检索结果-内蒙古大学图书馆

data analytics during pandemics: a transportation and location planning perspective

ANNALS OF OPERATIONS RESEARCH 2023年第1期328卷 193-244页

作者： Bozkaya, Elif Eriskin, Levent Karatas, Mumtaz Natl Def Univ Turkish Naval Acad Dept Comp Engn TR-34940 Istanbul Turkey Natl Def Univ Turkish Naval Acad Dept Ind Engn TR-34940 Istanbul Turkey

The recent COVID-19 pandemic once again showed the value of harnessing reliable and timely data in fighting the disease. Obtained from multiple sources via different collection streams, an immense amount of data is processed to understand and predict the future state of the disease. Apart from predicting the spatio-temporal dynamics, it is used to foresee the changes in human mobility patterns and travel behaviors and understand the mobility and spread speed relationship. During this period, data-driven analytic approaches and Operations Research tools are widely used by scholars to prescribe emerging transportation and location planning problems to guide policy-makers in making effective decisions. In this study, we provide a review of studies which tackle transportation and location problems during the COVID-19 pandemic with a focus on data analytics. We discuss the major data collecting streams utilized during the pandemic era, highlight the importance of rapid and reliable data sharing, and give an overview of the challenges and limitations on the use of data.

关键词： Transportation Location data-driven analytics Pandemic COVID-19

来源：评论

学校读者我要写书评

暂无评论

Implementing a web-based optimized artificial intelligence system with metaheuristic optimization for improving building energy performance

引用

JOURNAL OF ASIAN ARCHITECTURE AND BUILDING ENGINEERING 2024年第1期23卷 264-281页

作者： Ngo, Ngoc-Tri Truong, Ngoc-Son Truong, Thi Thu Ha Pham, Anh-Duc Huynh, Nhat-To Univ Danang Univ Sci & Technol Fac Project Management Hanoi Vietnam Univ Danang Univ Technol & Educ Dept Civil Engn Da Nang City Vietnam Univ Danang Univ Sci & Technol Fac Project Management 54 Nguyen Luong Bang Danang Vietnam

Improving energy efficiency in buildings is a challenge during operation and maintenance. The work proposes a cloud artificial intelligence-based building energy management (cloud AI-BEM) system for predicting building energy consumption. The proposed system includes the data layer, the AI-analytics layer, and the decision support information layer. The data layer collects and stores data in the cloud database management system. The analytics layer performs applied a hybrid AI model which was developed and deployed in this layer that enables predict future energy consumption in buildings. The hybrid AI model, namely the SAMFOR model was developed based on the integration of the seasonal autoregressive integrated moving average (SARIMA) model and the firefly algorithm (FA) and least-squares support vector regression (LSSVR). The web-based layer visualizes insights for users. As insights, the cloud AI-BEM system enables to monitor and to compare the energy consumption among buildings;to predict one-day-ahead energy use in buildings, to produce key performance indicators of energy use;to visualize energy data and outdoor temperature data;to easily interact with data from the system interface. Average accuracy in terms of RMSE values ranged from 1.36 kW per 30 min. The R values were higher than 0.957 and very close to 1.

关键词： data-driven analytics building energy efficiency artificial intelligence machine learning building energy management system

来源：评论

学校读者我要写书评

暂无评论

Investigating the ability of deep learning to predict welding depth and pore volume in hairpin welding

引用

JOURNAL OF LASER APPLICATIONS 2024年第4期36卷

作者： Darwish, Amena Ericson, Stefan Ghasemi, Rohollah Andersson, Tobias Lonn, Dan Lassila, Andreas Andersson Salomonsson, Kent Univ Skovde Sch Engn Sci Virtual Mfg Proc Kaplansgatan 11 SE-54134 Skovde Sweden

To advance quality assurance in the welding process, this study presents a deep learning (DL) model that enables the prediction of two critical welds' key performance characteristics (KPCs): welding depth and average pore volume. In the proposed approach, a wide range of laser welding key input characteristics (KICs) is utilized, including welding beam geometries, welding feed rates, path repetitions for weld beam geometries, and bright light weld ratios for all paths, all of which were obtained from hairpin welding experiments. Two DL networks are employed with multiple hidden dense layers and linear activation functions to investigate the capabilities of deep neural networks in capturing the complex nonlinear relationships between the welding input and output variables (KPCs and KICs). Applying DL networks to the small numerical experimental hairpin welding dataset has shown promising results, achieving mean absolute error values of 0.1079 for predicting welding depth and 0.0641 for average pore volume. This, in turn, promises significant advantages in controlling welding outcomes, moving beyond the current trend of relying only on defect classification in weld monitoring to capture the correlation between the weld parameters and weld geometries.

