检索结果-内蒙古大学图书馆

A deep neural network based surrogate model for damage identification in full-scale structures with incomplete noisy measurements

引用

Frontiers of Structural and civil engineering 2024年第3期18卷 393-410页

作者： Tram BUI-NGOC Duy-Khuong LY Tam T TRUONG Chanachai THONGCHOM T.NGUYEN-THOI Laboratory for Computational Mechanics Institute for Computational Science and Artificial IntelligenceVan Lang UniversityHo Chi Minh City 70000Vietnam Faculty of Mechanical-Electrical and Computer Engineering School of TechnologyVan Lang UniversityHo Chi Minh City 70000Vietnam Faculty of Civil Engineering School of TechnologyVan Lang UniversityHo Chi Minh City 70000Vietnam Department of Computer Science Aarhus UniversityAarhus 8000Denmark Thammasat University research unit in structural and foundation engineering Department of Civil EngineeringThammasat UniversityPathumthani 12120Thailand Laboratory for Applied and Industrial Mathematics Institute for Computational Science and Artificial IntelligenceVan Lang UniversityHo Chi Minh City 70000Vietnam Thammasat School of Engineering Thammasat UniversityPathumthani 12120Thailand

The paper introduces a novel approach for detecting structural damage in full-scale structures using surrogate models generated from incomplete modal data and deep neural networks(DNNs).A significant challenge in this field is the limited availability of measurement data for full-scale structures,which is addressed in this paper by generating data sets using a reduced finite element(FE)model constructed by SAP2000 software and the MATLAB programming *** surrogate models are trained using response data obtained from the monitored structure through a limited number of measurement *** proposed approach involves training a single surrogate model that can quickly predict the location and severity of damage for all potential *** achieve the most generalized surrogate model,the study explores different types of layers and hyperparameters of the training algorithm and employs state-of-the-art techniques to avoid overfitting and to accelerate the training *** approach’s effectiveness,efficiency,and applicability are demonstrated by two numerical *** study also verifies the robustness of the proposed approach on data sets with sparse and noisy measured ***,the proposed approach is a promising alternative to traditional approaches that rely on FE model updating and optimization algorithms,which can be computationally *** approach also shows potential for broader applications in structural damage detection.

关键词： vibration-based damage detection deep neural network full-scale structures finite element model updating noisy incomplete modal data

来源：评论

学校读者我要写书评

暂无评论

Incremental Machine Learning Predictive Analysis for Agricultural Applications Using A Modular Weather Monitoring Sensor in Infanta, Quezon 8

Incremental Machine Learning Predictive Analysis for Agricul...

引用

8th International Conference on electrical, Telecommunication and computer engineering, ELTICOM 2024

作者： Tupaz, Zmantha Ysabel Cruz, Febus Reidj Monjardin, Cris Edward School of Graduate Studies Mapua University Manila Philippines School of Electrical Electronics and Computer Engineering Mapua University Manila Philippines School of Civil Environmental and Geological Engineering Mapua University Manila Philippines

ISBN: (纸本)9798331531249

The Philippines considers agriculture as an important part of the country's economic security, so when it comes to agriculture, there is always a demand when it comes to management. Specifically, Infanta, Quezon, a city in Southern Luzon, is often plagued with typhoons and landslides that affect their agriculture. This is why weather sensors play a big role in their city. These weather sensors play a big role in their agricultural areas as they help with irrigation control and flood mapping, which are often paired with predictive analysis using machine learning to help evaluate critical weather conditions. The study's objective is to develop an incremental machine learning algorithm using pre-existing machine learning techniques as a baseline to classify data from the modified weather sensor system to determine the status of the agricultural fields. The researcher tested LSTM, SVM, and Random Forest as its baseline model for the incremental model, and Random Forest was used for the baseline. Through thorough exploration of the parameters and models, the researchers were able to utilise the best model for predictions in the agricultural aspect. The incremental models for soil moisture prediction and crop yield prediction, which work hand-in-hand, are 98% and 98.3 %, respectively. © 2024 IEEE.

关键词： Soil moisture

来源：评论

学校读者我要写书评

暂无评论

Automated Ergonomics-Based Productivity Analysis for Intelligent Manufacturing in Industrialized Construction

Automated Ergonomics-Based Productivity Analysis for Intelli...

