检索结果-内蒙古大学图书馆

Multi-step ahead forecasting of heat load in district heating systems using machine learning algorithms

ENERGY 2019年 188卷 116085-000页

作者： Xue, Puning Jiang, Yi Zhou, Zhigang Chen, Xin Fang, Xiumu Liu, Jing Harbin Inst Technol Sch Architecture 73 Huanghe Rd Harbin 150000 Heilongjiang Peoples R China Harbin Inst Technol Key Lab Cold Reg Urban & Rural Human Settlement E Minist Ind & Informat Technol Harbin 150000 Heilongjiang Peoples R China Heilongjiang Prov Comp Ctr 600 Chuangxinsan Rd Harbin 150026 Heilongjiang Peoples R China

Predicting next-day heat load curves is essential to guarantee sufficient heat supply and optimal operation of district heat systems (DHSs). Existing studies have mainly investigated one-step ahead forecasting methods, which can predict a single value at a future time step. To predict heat load curves, multi-step ahead forecasting methods are needed. This study proposes a machine learning-based framework for multi-step ahead DHS heat load forecasting. Specifically, support vector regression, deep neural network, and extreme gradient boosting (XGBoost) are respectively used as the base learner to develop forecasting models. Two multi-step ahead forecasting methods, i.e. direct strategy and recursive strategy, adopt the learnt models to generate predictions. A DHS in China is used as the case study to comprehensively assess the performance of these two forecasting strategies. Recursive strategy using the XGBoost-based forecasting model can achieve the most accurate and stable predictions with a value of 10.52% for the coefficient of variation of root mean square error. Furthermore, the modeling process of recursive strategy is much more convenient than that of direct strategy. The research shows that the recursive strategy is a better solution to multi-step ahead forecasting than the direct strategy with respect to accuracy, prediction stability, and modeling process. (C) 2019 Elsevier Ltd. All rights reserved.

关键词： District heating Heat load forecasting Multi-step ahead forecasting Direct strategy Recursive strategy machine learning algorithms

来源：评论

学校读者我要写书评

暂无评论

How do 2D/3D urban landscapes impact diurnal land surface temperature: Insights from block scale and machine learning algorithms

引用

SUSTAINABLE CITIES AND SOCIETY 2023年 99卷

作者： Han, Dongrui An, Hongmin Cai, Hongyan Wang, Fei Xu, Xinliang Qiao, Zhi Jia, Kun Sun, Zongyao An, Ying Shandong Acad Agr Sci Inst Agr Informat & Econ Jinan 250100 Peoples R China Shandong Univ Sch Management Jinan 250100 Peoples R China Chinese Acad Sci Inst Geog Sci & Nat Resources Res State Key Lab Resources & Environm Informat Syst Beijing 100101 Peoples R China Tianjin Univ Sch Environm Sci & Engn Tianjin 300350 Peoples R China Shandong Jianzhu Univ Sch Management Engn Jinan 250101 Peoples R China Tianjin Univ Sch Architecture Tianjin 300272 Peoples R China 92 Weijin Rd Tianjin 300072 Peoples R China

Urban landscapes significantly affect land surface temperature (LST) and are considered crucial factors affecting urban heat island (UHI). The impacts of urban landscapes on LST have been extensively explored, mainly focusing on grid scale and the daytime. However, how 2D/3D urban landscapes affect diurnal LST at the block scale is unclear. Therefore, taking 1, 536 blocks (including low-rise blocks (LRB), middle-rise blocks (MRB), and high-rise blocks (HRB)) in Beijing as samples, the performances of boosted regression tree (BRT) and random forest (RF) were first evaluated, and the impacts of 2D/3D urban landscapes on diurnal LST across different block types were explored. The results showed that the mean LST was the highest in MRB (daytime) and HRB (nighttime). BRT performed better than RF in investigating diurnal impacts at the block scale. Vegetation and buildings are the domain factors influencing daytime and nighttime LST in LRB and MRB, while buildings are the domain factor in HRB except at 03:09 (impervious surface). The relationships between the key 2D/3D urban landscape metrics and block diurnal LST are nonlinear. The findings can serve as f basis for UHI mitigation and urban renewal strategies by urban planners to develop thermal comfort.

