检索结果-内蒙古大学图书馆

Mapping groundwater potentiality by using hybrid machine learning models under the scenario of climate variability: a national level study of Bangladesh

引用

ENVIRONMENT DEVELOPMENT AND SUSTAINABILITY 2024年 1-29页

作者： Sarkar, Showmitra Kumar Alshehri, Fahad Shahfahad Rahman, Atiqur Pradhan, Biswajeet Shahab, Muhammad Khulna Univ Engn & Technol Dept Urban & Reg Planning Khulna 9203 Bangladesh King Saud Univ Abdullah Alrushaid Chair Earth Sci Remote Sensing Geol & Geophys Dept POB 2455 Riyadh 11451 Saudi Arabia Jamia Millia Islamia Fac Sci Dept Geog New Delhi 110025 India Univ Technol Sydney Ctr Adv Modelling & Geospatial Informat Syst CAMGI Sch Informat Syst & Modelling Ultimo NSW 2007 Australia

A severe threat to natural resources and human livelihood is groundwater scarcity. Therefore, mapping groundwater potentiality (GWP) is necessary for future resource management. In this article, a framework for conducting ensemble modeling is introduced. This framework is used to map GWP at the national level under the scenario of climatic variability. Thirteen elements linked to topography, geology, hydrology, and land cover, as well as six climatic indicators based on historical time series data, were used to map the GWP. This study has used three conventional machine learning algorithms (< MLAs), such as logistic model tree, logistic regression, and artificial neural network and five ensemble models by combining standalone models with random forest under stacking framework to produce GWP map. Using the empirical and binormal receiver operating characteristic curves, the GWP mapping has been validated. Result shows that Bangladesh's major rivers run along the high GWP zones in the country's southern and central regions. In addition, the validation using the area under curve (AUC) of ROC curve demonstrates that the stacking model which combined all three MLAs outperformed other models (AUC: 0.971). The findings of this study may help the authorities and stakeholders to formulate the adequate groundwater management plans at national level. In addition, the suggested method might be applied to map GWP on a broader scale in additional nations as well as at the continental level.

关键词： Groundwater potentiality mapping Climate change Machine learning techniques Logistic regression stacking algorithm Bangladesh

来源：评论

学校读者我要写书评

暂无评论

Lifetime prediction of electronic devices based on the P-stacking machine learning model

引用

MICROELECTRONICS RELIABILITY 2023年第1期146卷

作者： Wang, Fei Yang, Ye Huang, Tao Xu, Yang Shanghai Normal Univ Coll Informat Mech & Elect Engn Shanghai 200234 Peoples R China Shanghai Normal Univ Shanghai Intelligent Educ Big Data Engn Technol Re Shanghai 200234 Peoples R China Univ Southern Calif Ctr Adv Mfg Los Angeles CA 90007 USA

Nowadays the data-driven artificial intelligence (AI) and machine learning (ML) provide novel approaches for the effective lifetime prediction of the electronic devices with complicated mechanisms and multiple controlling factors. However, the existing ML prediction models cannot process both high accuracy and high efficiency at the meantime. To address this problem, this paper proposes the new P-stacking ML algorithm model, which combines the Pearson correlation analysis and the stacking multi-model fusion. The Pearson correlation analysis is first applied to select the multiple base learner models with weak correlations for the following stacking multimodel fusion. Two neutral network layers are built to perform the stacking algorithm. In this work, two distinct types of electronic devices are utilized to verify the effectiveness of the P-stacking ML model, which are the IGBT devices and the lithium-ion batteries respectively. For the IGBT lifetime prediction, the results have shown that compared with the long-term and short-term memory neural network (LSTM) model in the previous literature, the mean square error (MSE) of the P-stacking ML model is improved by 6 %, and the average model training time is reduced by 90 %. Moreover, for the lithium batteries, the lifetime prediction accuracy of the P-stacking model is increased by 65 %, and the training time is decreased by 90 %. The results demonstrated that the Pstacking ML model can significantly improve both the prediction accuracy and efficiency simultaneously.

