检索结果-内蒙古大学图书馆

Heat consumption forecasting using partial least squares, artificial neural network and support vector regression techniques in district heating systems

引用

KOREAN JOURNAL OF CHEMICAL ENGINEERING 2010年第4期27卷 1063-1071页

作者： Park, Tae Chang Kim, Ui Sik Kim, Lae-Hyun Jo, Byung Wan Yeo, Yeong Koo Hanyang Univ Dept Chem Engn Seoul 133791 South Korea Seoul Natl Univ Technol Dept Chem Engn Seoul 135743 South Korea Hanyang Univ Dept Civil Engn Seoul 133791 South Korea

Effective management of district heating networks depends upon the correct forecasting of heat consumption during a certain period. In this work short-term forecasting for the amount of heat consumption is performed first to validate the three forecasting methods: partial least squares (PLS) method, artificial neural network ( ANN), and support vector regression (SVR) method. Based on the results of short-term forecasting, one-week ahead forecasting was performed for the Suseo district heating network. Data of heat consumption and ambient temperature during January and February in 2007 and 2008 were employed as training elements. The heat consumption estimated was compared with actual one in the Suseo area to validate the forecasting models.

关键词： Partial Least Squares Artificial Neural Network supporting vector regression Heat Forecasting

来源：评论

学校读者我要写书评

暂无评论

A comparative study of wind-induced dynamic response models of long-span bridges using artificial neural networks, support vector regression and buffeting theory

引用

JOURNAL OF WIND ENGINEERING AND INDUSTRIAL AERODYNAMICS 2021年 209卷 104484-104484页

作者： Castellon, Dario Fernandez Fenerci, Aksel oiseth, Ole Norwegian Univ Sci & Technol Dept Struct Engn Trondheim Norway

Long-span cable-supported bridges are structures susceptible to high dynamic responses due to the buffeting phenomenon. The current state-of-the-art method for buffeting response estimation is the buffeting theory. However, previous research has shown discrepancies between buffeting theory estimates and full-scale measured response, revealing a weakness in the theoretical models. In cases where wind and structural health monitoring data are available, machine learning algorithms may enhance the buffeting response estimation speed with less computational effort by bypassing the analytical model's assumptions. In this paper, multilayer perceptron and support vector regression models were trained with synthetic and full-scale measured data from the Hardanger Bridge. The analytical response was also computed from buffeting theory applied to a finite element model of the bridge, and the estimates are compared. The prediction accuracy was evaluated with the normalized root mean square error, the mean absolute percent error and the coefficient of determination (R2). The machine learning models trained with synthetic datasets achieved very high accuracy with normalized root mean square errors ranging from 1.46E-04 to 7.21E-03 and are therefore suitable for efficient surrogate modeling. Further, the support vector regression model trained with the full-scale measured dataset achieved the best accuracy compared with the other methods.

关键词： Long-span bridges Full-scaled measurements Buffeting response Multilayer perceptron supporting vector regression

来源：评论

学校读者我要写书评

暂无评论

Using machine learning to trace the pollution sources of disinfection by-products precursors compared to receptor models

引用

SCIENCE OF THE TOTAL ENVIRONMENT 2024年 914卷 169671页

作者： Xiao, Yuan Ma, Shunjun Yang, Shumin He, Huan He, Xin Li, Cheng Feng, Yuheng Xu, Bin Tang, Yulin Tongji Univ Key Lab Urban Water Supply Water Saving & Water En Minist Water Resources Shanghai 200092 Peoples R China Shanghai Pudong Water Grp Shanghai 201300 Peoples R China Tongji Univ Thermal & Environm Engn Inst Sch Mech Engn 1239 Siping Rd Shanghai 200092 Peoples R China