关键词： Urban landscapes Diurnal land surface temperature Block scale machine learning algorithms Urban heat island

来源：评论

学校读者我要写书评

暂无评论

Analysis and prediction of rockburst intensity using improved D-S evidence theory based on multiple machine learning algorithms

引用

TUNNELLING AND UNDERGROUND SPACE TECHNOLOGY 2023年第1期140卷

作者： Qiu, Daohong Li, Xuebing Xue, Yiguo Fu, Kang Zhang, Wenqing Shao, Tao Fu, Yusong Shandong Univ Geotech & Struct Engn Res Ctr Jinan 250061 Peoples R China China Univ Geosci Beijing Sch Engn & Technol Beijing 100083 Peoples R China

Accurate prediction of rockburst hazards is an effective means to improve the development and utilization of underground space. When using a single machine learning algorithm for rockburst prediction, the reliability of the classification results can hardly be guaranteed. In this paper, a fusion model for rockburst prediction based on multiple machine learning algorithms is proposed in combination with D-S evidence theory. Six characteristic parameters (& sigma;& theta;, & sigma;c, & sigma;t, SR, BR and Wet) were statistically analyzed for 304 sets of rockburst cases, and the data had outliers and class imbalances. The box plot method was used to detect replacement of a small number of outliers, and the Adasyn oversampling method eliminated the effect of data class imbalance. The visualization of the data by using the t-SNE method showed improved classifiability. SVM, BP, RBF, RF and ELM rockburst prediction models were developed with the six characteristic parameters as model inputs. In addition, the global optimization algorithms were used to find the optimal hyperparameters of the five machine learning algorithms. The accuracy of the optimized models was improved by 2.63%, 5.27%, 2.63%, 6.58% and 7.5% compared to the unoptimized models. Based on the prediction results, the precision was proposed as the fusion index. Additionally, based on improved D-S evidence theory, a fusion model for rockburst prediction was developed with five optimized machine learning algorithm models as base classifiers. Finally, the fusion model was applied to the rockburst prediction of Jiangbian Hydropower Station and Sanshan Island Gold Mine in China with the accuracy of 92.86%, and the prediction was outperformed by a single base classifier. The fusion model compensated for the uncertainty and poor robustness of the prediction results of the single-base classifier, and improved the accuracy and reliability of rockburst prediction.

关键词： Rockburst prediction Rockburst level machine learning algorithms D-S evidence theory Fusion model

来源：评论

学校读者我要写书评

暂无评论

Detection of malicious software by analyzing the behavioral artifacts using machine learning algorithms

引用

INFORMATION AND SOFTWARE TECHNOLOGY 2020年第0期121卷 106273-000页

作者： Singh, Jagsir Singh, Jaswinder Punjabi Univ Patiala Dept Comp Sci & Engn Patiala Punjab India

Malicious software deliberately affects the computer systems. Malware are analyzed using static or dynamic analysis techniques. Using these techniques, unique patterns are extracted to detect malware correctly. In this paper, a behavior-based malware detection technique is proposed. Various runtime features are extracted by setting up a dynamic analysis environment using the Cuckoo sandbox. Three primary features are processed for developing malware classifier. Firstly, printable strings are processed word by word using text mining techniques which produced a very high dimension matrix of the string features. Then we apply the singular value decomposition technique for reducing dimensions of string features. Secondly, Shannon entropy is computed over the printable strings and API calls to consider the randomness of API and PSI features. In addition to these features, behavioral features regarding file operations, registry key modification and network activities are used in malware detection. Finally, all features are integrated in the training feature set to develop the malware classifiers using the machine learning algorithms. The proposed technique is validated with 16489 malware and 8422 benign files. Our experimental results show the accuracy of 99.54% in malware detection using ensemble machine learning algorithms. Moreover, it aims to develop a behavior-based malware detection technique of high accuracy by processing the runtime features in a new way.

关键词： Dynamic analysis Malware machine learning algorithms Random Forest Static analysis

来源：评论

学校读者我要写书评

暂无评论

Enhanced Lithological Mapping in El-Missikat and El-Erediya Areas, Central Eastern Desert, Egypt, Leveraging Remote Sensing Techniques and machine learning algorithms

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2024年 62卷 1页

作者： Shereif, Aya S. Shebl, Ali Mahmoud, Abdelhalim Shokry Csamer, Arpad Tanta Univ Fac Sci Dept Geol Tanta 31527 Egypt Univ Debrecen Dept Mineral & Geol H-4032 Debrecen Hungary Fayoum Univ Dept Geol Al Fayoum 63514 Egypt Univ Debrecen Dept Mineral & Geol H-4032 Debrecen Hungary Univ Debrecen Cosmochem & Cosm Methods Res Grp H-4032 Debrecen Hungary