关键词： stacking algorithm Pearson correlation analysis Machine learning IGBT device Lithium -ion battery Lifetime prediction

来源：评论

学校读者我要写书评

暂无评论

Application of stacking hybrid machine learning algorithms in delineating multi-type flooding in Bangladesh

引用

JOURNAL OF ENVIRONMENTAL MANAGEMENT 2021年 295卷 113086-113086页

作者： Rahman, Mahfuzur Chen, Ningsheng Elbeltagi, Ahmed Islam, Md Monirul Alam, Mehtab Pourghasemi, Hamid Reza Tao, Wang Zhang, Jun Tian Shufeng Faiz, Hamid Baig, Muhammad Aslam Dewan, Ashraf Chinese Acad Sci Inst Mt Hazards & Environm Key Lab Mt Hazards & Earth Surface Proc Chengdu 610041 Peoples R China Univ Chinese Acad Sci UCAS Beijing 100049 Peoples R China Int Univ Business Agr & Technol Dept Civil Engn Dhaka 1230 Bangladesh Acad Plateau Sci & Sustainabil Xining 810016 Peoples R China Mansoura Univ Fac Agr Agr Engn Dept Mansoura 35516 Egypt Zhejiang Univ Coll Environm & Resource Sci Hangzhou 310058 Peoples R China Shiraz Univ Coll Agr Dept Nat Resources & Environm Engn Shiraz Iran Curtin Univ Sch Earth & Planetary Sci Kent St Bentley WA 6102 Australia

Floods are among the most devastating natural hazards in Bangladesh. The country experiences multi-type floods (i.e., fluvial, flash, pluvial, and surge floods) every year. However, areas prone to multi-type floods have not yet been assessed on a national scale. Here, we used locally weighted linear regression (LWLR), random subspace (RSS), reduced error pruning tree (REPTree), random forest (RF), and M5P model tree algorithms in a hybrid ensemble to assess multi-type flood probabilities at a national scale in Bangladesh. We used historical flood data (1988-2020), remote sensing images (e.g., MODIS, Landsat 5-8, and Sentinel-1), and topography, hydrogeology, and environmental datasets to train and validate the proposed algorithms. According to the results, the stacking ensemble machine learning LWLR-RF algorithm performed better than the other algorithms in predicting flood probabilities, with R2 = 0.967-0.999, MAE = 0.022-0.117, RMSE = 0.029-0.148, RAE = 4.48-23.38%, and RRSE = 5.8829.69% for the training and testing datasets. Furthermore, true skill statistics (TSS: 0.929-0.967), corrected classified instances (CCI: 96.45-98.35), area under the curve (AUC: 0.983-0.997), and Gini coefficients (0.966-0.994) were computed to validate the constructed (LWLR-RF) multi-type flood probability maps. The maps constructed via the LWLR-RF algorithm revealed that the proportions of different categories of flooding areas in Bangladesh are fluvial flooding 1.50%, 5.71%, 12.66%, and 13.77% of the total land area;flash floods of 4.16%, 8.90%, 11.11%, and 5.07%;pluvial flooding: 5.72%, 3.25%, 5.07%, and 0.90%;and surge flooding, 1.69%, 1.04%, 0.52%, and 8.64% of the total land area, respectively. These percentages represent low, medium, high, and very high probabilities of flooding. The findings can guide future flood risk management and sustainable land-use planning in the study area.

关键词： Extreme floods Machine learning stacking algorithm Risk management National scale

来源：评论

学校读者我要写书评

暂无评论

The network loan risk prediction model based on Convolutional neural network and stacking fusion model

引用

APPLIED SOFT COMPUTING 2021年第PartB期113卷 107961-107961页

作者： Li, Meixuan Yan, Chun Liu, Wei Shandong Univ Sci & Technol Coll Math & Syst Sci Qingdao 266590 Peoples R China Shandong Univ Sci & Technol Coll Comp Sci & Engn Qingdao 266590 Peoples R China

