检索结果-内蒙古大学图书馆

26th international conference on Computer Supported Cooperative Work in Design, CSCWD 2023

作者： Wu, Yirong He, Wenjing Sun, Shuifa Tang, Tinglong China Three Gorges University Yichang Key Laboratory of Intelligent Medicine College of Computer and Information Technology Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering Yichang443002 China

ISBN: (纸本)9798350331684

There is an urgent need for industrial manufacturing to fully integrate with emerging technologies to build enterprise core competitiveness. Currently, existing methods have difficulty meeting the high-precision and stability practical requirements with diversified industrial products. In this study, a PMAE (Parallel Multiple AutoEncoders, PMAE) model is proposed, which is designed with parallel multiple encoders based on the AutoEncoder framework. It uses the network of parallel multiple encoders with different encoder structures to obtain latent features that have rich and precise semantic information. A consistency objective function is proposed to make the PMAE network converge stably and rapidly, which allows the aggregated latent features to be simultaneously reconstructed and adaptively classified. Compared with the state-of-the-art methods on the NEU-CLS, data-Crack, and DAGM2007 datasets, our method achieves the most stable performance and the highest accuracy in different defect detection tasks. © 2023 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Full-Spectrum-knowledge-Aware Unsupervised Network for Photon-counting CT Imaging 7

Full-Spectrum-Knowledge-Aware Unsupervised Network for Photo...

引用

7th international conference on Image Formation in X-Ray Computed Tomography

作者： Li, Danyang Duan, Zheng Zeng, Dong Bian, Zhaoying Ma, Jianhua School of Biomedical Engineering Southern Medical University Guangzhou510515 China

ISBN: (纸本)9781510656697

Deep learning (DL) based methods have been widely adopted in computed tomography (CT) field. And they also show a great potential in photon-counting CT (PCCT) imaging field. They usually require a large quantity of paired data to train networks. However, it is time-consuming and expensive to collect such large-scale PCCT dataset. In addition, lots of energy-integrating detector (EID) data are not yet included in the DL-based PCCT reconstruction network training. In this work, to address the issue of limited PCCT data and take advantage of labeled EID data, we propose a novel unsupervised full-spectrum-knowledge-aware DL-based network (FSANet), which contains supervised and unsupervised networks, to produce high-quality PCCT images. Specifically, the supervised network is trained based on paired EID dataset and serves as the prior knowledge to regularize the unsupervised PCCT network training. Moreover, a data-fidelity term for characterizing the PCCT image characteristics is constructed as a self-supervised term. Finally, we train the PCCT network with the prior knowledge and self-supervised terms following an unsupervised learning strategy. Numerical studies on synthesized clinical data are conducted to validate and evaluate the performance of the presented FSANet method, qualitatively and quantitatively. The experimental results demonstrate that presented FSANet method significantly improves the PCCT image quality in the case of limited photon counts. © 2022 SPIE.

关键词： Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of the Features of Major Green Building Rating Tools (GBRTs): A Systematic Review 8th

Comparative Analysis of the Features of Major Green Building...

引用

8th international conference on Civil engineering, ICOCE 2024

作者： Okeke, Francis O. Ezema, Emmanuel C. Ibem, Eziyi O. Sam-amobi, Chinwe Ahmed, Abdullahi Department of Architecture University of Nigeria Enugu Campus Enugu Nigeria School of Engineering Technology and Design Canterbury Christ Church University EnglandCT1 1QU United Kingdom

ISBN: (纸本)9789819759095

The need for sustainable buildings has gained traction as a result of escalating negative environmental impacts of the conventional building type. A plethora of different green building rating systems and assessment tools have been developed and implemented around the globe to gage the performance of buildings in meeting sustainability goals. However, it is not clear the most common and widely adopted green building rating tools (GBRTs). This study identifies the most widely adopted GBRTs and their features through a systematic review of literature. A total of 52 articles published between 1997 and 2021 drawn from the World Green Building Council database and Google Scholar were included in this review. The data were analyzed using thematic content analysis. The results reviewed that there are ten most widely adopted GBRTs across the world with the LEED, BREEAM, and Passivhaus being the top three. It was also observed that even though each of the ten identified GBRTs has its focus on one or more elements of green building design, there exists a marked variation in the level of emphasis on the different green building elements due to different regional considerations. The study concludes that adequate knowledge of the most widely used GBRTs and their key features is a prerequisite for their adoption by industry stakeholders for the attainment of sustainability goals. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Green buildings

来源：评论

学校读者我要写书评

暂无评论

Building energy management system research in South Africa-A decade overview

引用

ENERGY REPORTS 2023年 9卷 33-39页

作者： Agbajor, Favour David Mewomo, Modupe Cecilia Umoh, Vincent B. Makanjuola, Sina A. Durban Univ Technol Dept Construct Management & Quant Surveying ZA-4001 Durban South Africa Durban Univ Technol Smart Grid Res Ctr Dept Elect Power Engn ZA-4001 Durban South Africa Fed Univ Technol Akure Dept Bldg Gaga 340252 Nigeria

