检索结果-内蒙古大学图书馆

25th international conference on Intelligent data engineering and Automated learning

作者： Llacer Luna, Socrates Garigliotti, Dario Martinez Plumed, Fernando Ferri Ramirez, Cesar Univ Politecn Valencia Valencia Spain Univ Bergen Bergen Norway

ISBN: (纸本)9783031777301;9783031777318

Universitat Polit`ecnica de Val`encia (UPV) faces challenges in managing its Alfresco document repository, which contains 600,000 PDF files, of which only 100,000 are correctly categorised. Manual classification is laborious and error-prone, hindering information retrieval and advanced search capabilities. This project presents an automated pipeline that integrates optical character recognition (OCR) and machine learning to efficiently classify documents. Our approach distinguishes between scanned and digital documents, accurately extracts text and categorises it into 51 predefined categories using models such as BERT and RF. By improving document organisation and accessibility, this work optimises UPV's document management and paves the way for advanced search technologies and real-time classification systems.

关键词： Document Classification OCR machine learning Alfresco Repository

来源：评论

学校读者我要写书评

暂无评论

Predicting surface roughness in machining aluminum alloys taking into account material properties

引用

international JOURNAL OF COMPUTER INTEGRATED MANUFACTURING 2025年第4期38卷 555-576页

作者： Nguyen, Van-Hai Le, Tien-Thinh PHENIKAA Univ Fac Mech Engn & Mechatron Hanoi Vietnam A&A Green Phoenix Grp JSC PHENIKAA Res & Technol Inst PRATI Hanoi Vietnam

This study investigates the use of machine learning models to predict surface roughness (Ra) in milling multi-grade aluminum alloys without prior knowledge of optimal cutting parameters. A diverse milling dataset encompassing material properties and cutting parameters from various aluminum alloy grades was compiled from research articles. Four machine learning algorithms, Extreme Gradient Boosting (XGB), Random Forest (RFR), Catalogical Gradient Boosting (CAT), and Gradient Boosting Regression (GBR), were employed to develop the predictive model. The dataset underwent cleaning, imputation, and outlier removal to ensure data quality. Feature engineering incorporated material properties and cutting parameters for model training. Performance metrics such as RMSE, MAPE, and R2 were used to assess the models' accuracy. The SHapley Additive exPlanations (SHAP) technique was employed to interpret the models and identify influential features. GBR achieved the highest prediction accuracy with an RMSE of 0.2507 mu m, MAPE of 23.36%, and R2 of 0.8709. Thermal conductivity, feed rate, and cutting speed were consistently identified as the most influential factors, although their rankings differed slightly. This study successfully developed a GBR model for effective Ra prediction in aluminum alloy milling, supporting advancements in smart manufacturing by enabling accurate surface quality prediction and data-driven process optimization through machine learning.

关键词： Surface roughness End milling Multi-grades aluminum alloys machine learning Material properties

来源：评论

学校读者我要写书评

暂无评论

Orchestration of machine learning Models to Solves Spatial data Analysis Problems 17

Orchestration of Machine Learning Models to Solves Spatial D...

引用

17th international conference on Management of Large-Scale System Development, MLSD 2024

作者： Kumankin, Dmitriy S. Yamashkin, Stanislav A. Institute of Electronics and Lighting Engineering National Research Mordovia State University Saransk Russia

ISBN: (纸本)9798350375718

This article presents the research results on the architectures and components of machine learning model orchestration systems aimed at solving problems of spatial data analysis. The stages of the life cycle of models are considered, and the critical components of orchestration systems, as well as their functionality, are identified. An orchestrator architecture is proposed, including the considered components and a diagram of their interaction. During the study, more than fifty different scenarios were developed regarding the operating processes of the orchestration system being developed. © 2024 IEEE.

关键词： architecture of machine learning systems machine learning pipelines MLOps orchestration of machine learning models spatial data

来源：评论

学校读者我要写书评

暂无评论

Application Research of Multi-label learning Under Concept Drift

Application Research of Multi-label Learning Under Concept D...