In order to establish a more suitable risk prediction system for the network loan platform and reduce the loan risk of the network platform, this paper proposes a loan risk prediction model stacking+CNN, which is based on the convolutional neural network (CNN) and the integration model of stacking. Using CNN to extract the local spatial features hidden in the results of stacking algorithm, improve the generalization ability of the model, give full play to the generalization ability of stacking algorithm and the feature extraction ability of CNN algorithm. Firstly, this paper uses wrapper method and variance inflation coefficient (VIF) to extract the features from the original data. Then, the processed data is brought into the first layer of stacking algorithm base learner for training. The predicted results are taken into CNN as a new data set for feature extraction. Finally, the extracted data are brought into the SVM for risk prediction. Empirical results show that the prediction model proposed in this paper is better than the single model and other integrated models in predicting accuracy and recall rate. (c) 2021 Elsevier B.V. All rights reserved.

关键词： Ensemble learning stacking algorithm Convolutional neural network Loan risk prediction

来源：评论

学校读者我要写书评

暂无评论

Predictive Analysis & Brief Study of Early-Stage Diabetes Using Multiple Classifier Models 12

Predictive Analysis & Brief Study of Early-Stage Diabetes Us...

引用

IEEE 12th Annual Computing and Communication Workshop and Conference (CCWC)

作者： Tahsin, Mohammad Sadman Jobayer, Md Antor, Md Borhan Uddin Islam, Maidul Raisa, Fatima Fairuz Shaikat, Md Al Hasan BRAC Univ Dept Comp Sci & Engn Dhaka Bangladesh BRAC Univ Dept Elect & Elect Engn Dhaka Bangladesh

ISBN: (纸本)9781665483032

Diabetes Mellitus is one of the world's leading causes of mortality, with a worldwide death toll estimated to be in the millions. It is determined by the concentration of a sugar molecule in the blood, which is produced from glucose. Predicting the likelihood of contracting this illness may now be done using a plethora of methods. Data about diabetic patients must be comprehensive and accurate in order to accurately forecast the onset of the disease. In this paper, we discussed early-stage diabetes prediction using six algorithms. The algorithms are Gradient Boosting, ADA Boosting, XG Boosting, Neural Network, SVM, Random Forest, stacking Neural Network, stacking SVM, stacking Random Forest. We also discussed briefly about the best algorithm among them with detailed accuracy by class and confusion matrix. By this study, we can predict early-stage diabetes disease more accurately.

关键词： Diabetes prediction Random Forest boosting algorithm stacking algorithm confusion matrix

来源：评论

学校读者我要写书评

暂无评论

The Processing Procedure for the Interpretation of Microseismic Signal Acquired from a Surface Array During Hydraulic Fracturing in Pomerania Region in Poland.

The Processing Procedure for the Interpretation of Microseis...

引用

International Conference on Computational Science (ICCS)

作者： Antoszkiewicz, Michal Kmiec, Mateusz Szewczuk, Pawel Szkodo, Marek Jankowski, Robert Gdansk Univ Technol Fac Mech Engn Gdansk Poland Gdansk Univ Technol Fac Civil & Environm Engn Gdansk Poland

Hydraulic fracturing is a procedure of injecting high pressure fluid into the wellbore in order to break shell rock and facilitate gas flow. It is a very costly procedure and, if not conducted properly, it may lead to environmental pollution. To avoid costs associated with pumping fluid outside the perspective (gas rich) zone and improve one's knowledge about the reservoir rock, microseismic monitoring can be applied. The method involves recording seismic waves, which are induced by fractured rock, by an array of sensors distributed in a wellbore nearby or on the surface. Combining geological and geophysical knowledge of region with signal processing computer techniques, one can locate induced fractures allowing for real-time process monitoring and rock properties evaluation. In Poland perspective shell formation is located very deep, i.e. about 4km from the surface. Additionally overlaying rock formations strongly attenuate and disperse seismic waves. Therefore, signal recorded by a surface array of sensors is very weak. Signal from a seismic event can be orders of magnitude lower than noise. To recover signal connected with fractured rock one needs to use numerical methods utilizing coherence of signals. An example of such a computer procedure is presented in this paper. (C) 2017 The Authors. Published by Elsevier B.V.

