检索结果-内蒙古大学图书馆

From data to Impact: Lessons Learned in Leveraging Digitalization and machine learning to Boost Operational Efficiency and ESG Performance in Drilling Rigs

From Data to Impact: Lessons Learned in Leveraging Digitaliz...

引用

2025 SPE/IADC international Drilling conference and Exhibition, DC 2025

作者： Poludasu, S. Hidad, S. Groh, A. Godumagadda, A. van Wissenkerke, M. Snijder Harrist, J. Patterson UTI Drilling Company LLC HoustonTX United States

ISBN: (纸本)9781959025641

While there is significant enthusiasm for leveraging data to drive optimization, discussions rarely focus on the challenges associated with the real-time deployment of data-driven workflows. This paper addresses these challenges, highlighting the crucial need for synergy between data, engineering expertise, technology, and organizational commitment to convert data-driven insights into tangible efficiency gains and reduced emissions. It details lessons learned from a drilling contractor's perspective in developing and implementing a data-driven performance evaluation system for a fleet of over a hundred onshore rigs. This paper highlights the significance of robust data architecture, which is crucial for improving the system's reliability in developing representative models and metrics for the rig performance evaluation system. These metrics cover multiple dimensions of rig performance, including Health, Safety, and Environmental (HSE) standards, drilling performance, resource management, and financial metrics. The selection of these metrics and their targets was informed by data trends and stakeholder expectations, with a strong emphasis on prioritizing safety, ensuring that all targets adhered to strict safe operating standards. Initially introduced in 2019, the performance evaluation system underwent a significant update in early 2022 to better reflect the benefits of advancements in automation, technology, and training available to rig crews. An ESG metric was added to the evaluation system to support the organization's commitment to sustainability. This ESG metric employs ensemble machine learning and on-rig edge devices to assess CO2 emissions against modeled targets. The automated system detailed in this paper produces standardized scores based on these metrics, enabling the monthly assessment of individual rig performance, and ensuring continuous improvement aligned with environmental and efficiency goals. Since updating the evaluation system in early 2022, s

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Research on Optimizing the Intelligent Recommendation System of College Courses by machine learning Algorithm

Research on Optimizing the Intelligent Recommendation System...

引用

2025 Asia-Europe conference on Cybersecurity, Internet of Things and Soft Computing, CITSC 2025

作者： Zhang, Lei Qian, Feng School of Mathematics and Computer Science Tongling University Tongling China

ISBN: (纸本)9798331504205

This paper proposes a course intelligent recommendation system based on machine learning algorithm to achieve more accurate personalized recommendation. The system uses deep learning model to design an optimized recommendation algorithm by collecting and analyzing multi-dimensional data such as student behavior, course evaluation and personal interests. Collaborative filtering, content-based filtering and deep-learning algorithm based on graph convolutional network (GCN) are introduced to convert the course recommendation problem into a multi-objective optimization problem, and the recommendation precision and the level of personalization are continuously enhanced by training the model. To validate the efficacy of the system, this article conducts extensive model simulation and data analysis. The simulation results show that on a specific data set, the accuracy and recall rate of the recommendation system reach 93% and 88% respectively, which is better than the traditional recommendation algorithm. By comparing with other mainstream algorithms, the recommendation system proposed in this paper performs better in dealing with data sparsity and improving recommendation accuracy, and greatly improves user satisfaction. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Research on Key Technologies and Applications of Recommendation System Based on machine learning 24

Research on Key Technologies and Applications of Recommendat...

引用

2nd international conference on Communication Networks and machine learning, CNML 2024

作者： Liu, Dan Sun, Yuan Hao, Jianmin Fu, Lin Dalian University of Finance and Economics Liaoning Dalian China

ISBN: (纸本)9798400711688

In the current highly information-based and digital social environment, numerous technical applications are constantly enriching the sources and communication channels of network information data, so that users are facing the problems of information explosion and information overload while enjoying the convenience of information acquisition. Therefore, the emergence and development of recommendation system has become the only way to solve this problem. However, the conventional recommendation system still has obvious lag when dealing with data sparsity and cold start, and it is difficult to achieve accurate recommendation. Based on the actual application requirements, this paper will comprehensively explore the feasibility of machine learning algorithm in the field of recommendation system, and propose a set of recommendation algorithm construction scheme based on machine learning to make up for the shortcomings of the existing recommendation system. Practice has proved that the hybrid recommendation algorithm model based on decision tree (DT), random forest (RF) and logistic regression (LR) can automatically combine and screen features, mine valuable feature information from sparse data, and use these feature information to make efficient classification prediction, and then generate more comprehensive and accurate recommendation results, so as to improve user satisfaction and the performance of recommendation system. © 2024 Copyright held by the owner/author(s).