Buildings account for about one-third of worldwide energy use alongside CO2 emission, and their energy demand is envisaged to increase in the upcoming decades, thus increasing the worries about climate change. Building energy management system (BEMS) is a strategic method that can assuage these impacts, balance the energy demand-supply mismatch, enhance building energy efficiency and whatnot. Information surrounding this subject should be readily available considering its significance. However, this is not the case as there is a dearth of such information in the form of a systematic review of scholarly contributions on BEMS in South Africa. Thus, this paper aims to fill the knowledge gap through an in-depth overview and analysis of recent research outputs from five prominent academic databases. Herein, the study unveils and discusses the BEMS in South Africa while drawing insights from five subsets namely: building typology;building services system;methodological approach and testbed;applied BEMS strategy;and focused energy management system task. The study synthesis revealed HVAC systems as the major building services system, while demand-side management is mostly considered as the ideal applied strategy, all which mainly manipulated in residential buildings. Based on the research findings, the paper proposes the utilization of novel data-driven methods for researchers and policymakers when developing models for energy datasets to achieve optimal results for monitoring building end-use energy patterns to improve energy saving and achieve the country's ambitious goal of carbon neutrality. (C) 2023 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license (http://***/licenses/by-nc-nd/4.0/).

关键词： Energy efficiency Energy management system Demand response Optimization data driven Carbon neutrality

来源：评论

学校读者我要写书评

暂无评论

Towards Low-Barrier Cybersecurity Research and Education for Industrial Control systems 20

Towards Low-Barrier Cybersecurity Research and Education for...

引用

20th IEEE international conference on Intelligence and Security Informatics, ISI 2023

作者： McGuan, Colman Yu, Chansu Lin, Qin Cleveland State University Department of Electrical Engineering and Computer Science 2121 Euclid Avenue ClevelandOH44115 United States

ISBN: (纸本)9798350337730

The protection of Industrial Control systems (ICS) that are employed in public critical infrastructures is of utmost importance due to catastrophic physical damages cyberattacks may cause. The research community requires testbeds for validation and comparing various intrusion detection algorithms to protect ICS. However, there exist high barriers to entry for research and education in the ICS cybersecurity domain due to expensive hardware, software, and inherent dangers of manipulating real-world systems. To close the gap, built upon recently developed 3D high-fidelity simulators, we further showcase our integrated framework to automatically launch cyberattacks, collect data, train machine learning models, and evaluate for practical chemical and manufacturing processes. On our testbed, we validate our proposed intrusion detection model called Minimal Threshold and Window SVM (MinTWin SVM) that utilizes unsupervised machine learning via a one-class SVM in combination with a sliding window and classification threshold. Results show that MinTWin SVM minimizes false positives and is responsive to physical process anomalies. Furthermore, we incorporate our framework with ICS cybersecurity education by using our dataset in an undergraduate machine learning course where students gain hands-on experience in practicing machine learning theory with a practical ICS dataset. All of our implementations have been open-sourced. © 2023 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Property Graph Schema Optimization for Domain-Specific knowledge Graphs 37

Property Graph Schema Optimization for Domain-Specific Knowl...

引用

37th IEEE international conference on data engineering (IEEE ICDE)

作者： Alotaibi, Rana Lei, Chuan Quamar, Abdul Efthymiou, Vasilis Ozcan, Fatma Univ Calif San Diego La Jolla CA 92093 USA IBM Res Almaden San Jose CA USA

ISBN: (纸本)9781728191843

Enterprises are creating domain-specific knowledge graphs by curating and integrating their business data from multiple sources. Ontologies provide a semantic abstraction for such knowledge graphs to describe their data in terms of the entities involved and their relationships. There has been a lot of effort to build systems that enable efficient querying over knowledge graphs, represented as property graphs. However the problem of schema optimization in the property graph setting has been largely ignored. In this work, we show that graph schema design has significant impact on query performance, and propose two algorithms to generate an optimized property graph schema from the domain ontology. To the best of our knowledge, we are the first to present an ontology-driven approach for property graph schema optimization. The rich semantic relationships in an ontology contain a variety of opportunities to reduce edge traversals and consequently improve the graph query performance. Our experimental study with two real-world knowledge graphs shows that our algorithms produce high-quality schemas, achieving up to 2 orders of magnitude speed-up compared to alternative schema designs.

关键词： knowledge engineering conferences Semantics Ontologies data engineering Optimization Business

来源：评论

学校读者我要写书评

暂无评论

Structural Assessment Based on Computational Models and Digital Twin Technologies 28

Structural Assessment Based on Computational Models and Digi...