关键词： microseismic monitoring surface array stacking algorithm

来源：评论

学校读者我要写书评

暂无评论

Stack algorithm Implementation in Robot-Based Mixed Case Palletizing System 4

Stack Algorithm Implementation in Robot-Based Mixed Case Pal...

引用

4th International Conference on Electrical, Control and Instrumentation Engineering, ICECIE 2022

作者： Nguyen-Vinh, Khuong Dewasurendra, Hasindu Gonapaladeniya, Saumith Sarbahi, Utkarsh Le, Nguyen School of Science Engineering and Technology Rmit University Ho Chi Minh City Viet Nam VSB-Technical University of Ostrava Faculty of Electrical Engineering and Computer Science Ostrava Czech Republic

ISBN: (纸本)9781665480765

This paper documents the design procedure of a mixed case palletizing system using the ABB robot variant, IRB660. With the evolution of the e-commerce industry and rising volumes of stock-flow in warehouses and trading facilities, there has been a requirement for the automation of some of the most important operations. An automated palletizing system is a potential solution for this problem, to create optimized pallets with greater packing density and pallet support compared with the manual practices in operation. By completing this project, the authors will provide an entirely robotized palletizing system capable of responding to any customized packing order in a quick and efficient manner. The system is designed to handle 1000 or more cases per hour making it ideal for any warehouse or logistic facility dealing with a high number of stock-keeping units. Starting with a literature review and market research on the available systems, three different bin packing algorithms were stated: the Guillotine, MAXRECTS, and Skyline algorithms. Further, a new metric 'percolation' was introduced to measure and compare the packing quality of a pallet. The main section of this paper consists of a study of the design solution the authors have implemented for the AI stacking algorithm while introducing the palletizing UI used in the system. A data-driven 3D bin packing approach was considered for the stacking process which makes use of even-height super boxes to form dense and supported pallets. This method was chosen for its flexibility and reliable packing density of 80% made within a short time frame. Moving to the UI, a sample design of a graphical user interface (GUI) was first made in Figma while focusing on the different functionalities of the palletizing system before implementing the UI as a Windows Forms application. A 2D image of the ongoing pallet is displayed with several other customizing features such as selecting the stacking pattern and choosing different box/palle

关键词： automation industrial robot mixed case palletizing system stacking algorithm

来源：评论

学校读者我要写书评

暂无评论

Prediction of glass-forming ability based on multi-model fusion

引用

JOURNAL OF NON-CRYSTALLINE SOLIDS 2024年 623卷

作者： Zeng, Yangchuan Tian, Zean Zheng, Quan Jiang, Mingxiang Peng, Yikun Guizhou Univ Coll Big Data & Informat Engn Guiyang 550025 Peoples R China Hunan Univ Coll Comp Sci & Elect Engn Changsha 410082 Peoples R China

At present, it is difficult to find metals with good glass-forming ability (GFA), seriously hindering the industrial application of metallic glasses (MGs). Therefore, it is urgent to develop a regression model that provides a prompt prediction for the critical diameter (Dmax) of alloys. Most established models rely heavily on elaborate feature descriptors and single algorithms, which may limit the predictive accuracy. In this work, the stacking fusion is adopted to construct a more efficient model (Stack-Dmax). To avoid domain knowledge involved in feature engineering, only the alloy composition is treated as the input. Experiments revealed that compared to 6 individual models, the Stack-Dmax model is more robust and accurate regarding performance;it achieves improvement up to 41.61 %, 54.76 % and 35.67 % respectively in RMSE, R2 and MAE. The Stack-Dmax model is also better than the five most recently reported models based on RF, XGB, and CNN. In practical applications, our model exhibits potential for designing new La- and Mg-based MGs. These findings suggest that the stacking approach provides an effective GFA-prediction model only based on the composition of alloys.