关键词： data-driven analytics deep learning hairpin welding quality assurance of laser welding welding similar materials

来源：评论

学校读者我要写书评

暂无评论

Integrating Soil Index Parameters and Machine Learning for Reliable California Bearing Ratio Estimation using a GA-ELM Model

引用

INTERNATIONAL JOURNAL OF PAVEMENT RESEARCH AND TECHNOLOGY 2024年 1-18页

作者： Khasawneh, Mohammad Ali Mewada, Hiren Nayeemuddin, Mohammed Rababah, Samer Khasawneh, Ahmad Ali Prince Mohammad Bin Fahd Univ Civil Engn Dept POB 1664 Al Khobar 31952 Saudi Arabia Prince Mohammad Bin Fahd Univ Elect Engn Dept POB 1664 Al Khobar 31952 Saudi Arabia Jordan Univ Sci & Technol Dept Civil Engn POB 3030 Irbid 2210 Jordan Ohio State Univ Wexner Med Ctr Management Engn & Proc Improvement Dept Integrated Syst Engn Dept 660 Ackerman Rd Columbus OH 43202 USA Ohio State Univ 660 Ackerman Rd Columbus OH 43202 USA

The need for accurate predictions of the California Bearing Ratio (CBR) is critical in optimizing subgrade soil evaluations for pavement design, as traditional testing methods are time-consuming and labor-intensive. The goal of this study is to overcome the limitations of traditional CBR estimation by introducing advanced machine learning models capable of predicting the CBR of subgrade soil using easily accessible soil index properties, thereby streamlining the process for state road agencies. Approximately 60 soil specimens were prepared by mixing varying amounts of sand with natural soil to encompass a broad spectrum of soil characteristics. Additionally, data from soil tests conducted by the local transportation authority were included, bringing the total number of samples analyzed to 110. The researchers employed two machine learning (ML) techniques: the Extreme Learning Machine (ELM) model and the optimized-hybrid Genetic Algorithm - Extreme Learning Machine (GA-ELM) model. The CBR values determined in the laboratory served as the response variable, while the predictors included soil compaction characteristics (optimum moisture content and maximum dry density), Atterberg limits (liquid limit, plastic limit, and plasticity index), density, and gradation parameters (percentages of materials retained on sieve #200 and #10). The results demonstrated that the GA-ELM model significantly outperformed the ELM model, achieving superior evaluation metrics: R2 = 95.27%, MAE = - 0.5946, RMSE = 8.1403, RRMSE = 0.3502, WI = 0.8831, LM = 0.7662, and NSE = 0.9044, compared to the ELM model's R2 = 85.10%, MAE = 6.1447, RMSE = 15.4957, RRMSE = 0.6666, WI = 0.7642, LM = 0.5284, and NSE = 0.6537. The primary advantage of this research is that it allows state road agencies to predict CBR using readily available soil data, reducing reliance on time-intensive testing. The superior performance of the GA-ELM model has the potential to significantly improve the accuracy and efficiency

关键词： Machine learning data-driven analytics California bearing ratio Subgrade soil Soil index parameters Asphalt pavement Asphalt performance Modeling Prediction

来源：评论

学校读者我要写书评

暂无评论

data driven scalability and profitability analysis in free floating electric car sharing systems

引用

INFORMATION SCIENCES 2023年 621卷 545-561页

作者： Ciociola, Alessandro Giordano, Danilo Vassio, Luca Mellia, Marco Politecn Torino Turin Italy OccupyAI Turin Italy

In this paper, we analyse the impact of system design options with different demand inten-sities for electric vehicle free-floating car sharing systems (EV-FFCS). We consider three dif-ferent cities for which we collected rental data from a car sharing system. Using these data, we build demand and supply models of an EV-FFCS. We evaluate the performance of dif-ferent design options from both the customers' and the operators' perspectives, i.e., quality of service and profitability. We study the number of chargers, their placement and the size of the fleet. We observe the impact on the system when demand is constant and then when demand increases. The results show that it is critical to scale the capacity of the charging infrastructure proportionally to the mobility demand. Conversely, the same fleet size can accommodate a 300% increase in demand, not satisfying less than 15% of it. Moreover, the observed demand and supply would likely not generate profits for the EV system. This is due to the high cost of electric vehicles and the need to manage the fleet for charging operations. The figure changes with at least a 5-fold increase in demand, with the current fleet size becoming profitable. (c) 2022 Elsevier Inc. All rights reserved.