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A Supervised Clustering Approach to Detect Similar Soccer Players 25th

A Supervised Clustering Approach to Detect Similar Soccer Pl...

引用

25th international conference on Intelligent data engineering and Automated learning

作者： Vidal, Andreu Simo Sanchez-Anguix, Victor Alberola, Juan M. Valencian Res Inst Artificial Intelligence Valencia Spain Univ Politecn Valencia Inst Tecnol Informat Cami Vera S-N Valencia 46022 Spain Univ Politecn Valencia Cami Vera S-N Valencia 46022 Spain

ISBN: (纸本)9783031777370;9783031777387

One promising application of data analytics in soccer is the identification of groups of players with similar playing styles. This can enhance recruitment processes and assist in tactical decisions, such as substitutions during a match. Previous research has explored various methods to measure a player's contribution, identify key variables for player positions, and predict market value using machine learning techniques. However, these efforts often focus on traditional player positions or a limited set of gameplay characteristics, lacking a comprehensive analysis of player participation. This paper introduces a novel approach to clustering similar soccer players using supervised clustering and dimensionality reduction. Unlike previous studies, our method aims to refine the well-known positions of players and incorporates a wide range of in-game metrics to provide a holistic view of each player's playing style.

关键词： big data machine learning dimensionality reduction sports analytics clustering optimisation

来源：评论

学校读者我要写书评

暂无评论

Classification of failure modes, bearing capacity, and effective stiffness prediction for corroded RC columns using machine learning algorithm

引用

JOURNAL OF BUILDING engineering 2025年 102卷

作者： Zeng, Zhuo Ying, Guogang Zhang, Yi Gong, Yiwei Mei, Yong Li, Xiaopeng Sun, Hua Li, Bing Ma, Jiaxing Li, Shaohua Zhejiang Univ Coll Civil Engn & Architecture Hangzhou 310058 Peoples R China NingboTech Univ Sch Civil Engn & Architecture Ningbo 315199 Peoples R China Southeast Univ Sch Civil Engn Nanjing Peoples R China VRcollab Pte Ltd 75 Ayer Rajah Crescent Singapore 139953 Singapore Acad Mil Sci Inst Def Engn Beijing 100036 Peoples R China PopSmart Technol Co Ltd Ningbo 315100 Peoples R China Nanyang Technol Univ Sch Civil & Environm Engn 50 Nanyang Ave Singapore 639798 Singapore NingboTech Univ Sch Civil Engn & Architecture Ningbo Peoples R China

Corrosion of reinforcement is a crucial factor that significantly impairs the seismic performance of reinforced concrete (RC) columns in building structures. This paper examines three key parameters related to the seismic performance of RC columns: seismic failure modes, maximum bearing capacity, and effective stiffness. The design methodologies for RC columns vary significantly depending on the failure modes, as different failure modes involve distinct mechanical characteristics, thereby influencing the corresponding bearing capacity and effective stiffness. In this study, an intelligent approach is proposed, which first performs the classification of failure modes and subsequently predicts the associated bearing capacity and effective stiffness through regression analysis. Seven supervised learning algorithms and one deep learning algorithm were utilized in this study, with particular emphasis on the k-nearest neighbor (KNN) algorithm due to its simplicity and effectiveness. A comprehensive dataset comprising 221 corroded column specimens under cyclic loading tests was collected, and the findings indicate that the KNN-based model exhibits a high degree of accuracy in failure modes classification (accuracy = 0.91), bearing capacity prediction (R2 = 0.99), and effective stiffness prediction (R2 = 0.95). Comparisons with other algorithms were conducted, and the results indicate that the KNN algorithm outperforms the others. Furthermore, the bearing capacity and effective stiffness predictions generated by the KNN algorithm were compared with empirical formulas from design codes, revealing the clear superiority of the proposed method. Thus, it can be concluded that machine learning techniques offer a promising alternative to traditional mechanics-driven models, particularly in the context of big data and the unique challenges posed by the complex mechanical behavior of RC columns in buildings.