In the field of mineral exploration, it is strikingly evident that radioactive-bearing mineralization predominantly resides within granitic intrusions and along structural discontinuities. Consequently, the comprehensive mapping of lithological features emerges as a crucial means of accurately guiding the identification of these mineralizations. The present research is dedicated to enhancing the characterization of granitic rocks located within Egypt's Central Eastern Desert (El-Missikat and El-Erediya regions). These areas have garnered attention due to their notably high concentrations of radioactive mineralizations, prompting the need for a more in-depth investigation. Despite the study area's importance for potential radioactive mineral deposits, examining the geological map reveals notable challenges and inconveniences. Our research aims to address these issues using remote sensing data and machine learning algorithms (MLAs). We used image processing techniques, including false-color composites (FCCs), principal component analysis (PCA), and independent component analysis (ICA) to identify eight lithological targets and generate reference maps for the study *** widely used support vector machine (SVM) was trained with informative image combinations, showing reasonable lithological allocations, especially when it fed with FCC 12-6-2 in RGB. Our study found that incorporating dimensionality-reduction techniques like PCA and ICA with FCCs significantly boosted accuracy by over 15%. Using Sentinel-2 imagery and SVM, we created a novel lithological map for the challenging study area, pinpointing mineralization-rich zones, particularly those linked to shear zones within granitic rocks. This map enhances progress in characterizing rock units, and we strongly advocate the use of dimensionality-reduction techniques, such as PCA and ICA, to feed MLAs. These techniques play a crucial role in producing precise, unbiased lithological maps for complex terrains, aiding i

关键词： Geology Mineralization Rocks Remote sensing machine learning algorithms Uranium Accuracy Principal component analysis Vectors Arabian-Nubian shield (ANS) and Eastern Desert geological mapping mineralized shear zones Sentinel 2 support vector machine (SVM) support vector machine (SVM)

来源：评论

学校读者我要写书评

暂无评论

Comparison of machine learning algorithms in the Prediction of Hospitalized Patients with Schizophrenia

引用

SENSORS 2022年第7期22卷 2517页

作者： Gongora Alonso, Susel Marques, Goncalo Agarwal, Deevyankar De la Torre Diez, Isabel Franco-Martin, Manuel Univ Valladolid Dept Signal Theory & Commun Paseo Belen 15 Valladolid 47011 Spain Polytech Coimbra ESTGOH Rua Gen Santos Costa P-3400124 Oliveira Do Hospital Portugal Higher Coll Technol Dept Engn EEE Sect Muscat 113 Oman Hosp Zamora Psiquiatry Serv Zamora 49021 Spain

New computational methods have emerged through science and technology to support the diagnosis of mental health disorders. Predictive models developed from machine learning algorithms can identify disorders such as schizophrenia and support clinical decision making. This research aims to compare the performance of machine learning algorithms: Decision Tree, AdaBoost, Random Forest, Naive Bayes, Support Vector machine, and k-Nearest Neighbor in the prediction of hospitalized patients with schizophrenia. The data set used in the study contains a total of 11,884 electronic admission records corresponding to 6933 patients with various mental health disorders;these records belong to the acute units of 11 public hospitals in a region of Spain. Of the total, 5968 records correspond to patients diagnosed with schizophrenia (3002 patients) and 5916 records correspond to patients with other mental health disorders (3931 patients). The results recommend Random Forest with the best accuracy of 72.7%. Furthermore, this algorithm presents 79.6%, 72.8%, 72.7%, and 72.7% for AUC, precision, F1-Score, and recall, respectively. The results obtained suggest that the use of machine learning algorithms can classify hospitalized patients with schizophrenia in this population and help in the hospital management of this type of disorder, to reduce the costs associated with hospitalization.

