiang Feng, Xingya Chen, Junru Southern Univ Sci & Technol Dept Ocean Sci & Engn Shenzhen 518055 Peoples R China Southern Marine Sci & Engn Guangdong Lab Guangzho Guangzhou 511458 Peoples R China

Accurate prediction of interfacial friction factor is critical for calculation of pressure drop and investigation of flow mechanism of vertical annular two-phase flows. Theoretical models of interfacial friction factor based on physical insight have been developed;however, these are inconvenient in engineering practice as too many parameters need to be measured. Although many researchers have proposed various empirical correlations to improve computation efficiency, there is no generally accepted simple formula. In this study, an efficient prediction model based on support vector regression machine (SVR) is proposed. Through sensitivity analysis, five factors are determined as the input parameters to train the SVR model, relative liquid film thickness, liquid Reynolds number, gas Reynolds number, liquid Froude number and gas Froude number. The interfacial friction factor is chosen as the output parameter to check the overall performance of the model. With the help of particle swarm algorithm, the optimization process is accelerated considerably, and the optimal model is obtained through iterations. Compared with other correlations, the optimal model shows the lowest average absolute error (AAE of 0.0004), lowest maximum absolute error (MAE of 0.006), lowest root mean square error (RMSE of 0.00076) and highest correlation factor (r of 0.995). The analysis using various data in the literature demonstrates its accuracy and stability in interfacial friction prediction. In summary, the proposed machine learning model is effective and can be applied to a wider range of conditions for vertical annular two-phase flows.

关键词： vertical annular two-phase flow interfacial friction factor support vector regression machine particle swarm algorithm

来源：评论

学校读者我要写书评

暂无评论

A 2-D empirical plasma sheet pressure model for substorm growth phase using the support vector regression machine

引用

JOURNAL OF GEOPHYSICAL RESEARCH-SPACE PHYSICS 2015年第3期120卷 1957-1973页

作者： Yue, Chao Wang, Chih-Ping Lyons, Larry Wang, Yongli Hsu, Tung-Shin Henderson, Michael Angelopoulos, Vassilis Lui, A. T. Y. Nagai, Tsugunobu Univ Calif Los Angeles Dept Atmospher & Ocean Sci Los Angeles CA 90089 USA Univ Maryland Baltimore Cty Goddard Planetary Heliophys Inst Baltimore MD USA Univ Calif Los Angeles Dept Earth & Space Sci Los Angeles CA 90024 USA Los Alamos Natl Lab Space Sci & Applicat Los Alamos NM USA Johns Hopkins Univ Appl Phys Lab Laurel MD USA Tokyo Inst Technol Dept Earth & Planetary Sci Tokyo 152 Japan

The plasma sheet pressure and its spatial structure during the substorm growth phase are crucial to understanding the development and initiation of substorms. In this paper, we first statistically analyzed the growth phase pressures using Geotail and Time History of Events and Macroscale Interactions during Substorms data and identified that solar wind dynamic pressure (P-SW), energy loading, and sunspot number as the three primary factors controlling the growth phase pressure change. We then constructed a 2-D equatorial empirical pressure model and an error model within r20R(E) using the support vector regression machine with the three factors as input. The model predicts the plasma sheet pressure accurately with median errors of 5%, and predicted pressure gradients agree reasonably well with observed gradients obtained from two-probe measurements. The model shows that pressure increases linearly as P-SW increases, and the P-SW effect is stronger under lower energy loading. However, the pressure responses to energy loading and sunspot number are nonlinear. The pressure increases first with increasing loading or sunspot number, then remains relatively constant after reaching a peak value at similar to 8000kVmin loading or sunspot number of similar to 80. The loading effect is stronger when P-SW is lower and the pressure variations are stronger near midnight than away from midnight. The sunspot number effect is clearer at smaller r. The pressure model can also be applied to understand the pressure changes observed during a substorm event by providing evaluations of the effects of energy loading and P-SW, as well as the temporal and spatial effects along the spacecraft trajectory.

关键词： plasma sheet pressure model substorm growth phase support vector regression machine

来源：评论

学校读者我要写书评

暂无评论

The Nonlinear Correction Model Research based on Wavelet support vector regression machine Sensor

The Nonlinear Correction Model Research based on Wavelet Sup...

引用

作者： Ning TIAN Yongsheng WAN School of Mechanical and Electrical Engineering Southwest Petroleum University

In view of the sensor due to factors such as aging, drift, temperature change caused by the sensor input and output of nonlinear problems, the support vector machine(SVM) based on wavelet kernel data correction, the nonlinear data correction method and constructed based on wavelet support vector machine(SVM) model for the nonlinear data correction. Through the Matlab simulation results show that the calibration results based on the wavelet support vector machine(SVM) is better than RBF and polynomial kernel correction, provides a very good method for sensor nonlinear correction, which has extensive promotion of significance.