关键词： machine learning K -nearest neighbor Reinforced concrete column Effective stiffness Predictions

来源：评论

学校读者我要写书评

暂无评论

An Improved Federated learning Intrusion Detection with Collaborative Feature Selection on CICIDS 2017 30th

An Improved Federated Learning Intrusion Detection with Coll...

引用

30th international conference on Computational and Experimental engineering and Sciences, ICCES 2024

作者： Cao, Yuan Chen, Chien-Ming Shandong University of Science and Technology No. 579 Qianwangang Road Shandong Qingdao China

ISBN: (纸本)9783031829062

This paper explores the application of feature selection in intrusion detection using federated learning, aimed at compressing training data features. It addresses the challenges posed by high-dimensional and redundant features in deep learning models, exacerbated in federated learning settings. Leveraging the gain-based importance of decision trees and entropy-based information gain, a collaborative selection algorithm is devised to reduce feature dimensionality. Contributions include a selection methodology, an intrusion detection system employing federated learning, process optimization, and achieving 97.81% accuracy on a subset of the CIDIDS2017 dataset, with training time reduced to one-third. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Automating Accessibility Compliance: Leveraging machine learning to Analyze Developer Challenges with WCAG Guidelines 8

Automating Accessibility Compliance: Leveraging Machine Lear...

引用

8th international conference on data Science and machine learning Applications, CDMA 2025

作者： Alghamdi, Asmaa Mansour Aljedaani, Wajdi Ludi, Stephanie Javed, Yasir University of North Texas United States Jazan University Saudi Arabia Saudi Authority for Data and Artificial Intelligence Saudi Arabia Prince Sultan University Saudi Arabia

ISBN: (纸本)9798331539696

The prevailing strategy for ensuring web application accessibility relies heavily on adherence to established guidelines, particularly the Web Content Accessibility Guidelines (WCAG). However, the process of interpreting and implementing these guidelines presents significant challenges for developers, which are often compounded by the time-consuming nature of manual analysis required to ensure compliance. Despite the critical importance of accessibility, there remains limited exploration of these challenges within the development process. In this paper, we aim to address these challenges by leveraging machine learning techniques to automatically classify and analyze accessibility-related issues discussed by developers on Stack Overflow, with a focus on understanding their connection to WCAG 2.2 guidelines. To achieve this, we analyzed 5,644 developers' posts related to web accessibility collected from Stack Overflow between 2008 and 2022. These posts were categorized according to the principles of WCAG 2.2 using advanced machine learning models, including Random Forest, Support Vector machine (SVM), Gradient Boosting, AdaBoost, and Multi-Layer Perceptron (MLP). The results highlight a strong emphasis among developers on addressing complex, non-linear accessibility issues. Our analysis demonstrated that Random Forest and Gradient Boosting models were most effective, achieving accuracy rates of 0.987 and 0.986, respectively. These findings underscore the challenges developers face in aligning with accessibility standards, particularly in areas such as time-based media customization and screen reader configuration, and the potential for machine learning to support more efficient and accurate compliance with accessibility guidelines. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Stock trend prediction based on multi-factor screening machine 24

Stock trend prediction based on multi-factor screening machi...

引用

5th international conference on Computer Science and Management Technology, ICCSMT 2024

作者： Hu, Ruijie Faculty of Science and Technology Guangdong Provincial Key Laboratory of Interdisciplinary Research and Application for Data Science BNU-HKBU United International College Zhuhai China

ISBN: (纸本)9798400709999

With the rapid development of financial markets, stock price prediction, as a highly complex and challenging topic, has attracted more and more attention from academia and industry. This study aims to use multiple machine learning algorithms to predict stock market prices, especially exploring the advantages of deep learning models in capturing market nonlinear and time series characteristics. In this article, a machine learning model is used for contribution analysis, analyzing multiple features of stocks, performing a weighted combination analysis of features, and then using a convolutional neural network to perform feature extraction and analysis of stocks, and combining the attention mechanism for deep feature extraction, and finally use the long short-term memory network (LSTM) model to output the model to analyze and predict future stock trends. The experimental results show that combining deep learning analysis technology and factor screening machine can significantly improve the prediction accuracy of the model. At the same time, this article also compared the performance of different models in different market environments, and concluded that in markets with higher volatility, models based on deep learning are more stable. Ultimately, this research provides a new technical means for risk management and investment decisions in financial markets. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

E-learning Platform for Information Technology in Business Management 12th

E-learning Platform for Information Technology in Business M...