关键词： Machine learning stacking algorithm Model fusion Glass -forming ability Critical diameter

来源：评论

学校读者我要写书评

暂无评论

Merging precipitation scheme design for improving the accuracy of regional precipitation products by machine learning and geographical deviation correction

引用

JOURNAL OF HYDROLOGY 2023年第PartB期620卷

作者： Yu, Chen Shao, Huaiyong Hu, Deyon Liu, Gang Dai, Xiaoai Chengdu Univ Technol Coll Earth Sci Chengdu 610059 Peoples R China Capital Normal Univ Coll Resource Environm & Tourism Beijing 100048 Peoples R China Capital Normal Univ Lab Cultivat Base Environm Proc & Digital Simulat Beijing 100048 Peoples R China 1 East 3rd Rd Erxianqiao Chengdu 610059 Sichuan Peoples R China

Global satellite precipitation products (SPPs) effectively obtain spatial precipitation information but frequently fail to meet application requirements in small-scale areas due to low accuracy. This study aims to design a merging precipitation scheme based on remote sensing and surface parameters to address the inaccuracy of regional precipitation. The scheme data are based on daily IMERG-FR, CHIRPS, and PDIR-Now satellite pre-cipitation products from 2011 to 2018, combined with WorldClim model climate data and 39 rain gauge ob-servations. The scheme generates merged precipitation with high-accuracy and high-resolution (0.04 degrees) through the streamlined operation of multiple methods in the Songhua River basin in northeast China. First, the stacking algorithm was employed to perform preliminary merging of SPPs and decrease data noise errors (mean absolute error and standard deviation were reduced by 13.80% and 14.44%, respectively). Second, the correlation of merged and observed precipitation was improved by 1.18%-4.46% in different seasons after geographically weighted regression. Finally, the merged data were subjected to local intensity scaling, which reduced the precipitation error by an average of 3.14%. When compared to the original SPPs, the final merged precipitation (FMP) improved the correlation (increased by 0.19) and reduced the errors (root mean square error and relative error decreased by 1.71 mm and 0.08 mm, respectively). FMP performed well under precipitation event cases, with an average difference of 0.24 mm from observed precipitation. The study realized the merging analysis of remote sensing precipitation data with varying precision and spatial resolution. Furthermore, a systematic merging precipitation scheme coupled with multiple algorithms of machine learning, geographic regression, and mathematical statistics was formed. This study provides a reference for merging precipitation at a regional scale, which can be applied to other study area

关键词： Remote sensing precipitation stacking algorithm Geographically weighted regression Local intensity scaling Multi-source data merging

来源：评论

学校读者我要写书评

暂无评论

Multi-omics integration strategy in the post-mortem interval of forensic science

引用

TALANTA 2024年第Part1期268卷 125249页

作者： Li, Jian Wu, Yan-juan Liu, Ming-feng Li, Na Dang, Li-hong An, Guo-shuai Lu, Xiao-jun Wang, Liang-liang Du, Qiu-xiang Cao, Jie Sun, Jun-hong Shanxi Med Univ Sch Forens Med 98 Univ St Jinzhong 030604 Shanxi Peoples R China Shanxi Key Lab Forens Med Jinzhong 030600 Shanxi Peoples R China Baotou City Publ Secur Bur Criminal Invest Detachment 191 Jianshe Rd Baotou 014030 Inner Mongolia Peoples R China

Estimates of post-mortem interval (PMI), which often serve as pivotal evidence in forensic contexts, are fundamentally based on assessments of variability among diverse molecular markers (including proteins and metabolites), their correlations, and their temporal changes in post-mortem organisms. Nevertheless, the present approach to estimating the PMI is not comprehensive and exhibits poor performance. We developed an innovative approach that integrates multi-omics and artificial intelligence, using multimolecular, multimarker, and multidimensional information to accurately describe the intricate biological processes that occur after death, ultimately enabling inference of the PMI. Called the multi-omics stacking model (MOSM), it combines metabolomics, protein microarray electrophoresis, and fourier transform-infrared spectroscopy data. It shows improved prediction accuracy of the PMI, which is urgently needed in the forensic field. It achieved an accuracy of 0.93, generalized area under the receiver operating characteristic curve of 0.98, and minimum mean absolute error of 0.07. The MOSM integration framework not only considers multiple markers but also incorporates machine-learning models with distinct algorithmic principles. The diversity of biological mechanisms and algorithmic models further ensures the generalizability and robustness of PMI estimation.

关键词： Machine learning Multi-omics Post-mortem interval stacking algorithm

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：