To increase the efficiency of managing backup water resources, it is critical to identify and allocate pollution sources. Source apportionment of dissolved organic matter (DOM) was investigated in our work. Parallel factor analysis (PARAFAC) and the Spearman correlation analysis were used for source identification. After that, a newly hybrid model applying the fuzzy c -means and support vector regression (FCM-SVR) was employed for source apportionment compared to receptor models. The results demonstrated that the FCM-SVR model exhibited excellent generalization, and only required standardization and normalization as pre-processing steps for dataset. According to the results, microbial sources played a key role (28.1 %) in the formation potential of disinfection byproducts (DBPFPs). Additionally, shipping marine sources exhibited a substantial contribution (21.2 %) to DBPFPs. The prediction accuracy of DBPFPs was matched or exceeded receptor models, and the R2 of DOC (0.884) was significantly high. Therefore, we recommend the FCM-SVR model combined with PARAFAC to trace the source of DBPFPs as its significant effectiveness in source identification, source apportionment, and prediction accuracy, possessing the potential for further applicability in tracking more organic compounds. Environmental implication: The disinfection byproducts precursors in water sources, which were thought to be hazardous materials in this study, are proved to be chlorinated into carcinogenic disinfection byproducts (DBPs) during drinking water treatment, However, the source apportionment methods of DBPs are not well developed compared to other inorganic matter, e.g., heavy metals and ammonia nitrogen. We proposed a new FCM-SVR model to trace the source of DBPs, which required easier pre-treatment and resulted a better source apportionment and prediction accuracy. As a result, it could provide a different prospect and useful management advices to trace the source of DBPs.

关键词： Source apportionment Parallel factor analysis Machine learning Fuzzy clustering algorithm supporting vector regression

来源：评论

学校读者我要写书评

暂无评论

Different-resolution solar radiation prediction with accompanying microclimate data and long-term monitoring experiment by LSTM, RF, and SVR: a case of campus area

引用

JOURNAL OF ASIAN ARCHITECTURE AND BUILDING ENGINEERING 2024年第5期23卷 1677-1698页

作者： Wang, Haining Lin, Qi Wei, Hailu Du, Jian Wang, Wei Luo, Zhixing Southeast Univ Sch Architecture Nanjing Jiangsu Peoples R China NYU Tandon Sch Engn Brooklyn NY USA Xian Univ Architecture & Technol Coll Architecture Xian Shanxi Peoples R China Southeast Univ Sch Architecture Sipailou 2 Nanjing Jiangsu Peoples R China

Solar radiation plays a pivotal role in urban microclimate, significantly, impacting building energy consumption and renewable energy utilization. Utilizing a comprehensive three- and-a- half-year dataset of high-precision urban microclimate, this study proposes a three-step approach to solar radiation prediction: 1) Data Preprocessing and Characterization: The microclimate data are meticulously preprocessed and categorized, with solar radiation values categorized into three resolutions: total daily solar radiation, hourly solar radiation, and 30-min solar radiation. 2) Feature Selection: Various climatic parameters are carefully selected for solar radiation prediction at different resolutions. 3) Machine Learning Models: Three machine learning models, namely Long Short-Term Memory (LSTM), Random Forest (RF) and Support vector regression (SVR), are employed for solar radiation prediction. The results show that all three models exhibit prediction accuracy with closely matched errors. Particularly noteworthy findings include SVR's superior performance in predicting total daily solar radiation with a minimal error rate of about 6.0% and an impressive coefficient of determination of 0.9789. LSTM exhibits adaptability, achieving R2 values of 0.9906 and 0.9956 for hourly and 30-min radiation predictions, respectively. This study offers valuable insights into solar radiation and its implications for building energy research. It underscores that large datasets enable accurate solar radiation predictions, even when excluding certain parameters like daily maximum temperature and relative humidity.

关键词： Urban microclimate solar radiation prediction Long short time memory Random forest supporting vector regression

来源：评论

学校读者我要写书评

暂无评论

Reliability assessment method based on the meta-action unit for complex mechanical system

引用

JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY 2023年第3期37卷 1233-1242页

作者： Zhu, Xiao Ran, Yan Li, Xinglong Chongqing Univ Coll Mech & Vehicle Engn Chongqing 400044 Peoples R China State Key Lab Mech Transmiss Chongqing 400044 Peoples R China

In this paper, a functionality unit named as meta-action unit (MAU) is proposed to correlate the system function with the part actions and assess reliability of mechanical system. Firstly, the function of system is decomposed into multiple MAUs by function-movement-action (FMA). Then, the lifetime of MAU is fitted by Weibull distribution, and its parameters are estimated by support vector regression (SVR). In addition, taking the distributions of MAU as marginal distributions, the lifetime distribution of mechanical system is constructed by copula function to assess system reliability, and its parameters are estimated using the maximum likelihood estimator (MLE). Further, the reliability assessment accuracy based on MAU is compared with that from traditional method based on mechanical part failure modes. Finally, the reliability assessment of the indexing turntable (IT) is performed as an example to illustrate the feasibility and reasonability of the proposed method.