关键词： Sensors Wavelet kernel support vector regression machine Nonlinear correction

来源：评论

学校读者我要写书评

暂无评论

Forecasting of Electricity Load Based on Improved Particle Swarm Optimization and support vector regression machine

Forecasting of Electricity Load Based on Improved Particle S...

引用

2015 International Conference on Test, Measurement and Computational Method (TMCM 2015)

作者： Limei Liu Department of basic education Shenyang Institute of Engineering

ISBN: (纸本)9781510817388

support vector regression machine is suitable for small sample decision and it is good to data forecasting capabilities. Its nature of learning method is under the condition of limited information to obtain a good ability in data mining. Accurate electricity load forecasting is an important practical value to our lives. This paper presents a new algorithm that is an improved particle swarm optimization algorithm and support vector regression machine that is proposed to predict electricity load. It is of great significance to forecasting electricity load. The algorithm can optimize training parameters of support vector regression machine by improved particle swarm optimization algorithm. The simulation experimental results indicate that the new algorithm made a meaningful exploration on forecasting electricity load.

关键词： power system support vector regression machine forecasting of electricity load improved particle swarm optimization

来源：评论

学校读者我要写书评

暂无评论

An e-E-insensitive support vector regression machine

引用

COMPUTATIONAL STATISTICS 2014年第6期29卷 1447-1468页

作者： Safari, Amir Cent Insurance IR Iran Tehran Iran

According to the Statistical Learning Theory, the support vectors represent the most informative data points and compress the information contained in training set. However, a basic problem in the standard support vector machine is that when the data is noisy, there exists no guaranteed scheme in support vector machines' formulation to dissuade the machine from learning noise. Therefore, the noise which is typically presents in financial time series data may be taken into account as support vectors. In turn, noisy support vectors are modeled into the estimated function. As such, the inclusion of noise in support vectors may lead to an over-fitting and in turn to a poor generalization. The standard support vector regression (SVR) is reformulated in this article in such a way that the large errors which correspond to noise are restricted by a new parameter . The simulation and real world experiments indicate that the novel SVR machine meaningfully performs better than the standard SVR in terms of accuracy and precision especially where the data is noisy, but in expense of a longer computation time.

关键词： Financial time series Loss function Noise process support vector regression machine

来源：评论

学校读者我要写书评

暂无评论

Dynamic Modeling of SOFC Based on support vector regression machine and Improved Particle Swarm Optimization 11

Dynamic Modeling of SOFC Based on Support Vector Regression ...

引用

11th World Congress on Intelligent Control and Automation

作者： Huo, Haibo Ji, Yi Kuang, Xinghong Liu, Yuqing Wu, Yanxiang Shanghai Ocean Univ Dept Elect Engn Shanghai 201306 Peoples R China

ISBN: (纸本)9781479958252

For predicting the electrochemical and heat transfer dynamics synchronously, a dynamic identification model of the solid oxide fuel cell (SOFC) is reported. In this study, support vector regression machine (SVRM) is proposed to model the nonlinear dynamic characteristics of the SOFC. In addition, a kind of improved particle swarm optimization (IPSO) is preferably chosen for the parameter optimization of the SVRM model. The applicability of the proposed SVRM with IPSO (IPSO-SVRM) model in modeling the voltage and the temperature transient responses to the hydrogen input flow rate change of the SOFC is illustrated by the simulation. Furthermore, the comparisons between the IPSO-SVRM model and the SVRM model are provided which show a substantially better performance for the IPSO-SVRM model. The results also show that IPSO algorithm outperforms the crossover validation method in terms of parameters choice of the SVRM model.

关键词： Solid oxide fuel cell Dynamic modeling support vector regression machine Particle swarm optimization