引用

international conference on Communications, Signal Processing, and Systems, CSPS 2023

作者： Tang, Jiakang Zhou, Wei Sun, Hanbing Department of Information Engineering Suzhou University Suzhou234000 China

ISBN: (纸本)9789819975556

In order to address the interference of concept drift on the results of multi-label learning algorithms, a hybrid kernel extreme learning machine is used as the foundation for the classification algorithm. Concept drift detection is incorporated, and the classifier is updated based on the detection results for application in multi-label learning. Firstly, the data stream is divided into appropriately sized data blocks, and a hybrid extreme learning machine is used on several of the preceding data blocks to obtain the base classifier. Subsequently, the incoming data blocks are processed using the base classifier to calculate the sample mean and variance between the current data and previous data. Based on this result, it is determined whether concept drift has occurred, and the base classifiers within the ensemble model are retrained and adjusted to update the model. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

learning from high-dimensional cyber-physical data streams: a case of large-scale smart grid

引用

international JOURNAL OF machine learning AND CYBERNETICS 2025年第3期16卷 1819-1831页

作者： Hassani, Hossein Hallaji, Ehsan Razavi-Far, Roozbeh Saif, Mehrdad Univ Windsor Dept Elect & Comp Engn Windsor ON N9B 3P4 Canada Univ New Brunswick Fac Comp Sci Fredericton NB E3B 5A3 Canada Univ New Brunswick Canadian Inst Cybersecur Fredericton NB E3B 5A3 Canada

Quality of data and complexity of decision boundaries in high-dimensional data streams that are collected from cyber-physical power systems can greatly influence the process of learning from data and diagnosing faults in such critical systems. These systems generate massive amounts of data that overburden the system with excessive computational costs. Another issue is the presence of noise in recorded measurements that poses a challenge to the learning process, leading to a degradation in the performance of fault diagnosis. Furthermore, the diagnostic model is often provided with a mixture of redundant measurements that may deviate it from learning normal and fault distributions. This paper presents the effect of feature engineering on mitigating the aforementioned challenges in learning from data streams collected from cyber-physical systems. A data-driven fault diagnosis framework for a 118-bus power system is constructed by integrating feature selection, dimensionality reduction methods, and decision models. A comparative study is enabled accordingly to compare several advanced techniques in both domains. Dimensionality reduction and feature selection methods are compared both jointly and separately. Finally, experiments are concluded, and a setting is suggested that enhances data quality for fault diagnosis.

关键词： Classification Cyber-physical power systems Dimensionality reduction Fault diagnosis Feature selection High-dimensional data streams

来源：评论

学校读者我要写书评

暂无评论

machine learning for Improved Bariatric Surgery Management 6th

Machine Learning for Improved Bariatric Surgery Management

引用

6th international conference on Biomedical engineering

作者： D'Amore, Antonio D'Onofrio, Gaetano Fidecicchi, Andrea Triassi, Maria Marino, Marta Rosaria AORN Antonio Cardarelli Naples Italy Univ Naples Federico II Dept Publ Hlth Naples Italy Univ Naples Federico II Interdept Ctr Res Healthcare Management & Innovat Naples Italy

ISBN: (纸本)9783031803543;9783031803550

Bariatric surgery has emerged as an effective treatment option for individuals with severe obesity, offering not only weight loss but also remarkable improvements in metabolic health and endocrine function. Efficient management of the patient's length of stay (LOS) in the hospital is critical to optimizing healthcare resources and ensuring patient well-being. The objective of this study was to analyze post-operative LOS following bariatric surgery using machine learning (ML) algorithms and determine their predictive performance. data from 757 patients undergoing bariatric surgery from 2019 to 2022 in a single institution were collected and analyzed. The ML algorithms used included Decision Tree (DT), Random Forest (RF), and Gradient Boosted Trees (GBT). The results showed that RF and GBT had comparable accuracy (71.7% and 71.1% respectively) and outperformed DT (62.0%). RF showed better overall performance, while GBT showed higher precision for predicting shorter LOS (less than 5 days). The results highlight the potential of machine learning algorithms in predicting post-operative LOS, aiding in healthcare resource allocation and personalized patient care.

关键词： Bariatric Surgery Endocrinology machine learning

来源：评论

学校读者我要写书评

暂无评论

Comparison Analysis of Forecasting Accuracy for Electricity Consumption Using Extreme learning machine and Backpropagation Algorithms 3

Comparison Analysis of Forecasting Accuracy for Electricity ...