关键词： Copula function Lifetime distribution Meta-action unit Reliability assessment supporting vector regression

来源：评论

学校读者我要写书评

暂无评论

Estimating atmospheric visibility using synergy of MODIS data and ground-based observations 3

Estimating atmospheric visibility using synergy of MODIS dat...

引用

3rd Remote Sensing and Hydrology Symposium (RSHS 14) / 3rd International Conference of GIS/RS in Hydrology, Water Resources and Environment (ICGRHWE 14)

作者： Komeilian, Hossein Bateni, S. Mohyeddin Xu, Tongren Nielson, Jeffrey Beijing Normal Univ Res Ctr Remote Sensing & GIS State Key Lab Remote Sensing Sci Beijing 100875 Peoples R China Beijing Normal Univ Sch Geog Beijing 100875 Peoples R China Tarbiat Modares Univ Dept Civil & Environm Engn Al E Ahmad 11369 Tehran Province Iran Univ Hawaii Manoa Dept Civil & Environm Engn Honolulu HI 96822 USA Univ Hawaii Manoa Water Resource Res Ctr Honolulu HI 96822 USA

ISBN: (纸本)9781907161469

Dust events are intricate climatic processes, which can have adverse effects on human health, safety, and the environment. In this study, two data mining approaches, namely, back-propagation artificial neural network (BP ANN) and supporting vector regression (SVR), were used to estimate atmospheric visibility through the synergistic use of Moderate Resolution Imaging Spectroradiometer (MODIS) Level 1B (LIB) data and ground-based observations at fourteen stations in the province of Khuzestan (southwestern Iran), during 2009-2010. Reflectance and brightness temperature in different bands (from MODIS) along with in situ meteorological data were input to the models to estimate atmospheric visibility. The results show that both models can accurately estimate atmospheric visibility. The visibility estimates from the BP ANN network had a root-mean-square error (RMSE) and Pearson's correlation coefficient (R) of 0.67 and 0.69, respectively. The corresponding RMSE and R from the SVR model were 0.59 and 0.71, implying that the SVR approach outperforms the BP ANN.

关键词： atmospheric visibility MODIS data back-propagation artificial neural network supporting vector regression

来源：评论

学校读者我要写书评

暂无评论

MACHINE-LEARNING BASED HIGH EFFICIENCY RATE CONTROL FOR AV1 5

MACHINE-LEARNING BASED HIGH EFFICIENCY RATE CONTROL FOR AV1

引用

IEEE 5th International Conference on Multimedia Information Processing and Retrieval (MIPR)

作者： Chen, Yi Mao, Yunhao Wang, Shiqi Zhang, Xianguo Kwong, Sam City Univ Hong Kong Dept Comp Sci Kowloon Hong Kong Peoples R China Tencent Shannon Lab TEG Beijing Peoples R China

ISBN: (数字)9781665495486

ISBN: (纸本)9781665495486

Recent years have witnessed the increasing demand of video coding technologies, which have been continuously developed to meet various requirements in video-related applications. Developed by Alliance for Open Media (AOM), the AOMedia Video 1 (AV1) is an open-source and royalty-free standard. Herein, we achieve high efficiency rate control for AV1 based on the machine-learning model, which establishes the rate-quantization relationship in a data-driven manner. More specifically, the supporting vector regression (SVR) is used for rate model parameter estimation. The model is trained using sufficient training data, and incorporated in the encoder. Compared to the default rate control scheme in AV1, experimental results have shown that 2.01% bitrate could be saved with tolerable bitrate error.

关键词： Video coding supporting vector regression Quantization parameter (QP) Rate control

来源：评论

学校读者我要写书评

暂无评论

A hybrid model based on neural networks for financial time series

A hybrid model based on neural networks for financial time s...