引用

28th international Scientific conference on Transport Means 2024

作者： Duarte, J. Ribeiro, J. de Castro, P.M.S.T. Tavares, S.M.O. TEMA - Centre for Mechanical Technology and Automation Department of Mechanical Engineering University of Aveiro Aveiro3810-193 Portugal Faculdade de Engenharia Universidade do Porto Rua Dr. Roberto Frias Porto4200-465 Portugal LASI - Intelligent Systems Associate Laboratory Guimarães Portugal

Modern structural design and assessment of aerospace and automotive structures relies on numerical modelling for the analysis of complex components under diverse loading conditions and material properties, reducing the reliance on costly experimental testing. However, these models often struggle to fully replicate the intricate real-world behavior of structures. Discrepancies arise due to factors like variable loading, environmental effects, material properties scatter, manufacturing imperfections, and other effects that can only fully observable in operation. This paper explores the potential of digital twins to bridge this gap, enhancing the accuracy and reliability of structural assessments. As virtual replicas integrating numerical models with sensor data, operational history, and machine learning, digital twins offer a dynamic and comprehensive understanding of structural behavior throughout a structure's lifecycle. Approaches to enable model updating, real-time structural health monitoring, and the development of new methods for model calibration and validation that combine simulations with experimental data are proposed in this paper. This path can revolutionize design, evaluation, and maintenance processes, optimizing structures for performance and lightweight while upholding rigorous safety factors. © 2024 Kaunas University of Technology. All rights reserved.

关键词： aircraft structures artificial intelligence damage tolerance digital twins machine learning

来源：评论

学校读者我要写书评

暂无评论

Restaurant Recommendation System using Machine Learning Algorithms

Restaurant Recommendation System using Machine Learning Algo...

引用

knowledge engineering and Communication systems (ICKECS), international conference on

作者： Shefali Goyal Nongmeikapam Thoiba Singh Iesh Bajetha Sukhpreet Singh Himanshu Singh Prashant Kumar Department of Computer Science And Engineering Chandigarh University Punjab India

ISBN: (数字)9798350359688

ISBN: (纸本)9798350359695

The necessity for recommendation systems spans across various domains, not least in the realm of dining and exploring new locales. Restaurants, in particular, benefit from such systems to both attract customers and offer them a chance to indulge in preferred and renowned dishes. Discovering these dishes, especially in unfamiliar areas, poses a significant challenge. This paper introduces a restaurant recommendation system that leverages food and service rating distributions to calculate matrix density. Additionally, we implement a popularity-based model to suggest restaurants to patrons. A ranking mechanism is utilized, based on scoring, to recommend top-rated restaurants and their most popular dishes. We use singular value decomposition and collaborative filtering to improve the model. The model’s performance is assessed using the RMSE metric. This study is conducted using data from Kaggle and includes the development of a web-based application created with Python’s Flask framework.

关键词： Measurement knowledge engineering Machine learning algorithms Communication systems Collaborative filtering Filtering algorithms Information filters

来源：评论

学校读者我要写书评

暂无评论

Current Status and Consideration of Entrepreneurship Education for engineering Major Students at National Institute of Technology, Tsuruoka College 28th

Current Status and Consideration of Entrepreneurship Educati...

引用

28th international conference on knowledge Based and Intelligent information and engineering systems, KES 2024

作者： Kurata, Karin Yajima, Kuniaki Sato, Jun National Institute of Technology Tsuruoka College Tsuruoka997-8511 Japan National Institute of Technology Sendai College Sendai989-3128 Japan

This paper introduces and examines the status of students' perception of entrepreneurship education at the National Institute of Technology, Tsuruoka College. This research aims to identify and consider the factors that influence the development of entrepreneurship intention. The significance of this paper is conducting a study of students who aim to become engineers since most of the entrepreneurship education discussion happens in the field of business. Based on the theory of planned behavior, this study will conduct multiple regression analysis using SPSS software to identify the relationship between attitude, subjective norm, and perceived behavioral control with entrepreneurship intention. Results indicated that there were significant and positive effects of attitude and perceived behavior control toward entrepreneurship intention. However, there were no significant effects shown by the subjective norm. These results indicate that when conducting entrepreneurship education for students who study engineering, it is important to focus on fostering students' attitudes and perceived behavior control. The theoretical implication is that we have extended the theory of planned behavior to examine students who are studying science and engineering from the age of 15. The practical implication of this study is that it is important to foster perceived behavior control. This study will support policymakers, educators, and researchers to foster entrepreneurship education in the engineering field. © 2024 The Authors.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Intelligent Computation in manufacturing engineering-CIRP ICME '20 Editorial

引用

Procedia CIRP 2021年 99卷 1-2页

作者： Teti, Roberto Department of Chemical Materials and Industrial Production Engineering University of Naples Federico II P.le Tecchio 80 Naples80125 Italy Fraunhofer Joint Laboratory of Excellence on Advanced Production Technology Fh-J_LEAPT UniNaples P.le Tecchio 80 Naples80125 Italy

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：