关键词： data-driven analytics Car sharing Scalability Charging infrastructure Profitability Electric vehicles

来源：评论

学校读者我要写书评

暂无评论

Hyperparameter optimization for cardiovascular disease data-driven prognostic system

引用

Visual Computing for Industry,Biomedicine,and Art 2023年第1期6卷 218-244页

作者： Jayson Saputra Cindy Lawrencya Jecky Mitra Saini Suharjito Suharjito Industrial Engineering Department BINUS Graduate Program-Master of Industrial EngineeringBina Nusantara UniversityJakarta 11480Indonesia

Prediction and diagnosis of cardiovascular diseases(CVDs)based,among other things,on medical examinations and patient symptoms are the biggest challenges in *** 17.9 million people die from CVDs annually,accounting for 31%of all deaths *** a timely prognosis and thorough consideration of the patient’s medical history and lifestyle,it is possible to predict CVDs and take preventive measures to eliminate or control this life-threatening *** this study,we used various patient datasets from a major hospital in the United States as prognostic factors for *** data was obtained by monitoring a total of 918 patients whose criteria for adults were 28-77 years *** this study,we present a data mining modeling approach to analyze the performance,classification accuracy and number of clusters on Cardiovascular Disease Prognostic datasets in unsupervised machine learning(ML)using the Orange data mining *** techniques are then used to classify the model parameters,such as k-nearest neighbors,support vector machine,random forest,artificial neural network(ANN),naïve bayes,logistic regression,stochastic gradient descent(SGD),and *** determine the number of clusters,various unsupervised ML clustering methods were used,such as k-means,hierarchical,and density-based spatial clustering of applications with noise *** results showed that the best model performance analysis and classification accuracy were SGD and ANN,both of which had a high score of 0.900 on Cardiovascular Disease Prognostic *** on the results of most clustering methods,such as k-means and hierarchical clustering,Cardiovascular Disease Prognostic datasets can be divided into two *** prognostic accuracy of CVD depends on the accuracy of the proposed model in determining the diagnostic *** more accurate the model,the better it can predict which patients are at risk for CVD.

关键词： Cardiovascular disease data-driven analytics data mining Hyperparameter optimization Orange data mining software Prognostic system Unsupervised machine learning

来源：评论

学校读者我要写书评

暂无评论

Statistical Models for Condition Monitoring and State of Health Estimation of Lithium-Ion Batteries for Ships

引用

Journal of Dynamics, Monitoring and Diagnostics 2024年第1期3卷 11-20页

作者： Erik Vanem Qin Liang Maximilian Bruch Gjermund Bøthun Katrine Bruvik Kristian Thorbjørnsen Azzeddine Bakdi DNV GRD HøvikNorway Department of Mathematics University of OsloOsloNorway Fraunhofer ISE FreiburgGermany Corvus Energy BergenNorway Corvus Energy PorsgrunnNorway

Battery systems are increasingly being used for powering ocean going ships,and the number of fully electric or hybrid ships relying on battery power for propulsion is *** ensure the safety of such ships,it is important to monitor the available energy that can be stored in the batteries,and classification societies typically require the state of health(SOH)to be verified by independent *** paper addresses statistical modeling of SOH for maritime lithium-ion batteries based on operational sensor *** methods for sensor-based,data-driven degradation monitoring will be presented,and advantages and challenges with the different approaches will be *** different approaches include cumulative degradation models and snapshot models,models that need to be trained and models that need no prior training,and pure data-driven models and physics-informed *** of the methods only rely on measured data,such as current,voltage,and temperature,whereas others rely on derived quantities such as state of *** include simple statistical models and more complicated machine learning *** from this exploration will be important in establishing a framework for data-driven diagnostics and prognostics of maritime battery systems within the scope of classification societies.