来源：评论

学校读者我要写书评

暂无评论

Some support vector regression machines with Given Empirical Risks Partly

引用

电脑学刊 2022年第5期33卷 61-72页

作者： Lin-Kai Luo Chao-Jie Xu Ling-Jun Ye Hong Peng

There are often some prior requirements about empirical risk in regression problems. To meet these requirements, this paper firstly proposes two novel support vector regression machine models in which part of empirical risks are given. One is a support vector regression machine in which partial empirical risks are given (PSVR), and the other is a model in which unilateral partial empirical risks are given (UPSVR). For the samples with given empirical risk levels, PSVR meets the requirements by some inequality constraints about empirical risk levels, while for the other samples without empirical risk requirement, PSVR uses the same strategy as the tradition support vector regression (SVR) to meet the requirement of empirical risk. UPSVR is similar to PSVR, except that the inequality constrains of empirical risks are unilateral. Secondly, the dual problems and the solving methods of PSVR and UPSVR are given. Finally, the effectiveness and superiority of PSVR and UPSVR are verified by the experiments on four artificial datasets. Both PSVR and UPSVR achieve better regression performance than the traditional models respectively. At the same time, PSVR is less sensitive to the trade-off coefficient C between empirical risk and confident risk compared with SVR. Thus, PSVR can select parameter C faster and more conveniently. PSVR and UPSVR are the extensions of the traditional models. When the set of samples with given empirical risks is empty, they degenerate into the traditional models. PSVR and UPSVR are suitable for the scene with prior requirements of empirical risk.

关键词： support vector regression machine partial empirical risks confidence risk unilateral empirical risk

来源：评论

学校读者我要写书评

暂无评论

A hybrid-forecasting model reducing Gaussian noise based on the Gaussian support vector regression machine and chaotic particle swarm optimization

引用

INFORMATION SCIENCES 2013年 238卷 96-110页

作者： Wu, Qi Law, Rob Wu, Edmond Lin, Jinxing Shanghai Jiao Tong Univ Sch Aeronaut & Astronaut Shanghai 200040 Peoples R China Hong Kong Polytech Univ Sch Hotel & Tourism Management Kowloon Hong Kong Peoples R China Sun Yat Sen Univ Sch Tourism Management Guangzhou 510275 Guangdong Peoples R China Nanjing Univ Posts & Telecommun Coll Automat Nanjing 210046 Jiangsu Peoples R China

In this paper, the relationship between Gaussian noise and the loss function of the support vector regression machine (SVRM) is analyzed, and then a Gaussian loss function proposed to reduce the effect of such noise on the regression estimates. Since the epsilon-insensitive loss function cannot reduce noise, a novel support vector regression machine: g-SVRM, is proposed, then a chaotic particle swarm optimization (CPSO) algorithm developed to estimate its unknown parameters. Finally, a hybrid-forecasting model combining g-SVRM with the CPSO is proposed to forecast a multi-dimensional time series. The results of two experiments demonstrate the feasibility of this approach. (C) 2013 Elsevier Inc. All rights reserved.

关键词： support vector regression machine Gaussian loss function Particle swarm optimization Chaotic mapping Forecast

来源：评论

学校读者我要写书评

暂无评论

A new three-dimensional magnetopause model with a support vector regression machine and a large database of multiple spacecraft observations

引用

JOURNAL OF GEOPHYSICAL RESEARCH-SPACE PHYSICS 2013年第5期118卷 2173-2184页

作者： Wang, Y. Sibeck, D. G. Merka, J. Boardsen, S. A. Karimabadi, H. Sipes, T. B. Safrankova, J. Jelinek, K. Lin, R. NASA Goddard Space Flight Ctr Heliophys Sci Div Greenbelt MD 20771 USA Univ Maryland Goddard Planetary Heliophys Inst Baltimore MD 21201 USA SciberQuest Inc Del Mar CA USA Charles Univ Prague Fac Math & Phys Prague Czech Republic Chinese Acad Sci Natl Space Sci Ctr Beijing Peoples R China

We present results from a new three-dimensional empirical magnetopause model based on 15,089 magnetopause crossings from 23 spacecraft. To construct the model, we introduce a support vector regression machine (SVRM) technique with a systematic approach that balances model smoothness with fitting accuracy to produce a model that reveals the manner in which the size and shape of the magnetopause depend upon various control parameters without any assumptions concerning the analytical shape of the magnetopause. The new model fits the data used in the modeling very accurately, and can guarantee a similar accuracy when predicting unseen observations within the applicable range of control parameters. We introduce a new error analysis technique based upon the SVRM that enables us to obtain model errors appropriate to different locations and control parameters. We find significant east-west elongations in the magnetopause shape for many combinations of control parameters. Variations in the Earth's dipole tilt can cause significant magnetopause north/south asymmetries and deviation of the magnetopause nose from the Sun-Earth line nonlinearly by as much as 5Re. Subsolar magnetopause erosion effect under southward IMF is seen which is strongly affected by solar wind dynamic pressure. Further, we find significant shrinking of high-latitude magnetopause with decreased magnetopause flaring angle during northward IMF.

关键词： magnetopause empirical model support vector regression machine dipole tilt erosion

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：