引用

3rd FORTEI-international conference on Electrical engineering, FORTEI-ICEE 2024

作者： Miefthawati, Nanda Putri Akbar, Sukma Aini, Zulfatri Sutoyo Department of Electrical Engineering State Islamic University of Sultan Syarif Kasim Riau Pekanbaru Indonesia

ISBN: (纸本)9798331542207

Accurate calculations are essential in forecasting. Therefore, it is important to select the appropriate forecasting method, which can be determined by testing the accuracy level of the forecasting results using the MAPE value. The purpose of this research is to analyze the comparison of the accuracy of electricity consumption forecasts using the Extreme learning machine and Backpropagation algorithms. The data used are monthly electricity consumption data as input pattern designs. The input data will be divided into two parts: training data and testing data, followed by simulations using the Extreme learning machine and Backpropagation algorithms to obtain the 2022 forecast results. The accuracy of each algorithm's forecast results will then be calculated using the MAPE value. The research results indicate that the Extreme learning machine algorithm has a MAPE value of 4.67%, where the error rate is higher than the Backpropagation algorithm, which has only 2.27%. From the algorithm testing stages, the most accurate forecasting result for electricity consumption was obtained using Backpropagation, as it has the lowest MAPE value, indicating the highest accuracy and lowest error rate. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

machine learning-based global trends and the development prospects of wastewater treatment: A bibliometric analysis

引用

JOURNAL OF ENVIRONMENTAL CHEMICAL engineering 2024年第3期12卷

作者： Xia, Libo Hao, Xiaoxuan Zhou, Yun Huazhong Agr Univ Coll Resources & Environm Wuhan 430070 Peoples R China CCCC Highway Consultants Co Ltd Beijing 100010 Peoples R China Huazhong Agr Univ Frontiers Sci Ctr Anim Breeding & Sustainable Prod Wuhan 430070 Peoples R China

Wastewater treatment is important for pollutant reduction and reclaimed water production. machine learning is increasing applied in environmental field for deciphering variables' relationships and processing large datasets. However, multifarious sewage treatment systems, technologies and data processing methods led to the widespread application of machine learning in wastewater treatment. Here, we evaluated a total of 398 publications focus on machine learning-based wastewater treatment from 1993 to 2022 using bibliometric method. We aimed to provide a quantitative analysis on research hotpots, global trends and development prospects of wastewater treatment. Results showed that the related topic began in 1993 and publications' number was significantly increased since 2018. In the past three decades, modeling-based prediction and optimization has always been a research hotspot in wastewater treatment, although the continuous increasing of multifarious research topics in this field. As the international collaboration network core, China published 22.9% of the literatures, followed by the United States (13.1%) and Spain (9.36%). Water Research is the most productive journal with 22 publications containing research articles and review papers. Pollutant and antibiotics removal prediction, and neutral network based regression prediction are three independent research categories. Future research focus will still be on modeling-based wastewater treatment prediction and optimization. The findings provide an important reference and international overview to recognize the potential opportunity for researchers whom are working on machine learning based wastewater treatment and related projects.

关键词： machine learning Wastewater treatment Bibliometric Social network analysis Thematic map

来源：评论

学校读者我要写书评

暂无评论

Trustworthy machine learning under Imperfect data 33

Trustworthy Machine Learning under Imperfect Data

引用

33rd international Joint conference on Artificial Intelligence (IJCAI)

作者： Han, Bo Hong Kong Baptist Univ Ctr Adv Intelligence Project TMLR Grp Dept Comp SciRIKEN Hong Kong Peoples R China

ISBN: (纸本)9781956792041

Trustworthy machine learning (TML) under imperfect data has recently brought much attention in the data-centric fields of machine learning (ML) and artificial intelligence (AI). Specifically, there are mainly three types of imperfect data along with their challenges for ML, including i) label-level imperfection: noisy labels;ii) feature-level imperfection: adversarial examples;iii) distribution-level imperfection: out-of-distribution data. Therefore, in this paper, we systematically share our insights and solutions of TML to handle three types of imperfect data. More importantly, we discuss some new challenges in TML, which also open more opportunities for future studies, such as trustworthy foundation models, trustworthy federated learning, and trustworthy causal learning.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Implementation of Temporal Action Detection Workflow for Video data Analysis with the Use of machine learning Operations 5

Implementation of Temporal Action Detection Workflow for Vid...

引用

5th international conference on Neural Networks and Neurotechnologies, NeuroNT 2024

作者： Kupriyanov, Mikhail S. Shichkina, Yulia A. Ilin, Semyon E. Saint Petersburg Electrotechnical University 'LETI' Department of Computer Science and Engineering St. Petersburg Russia

ISBN: (纸本)9798350363739

The article aims to discuss the peculiarities of using the machine learning Operations paradigm in the context of addressing the task of temporal action detection in video data. The results of applying machine learning Operations to the aforementioned task are analyzed at three levels of machine learning workflow, namely, at the level of machine learning system design, at the level of machine learning system components, and at the level of elements within the machine learning system components. It is emphasized that machine learning Operations facilitates the procedures of designing, developing and deploying the temporal action detection workflow. © 2024 IEEE.

关键词： Video recording

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：