关键词： battery condition monitoring data-driven analytics diagnostics state of health

来源：评论

学校读者我要写书评

暂无评论

A data-analytics Approach for Risk Evaluation in Peer-to-Peer Lending Platforms

引用

IEEE INTELLIGENT SYSTEMS 2020年第3期35卷 85-94页

作者： He, Feng Li, Yuelei Xu, Tiecheng Yin, Libo Zhang, Wei Zhang, Xiaotao Tianjin Univ Finance & Econ Sch Finance Tianjin Peoples R China Tianjin Univ Coll Management Tianjin Peoples R China Singapore Management Univ Sch Accountancy Business Adm Accounting & Finance Singapore Singapore Cent Univ Finance & Econ Beijing Peoples R China Tianjin Univ Coll Management & Econ Tianjin Peoples R China

The goal of this article is to investigate the roles of individual behavior characteristics and Internet finance industry risk in the light of bank run theory for P2P. We know that risk evaluation is clearly important for peer-to-peer (P2P) lending platforms in China, as during the last two years, the industry has experienced thousands of platform crashes. Traditional approaches to evaluate enterprise risk are increasingly ineffective in this industry, due to the difficulty of assessing the real information. In addition, the Internet business model makes it possible to record new kinds of information. By applying a data-driven analytics method, we build an intelligent risk evaluation model for P2P platforms that have comparable targeting platforms. The case study shows that our risk evaluation method can generate early warning signals regarding platform or industry risk, which is able to provide effective supporting for P2P business in practice.

关键词： Internet Industries Finance Risk management Peer-to-peer computing Computer crashes Peer-to-Peer lending data-driven analytics risk evaluation crash

来源：评论

学校读者我要写书评

暂无评论

Benchmarking AutoML-Supported Lead Time Prediction 3

Benchmarking AutoML-Supported Lead Time Prediction

引用

3rd International Conference on Industry 4.0 and Smart Manufacturing (ISM)

作者： Bender, Janek Trat, Martin Ovtcharova, Jivka FZI Res Ctr Informat Technol Haid & Neu Str 10-14 D-76135 Karlsruhe Germany

In manufacturing companies, especially in small and medium enterprises (SME) in the make-to-order domain, predicting accurate lead times for highly customisable products poses a challenge. One avenue to tackle this challenge is using machine learning to create data-driven models. With the advent of Automated Machine Learning (AutoML), there is a potential also for non-data-scientists in the SMEs to utilise machine learning in a self-sufficient manner In this paper, we benchmarked three AutoML solutions on data from two SMEs and compared their models with manual predictions currently in productive use as well as simple mean models. We furthermore investigated how these solutions support the model development process. While we found that the models generated by the AutoML solutions outperformed manual predictions, labour-intensive parts of the model development process such as data understanding and pre-processing as well as feature engineering were not supported sufficiently by the benchmarked solutions. (C) 2022 The Authors. Published by Elsevier B.V.

关键词： AutoML production data-driven analytics machine learning lead time prediction

来源：评论

学校读者我要写书评

暂无评论

A data-driven Approach for Option-Specific Order Freeze Points in Mass-Customized Production 8th

A Data-Driven Approach for Option-Specific Order Freeze Poin...

引用

8th Changeable, Agile, Reconfigurable and Virtual Production Conference, CARV 2021 and 10th World Mass Customization and Personalization Conference, MCPC 2021

作者： Dürr, Simon Silbernagel, Rainer Bartsch, Hannah Steier, Gwen Louis Huber, Marco F. Lanza, Gisela Dr. Ing. h.c. F. Porsche AG Porscheplatz 1 Stuttgart70435 Germany University of Stuttgart Institute of Industrial Manufacturing and Management IFF Allmandring 35 Stuttgart70569 Germany Institute of Production Science wbk Kaiserstraße 12 Karlsruhe76131 Germany Fraunhofer Institute for Manufacturing Engineering and Automation IPA Nobelstraße 12 Stuttgart70569 Germany

ISBN: (纸本)9783030906993

Customer satisfaction is a key factor to ensure long-term business success. Therefore, automotive manufacturers offer various options to individualize a car. Furthermore, customers and dealers are allowed to change their configuration until the vehicles are scheduled for production. This point is called order freeze. While vehicle specifications remain nearly unchanged in a build-to-order fulfillment strategy, this is not the case in build-to-stock. Mass-customized products with billions of possible car configurations, changing customer demands, or a dynamic environment are some of the challenges that confront the manufacturers in the planning and ordering processes. In this paper, the concept of multiple option-specific order freeze points is developed, which allows customers and dealers to change the configuration specifications at an even later point. For this purpose, the planning process, customer preferences, feasibility rules as well as technical and sales-operated option dependencies are evaluated. Furthermore, independent option-specific order freeze points are detected based on data-driven methods to handle the requirements for agile production systems by using current analytical technologies. The concept of multiple option-specific order freeze points has a high potential to be applied in a practical usage and is validated by a real-world use case of the Dr. Ing. h.c. F. Porsche AG. © 2022, Springer Nature Switzerland AG.

关键词： Customer satisfaction data-driven analytics Demand uncertainty Mass customization Order freeze point

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：