引用

12th international conference of machine and Industrial Design in Mechanical engineering

作者： Prajova, Vanessa Praj, Filip Kostal, Peter Homokyova, Maria Slovak Univ Technol Fac Mat Sci & Technol Trnava Trnava Slovakia

ISBN: (纸本)9783031805141;9783031805127;9783031805110

The development of information technology and digitalisation is now having a major impact on the overall development of the industry. Today's industrial enterprises are constantly striving to improve their processes and efficiency, and digitalisation and information technology can be key tools for achieving these goals. Information technology (IT) plays a very important role in industrial enterprises today. It enables businesses to adapt to rapid and rapid market changes and improve their competitiveness. Digitalisation brings many benefits to industry, which are reflected in increased efficiency, performance and innovation. One of the biggest benefits of digitisation is automation. Production lines are able to produce continuously 24 h a day without human intervention, increasing production capacity and reducing errors. Automation reduces errors in production and increases efficiency and output, helping businesses save costs and improve their profitability. Another benefit is improving the quality of products and services. Thanks to IT, the quality of data is improved, which helps in decision-making and planning. Digital data analysis enables businesses to identify weaknesses and improve processes, thereby increasing the quality of products and services. Last but not least, it is important to stress that information systems also help businesses in decision-making and planning. Analytical tools can process huge amounts of data, which are then used in decision-making and planning, thereby increasing efficiency and reducing the risk of errors. Nowadays, many businesses are trying to use information technology and information systems to their advantage. In particular, industrial enterprises often use information systems for production planning and management, as well as for monitoring product quality and tracking consumer trends.

关键词： E-learning Information technology Modules of enterprise information systems Business processes

来源：评论

学校读者我要写书评

暂无评论

Exploring the rare-earth zirconate ceramics RE2Zr2O7 with ultralow thermal conductive through an interpretable machine learning

引用

international JOURNAL OF HEAT AND MASS TRANSFER 2025年 236卷

作者： Yao, Hang Shan, Dongliang Pan, Kai Xie, Shuhong He, Zhijian Lei, Chihou Liu, Yunya Xiangtan Univ Sch Mat Sci & Engn Hunan Prov Key Lab Thin Film Mat & Devices Xiangtan 411105 Peoples R China Xiangtan Univ Sch Mat Sci & Engn Key Lab Low Dimens Mat & Applicat Technol Minist Educ Xiangtan 411105 Peoples R China Univ Scranton Dept Phys & Engn Scranton PA 18510 USA

Thermal barrier coatings (TBCs) have a unique advantage in aviation engines and industrial gas turbines due to their low thermal conductivity (TC). Rare-earth zirconate ceramics RE2Zr2O7 (RE=La similar to Lu, Y) with low TC and high-temperature thermal stability are leading candidates for the next generation of TBCs. Introducing rare-earth elements into the RE-site to form multi-component solid solutions can effectively reduce the TC of RE2Zr2O7 ceramics;however, as the increase of doping elements, the experimental difficulty escalates sharply, so there is an urgent need to find new methods to predict the TC of RE2Zr2O7 ceramics. Based on the TC data of RE2Zr2O7 ceramics, combined with a machine learning (ML) approach and feature engineering, an ML model for predicting the TC of RE2Zr2O7 ceramics is established in this work. Using the SHapley Additive exPlanations (SHAP) method to explain the predictions of the ML model, it has been found that reducing the TC of RE2Zr2O7 ceramics can be achieved by increasing the atomic species and decreasing the weighted mean atomic molar volume of the RE-site. The TC of about 150,000 new RE2Zr2O7 ceramics in the component search space is predicted by our established ML model, and a new RE2Zr2O7 ceramic (Nd0.4Er0.5Yb0.1)(2)Zr2O7 with low TC potential is found. At 1400 degrees C, the predicted TC of (Nd0.4Er0.5Yb0.1)(2)Zr2O7 is 0.797 Wm(-1)K-1, which is 12.42 % lower than 0.91 Wm(-1)K-1 for (Gd0.4Sm0.5Yb0.1)(2)Zr2O7 with ternary solid solution at RE-site. This work provides a new strategy for the experimental exploration of RE2Zr2O7 ceramics with low TC.

关键词： Thermal conductivity machine learning Interpretable RE2Zr2O7

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：