关键词： hospitalization machine learning algorithms predictive models random forest schizophrenia

来源：评论

学校读者我要写书评

暂无评论

Development of prediction model for phosphate in reservoir water system based machine learning algorithms

引用

AIN SHAMS ENGINEERING JOURNAL 2022年第1期13卷

作者： Latif, Sarmad Dashti Birima, Ahmed H. Ahmed, Ali Najah Hatem, Dahan Mohammed Al-Ansari, Nadhir Fai, Chow Ming El-Shafie, Ahmed Komar Univ Sci & Technol Dept Civil Engn Coll Engn Sulaimany 46001 Kurdistan Regio Iraq Qassim Univ Coll Engn Dept Civil Engn Unaizah Saudi Arabia Univ Tenaga Nas Inst Energy Infrastruct Kajang 43000 Selangor Malaysia Lulea Univ Technol Civil Environm & Nat Resources Engn S-97187 Lulea Sweden Monash Univ Malaysia Sch Engn Discipline Civil Engn Jalan Lagoon Selatan Bandar Sunway 47500 Selangor Malaysia Univ Malaya Dept Civil Engn Fac Engn Kuala Lumpur 50603 Malaysia United Arab Emirates Univ Natl Water & Energy Ctr Al Ain U Arab Emirates

Phosphate (PO4) is a major component of most fertilizers, and when erosion and runoff occur, large amounts of it enter the water bodies, causing several problems such as eutrophication. Feitsui reservoir, the primary source of water supply to Taipei, reported half of the reservoir's pollutants from nonpointsource pollution. The value of the PO4 in the water body fluctuates in highly nonlinear and stochastic patterns. However, conventional modeling techniques are no longer sufficiently effective in predicting accurately such stochastic patterns in the concentrations of PO4 in water. Therefore, this study proposes different machine learning algorithms: the artificial neural network (ANN), support vector machine (SVM), random forest (RF), and boosted trees (BT) to predict the concentration of PO4. Monthly measured data between 1986 and 2014 were used to train and test the accuracy of these models. The performances of these models were examined using different statistical indices. Hyperparameters optimization such as cross-validation was performed to enhance the precision of the models. Five water quality parameters were used as input to the proposed models. Different input combinations were explored to optimize the precision. The findings revealed that ANN outperformed the other three models to capture the changes in the concentrations of PO4 with high precision where RMSE is equal to 1.199, MAE is equal to 0.858, and R-2 is equal to 0.979, MSE is equal to 1.439, and finally, CC is equal to 0.9909. The developed model could be used as a reliable means for managing eutrophication problems. (c) 2021 THE AUTHORS. Published by Elsevier BV on behalf of Faculty of Engineering, Ain Shams University. This is an open access article under the CC BY-NC-ND license (http://***/licenses/by-nc-nd/4.0/).

关键词： Water quality parameters Phosphate (PO4), concentration machine learning algorithms Prediction and Feitsui reservoir

来源：评论

学校读者我要写书评

暂无评论

Assessing the performance of state-of-the-art machine learning algorithms for predicting electro-erosion wear in cryogenic treated electrodes of mold steels

引用

ADVANCED ENGINEERING INFORMATICS 2024年 61卷

作者： Cetin, Abdurrahman Atali, Gokhan Erden, Caner Ozkan, Sinan Serdar Sakarya Univ Appl Sci Vocat Sch Sakarya Machinery & Met Technol Sakarya Turkiye Sakarya Univ Appl Sci Fac Technol Dept Mechatron Engn Sakarya Turkiye Sakarya Univ Appl Sci Fac Technol Dept Comp Engn Sakarya Turkiye Sakarya Univ Appl Sci AI Res & Applicat Ctr Sakarya Turkiye

In manufacturing, predicting and reducing electro-erosion wear during the electric discharge machining (EDM) process is critical to minimize delays, financial losses and product defects. Achieving this requires developing and evaluating accurate machine learning models. In our study, we focus on cryogenically treated mold steel electrodes to investigate the potential of different machine learning algorithms to predict EDM wear. We considered five machine learning algorithms-artificial neural networks, ensemble learning, boosting algorithms, tree-based algorithms, and k-nearest neighbors-to evaluate their ability to predict wear patterns accurately. Each algorithm was trained and tested using actual experimental data from EDM processes. Our results show that the machine learning models demonstrated exceptional accuracy, accurately predicting EDM wear in training and testing datasets with almost 99% accuracy. In addition, we identified the most influential characteristics that affect wear patterns, including operating current, cryogenic process parameters, and electrode composition. Based on these findings, manufacturers can gain valuable insight into the factors that cause EDM wear and optimize their EDM processes accordingly to improve productivity, reduce wear-related costs, and increase production quality across multiple manufacturing industries. Furthermore, this research provides insights into the possibilities of implementing these models in real manufacturing contexts and motivates future research on this topic. Ultimately, integrating advanced computing techniques and prudent decision-making strategies will shape the future of manufacturing operations management and promote sustainable and profitable business growth.