引用

12th Mexican International Conference on Artificial Intelligence (MICAI)

作者： Huang, Dong Wang, Xiaolong Fang, Jia Liu, Shiwen Dou, Ronggang Harbin Inst Technol Shenzhen Grad Sch Comp Sci & Technol Dept Shenzhen Peoples R China

ISBN: (纸本)9781479926053;9781479926046

Because of their fuzzy and non-stationary nature, financial time series forecasting is still a challenge. In this paper, we propose and implement a hybrid model by combining the Maximum Entropy (ME), Support vector regression (SVR) and Trend model based on Artificial neural networks (ANNs) for forecasting financial time series. The approach contains three steps: feature and time alignment in data preprocessing, adopting ME, SVR and Trend model for different features as the input for ANNs, and obtaining the final predicted value using Back Propagation algorithm. The feature selection flexibility of ME and global optimality of SVR make the input model better because of its different features, which helps to have a better forecasting accuracy of ANN sin proposed model. Experimental results clearly show that the accuracy of prediction for Chinese closed-end fund net value can achieve 98.3% using the hybrid model, which is more accurate than some institutions or known financial websites in China, and we provide the prediction of real time fund net value for free in our Hai tianyuan knowledge service platformhttp://***.

关键词： Financial time series supporting vector regression Artificial neural network Maximum entropy Fund net value

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Enabled Repurposing and Design of Antifouling Polymer Brushes

引用

CHEMICAL ENGINEERING JOURNAL 2021年第Part1期420卷 129872-129872页

作者： Liu, Yonglan Zhang, Dong Tang, Yijing Zhang, Yanxian Gong, Xiong Xie, Shaowen Zheng, Jie Univ Akron Dept Chem Biomol & Corros Engn Akron OH 44325 USA Univ Akron Dept Polymer Engn Akron OH 44325 USA Hunan Univ Technol Coll Life Sci & Chem Hunan Key Lab Biomed Nanomat & Devices Zhuzhou 412007 Peoples R China

Rational development of antifouling materials is of great importance for fundamental research and real-world applications. However, current experimental designs and computational modelings of antifouling materials still retain empirical flavor due to the data complexity of polymers and their associated structures/properties. In this work, we developed a data-driven, machine learning workflow, in combination with an in-house benchmark dataset of antifouling polymer brushes, to discover the potential antifouling property of existing polymer brushes using the descriptor-based artificial neural network (ANN) model and design the new antifouling polymer brushes using the group-based supporting vector regression (SVR) model. The resultant two machine learning models not only demonstrated their reliability, predictivity, and applicability, but also established the composition-structure-property relationships using both descriptors and functional groups. Finally, we synthesized different repurposed and newly designed polymer brushes, as predicted by ANN and SVR models, all of which exhibited excellent surface resistance to protein adsorption from undiluted human blood serum and plasma at optimal film thicknesses. Overall, our data-driven machine learning models can be used as an intelligent tool for determining, repurposing, and designing new superior antifouling materials beyond polymer brushes.

关键词： Machine learning Antifouling Polymer brush Protein adsorption Artificial neural network supporting vector regression

来源：评论

学校读者我要写书评

暂无评论

Gradient boosting decision tree in the prediction of NOX emission of waste incineration

引用

ENERGY 2023年 264卷

作者： Ding, Xiaosong Feng, Chong Yu, Peiling Li, Kaiwen Chen, Xi Beijing Foreign Studies Univ Int Business Sch Beijing 100089 Peoples R China Stockholm Univ Dept Comp & Syst Sci DECIDE SE-16407 Kista Sweden Jiangsu Amber Environm Technol Co Ltd Nanjing 211101 Jiangsu Peoples R China Univ Penn Sch Engn & Appl Sci Dept Elect & Syst Engn Philadelphia PA 19104 USA Univ Iowa Tippie Coll Business Dept Management Sci Iowa City IA 52242 USA

This paper investigates the real-time prediction of nitrogen oxides (NOX) emission by using around 17000 samples involved in a collection of three-day real data from a waste incineration power plant. To disclose the relationship between the ammonia (NH3) ejection and NOX emission, we choose the NOX reduction from inlet to outlet rather than the NOX concentration monitored by continuous emission monitoring system (CEMS). A hybrid procedure is developed to select appropriate features from the large and unsynchronized data, with which we establish a model based on the gradient boosting decision tree (GBDT) for the prediction. Computational experiments demonstrate that, with root mean square error (RMSE) values being 1.851 and 3.593 for training and test data, respectively, GBDT outperforms its two popular counterparts, supporting vector regression (SVR) and long short-term memory (LSTM). Shapley additive explanations (SHAP) is also conducted for analysis.

关键词： Waste incineration supporting vector regression Long short-term memory Gradient boosting decision tree Feature selection Nitrogen oxides emission

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：