关键词： Electro-erosion wear Cryogenic treatment Mold steel machine learning algorithms Boosting algorithms Ensemble learning

来源：评论

学校读者我要写书评

暂无评论

Spatio-temporal modeling of PM_2.5 risk mapping using three machine learning algorithms

引用

ENVIRONMENTAL POLLUTION 2021年 289卷 117859页

作者： Shogrkhodaei, Seyedeh Zeinab Razavi-Termeh, Seyed Vahid Fathnia, Amanollah Razi Univ Fac Literature & Humanities Dept Geog Kermanshah Iran KN Toosi Univ Technol Fac Geodesy & Geomat Engn Geoinformat Tech Ctr Excellence Tehran 19697 Iran

Urban air pollution is one of the most critical issues that affect the environment, community health, economy, and management of urban areas. From a public health perspective, PM2.5 is one of the primary air pollutants, especially in Tehran's metropolis. Owing to the different patterns of PM2.5 in different seasons, Spatio-temporal modeling and identification of high-risk areas to reduce its effects seems necessary. The purpose of this study was Spatio-temporal modeling and preparation of PM2.5 risk mapping using three machine learning algorithms (random forest (RF), AdaBoost, and stochastic gradient descent (SGD)) in the metropolis of Tehran, Iran. Therefore, in the first step, to prepare the dependent variable data, the PM2.5 average was used for the four seasons of spring, summer, autumn, and winter. Then, using remote sensing (RS) and a geographic information system (GIS), independent data such as temperature, maximum temperature, minimum temperature, wind speed, rainfall, humidity, normalized difference vegetation index (NDVI), population density, street density, and distance to industrial centers were prepared as a seasonal average. To Spatio-temporal modeling using machine learning algorithms, 70% of the data were used for training and 30% for validation. The frequency ratio (FR) model was used as input to machine learning algorithms to calculate the spatial relationship between PM2.5 and the effective parameters. Finally, Spatio-temporal modeling and PM2.5 risk mapping were performed using three machine learning algorithms. The receiver operating characteristic (ROC) area under the curve (AUC) results showed that the RF algorithm had the greatest modeling accuracy, with values of 0.926, 0.94, 0.949, and 0.949 for spring, summer, autumn, and winter, respectively. According to the RF model, the most important variable in spring and autumn was NDVI. Temperature and distance to industrial centers were the most important variables in the summer and winter, respec

关键词： PM2.5 Spatio-temporal modeling GIS Remote sensing machine learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Estimating the thermal conductivity of soils using six machine learning algorithms

引用

INTERNATIONAL COMMUNICATIONS IN HEAT AND MASS TRANSFER 2022年第0期136卷

作者： Li, Kai-Qi Liu, Yong Kang, Qing Wuhan Univ Inst Engn Risk & Disaster Prevent State Key Lab Water Resources & Hydropower Engn Sc 299 Bayi Rd Wuhan 430072 Peoples R China Natl Univ Singapore Dept Civil & Environm Engn 1 Engn Dr 2 Singapore 117576 Singapore

Many machine learning algorithms have been applied to determine soil properties in recent years. However, the prediction performances of thermal conductivity of soils via machine learning algorithms are still unclear due to the lack of sufficient databases. In this work, a large database containing 2197 data points from various literature was compiled. Six machine learning algorithms, namely multivariance linear regression (MLR), Gaussian process regression (GPR), support vector machine (SVM), decision tree (DT), random forest (RF) and adaptive boosting methods (AdaBoost) were implemented to predict the thermal conductivity of soils based on the compiled database. In addition, Spearman correlation analysis and grey relational analysis were adopted to compute the strength of influencing factors in thermal conductivity. For obtaining the best prediction model, the performances of six machine learning algorithms were assessed via eight evaluation indicators and compared with three typical empirical models. Results show that the AdaBoost can yield good predicted values of the thermal conductivity of soils with minimum errors (i.e., RMSE = 0.099). This study constructs a database of thermal conductivity and provides a reference for evaluating the thermal conductivity of soils via machine learning algorithms.

关键词： machine learning algorithms Thermal conductivity database Parameter correlation Performance indicators Ensemble learning model

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：