引用

Annual Conference of the Canadian Society of civil engineering, CSCE 2021

作者： Wang, Jingwen Mohamed, Yomna Han, SangHyeok Li, Xinming Al-Hussein, Mohamed Department of Civil and Environmental Engineering University of Alberta Edmonton Canada Department of Electrical and Computer Engineering University of Alberta Edmonton Canada Department of Building Civil and Environmental Engineering Concordia University Montreal Canada Department of Mechanical Engineering University of Alberta Edmonton Canada

ISBN: (纸本)9789811909672

Construction workers perform repetitive and physically demanding tasks that expose them to the risk of developing work-related musculoskeletal disorders. Accurate estimation of the cycle times of manual operations is essential for reliable planning and scheduling as well as for ergonomic risk assessment. However, the reliability of the standardized cycle time analysis is hindered by its dependence on various factors that change with the increasing complexity of the working environment, as well as by the inherent challenges involved in acquiring accurate measurements. This study thus investigates the integration of predetermined motion time systems (PMTSs) with ergonomic risk assessments in 3D visualization for the purposes of cycle time estimation and ergonomic risk evaluation. An integrated approach is implemented to provide an automated and user-friendly method of analyzing manual operations at the motion level in the design phase. The actual and simulated cycle times and ergonomic risks are compared and analyzed using a case study. Preliminary cases are provided to demonstrate the feasibility and the potential applications of the proposed method. The proposed method is shown to be capable of quantifying the required cycle time and the ergonomic risks associated with body parts during the execution of manual operations. Using the proposed method, rapid ergonomic-centric workplace design can be achieved that, in turn, helps to improve productivity while mitigating ergonomic risk. The proposed method can be implemented to improve occupational health and safety, increase the reliability of planning and scheduling, and boost the overall productivity of industrialized construction. © 2023, Canadian Society for civil engineering.

关键词： Scheduling

来源：评论

学校读者我要写书评

暂无评论

Context-Aware PPE Compliance Check in Far-Field Monitoring 19th

Context-Aware PPE Compliance Check in Far-Field Monitoring

引用

19th International Conference on Computing in civil and Building engineering, ICCCBE 2022

作者： Chern, Wei-Chih Hyeon, Jeongho Nguyen, Tam V. Asari, Vijayan K. Kim, Hongjo Department of Electrical and Computer Engineering University of Dayton DaytonOH45469 United States Department of Civil and Environmental Engineering Yonsei University Seoul Korea Republic of Department of Computer Science University of Dayton DaytonOH45469 United States

ISBN: (纸本)9783031353987

Context-aware safety monitoring based on computer vision has received relatively little attention, although it is critical for recognizing the working context of workers and performing precise safety assessment with respect to Personal Protective Equipment (PPE) compliance checks. To address this knowledge gap, this study proposes vision-based monitoring approaches for context-aware PPE compliance checks using a modularized analysis pipeline composed of object detection, semantic segmentation, and depth estimation. The efficacy of two different approaches under this methodology was examined using YUD-COSAv2 data collected from actual construction sites. In experiments, the proposed method was able to distinguish between workers at heights and on the ground, applying different PPE compliance rules for evaluating workers’ safety. The depth estimation model achieved an Average Precision of 78.50%, while the segmentation model achieved an Average Precision of 86.22%. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

CARL: Congestion-Aware Reinforcement Learning for Imitation-Based Perturbations in Mixed Traffic Control 14

CARL: Congestion-Aware Reinforcement Learning for Imitation-...

引用

14th IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems, CYBER 2024

作者： Poudel, Bibek Li, Weizi Li, Shuai University of Tennessee Min H. Kao Department of Electrical Engineering and Computer Science KnoxvilleTN United States University of Tennessee Department of Civil and Environmental Engineering KnoxvilleTN United States

ISBN: (纸本)9798331506056

Human-driven vehicles (HVs) exhibit complex and diverse behaviors. Accurately modeling such behavior is crucial for validating Robot Vehicles (RVs) in simulation and realizing the potential of mixed traffic control. However, existing approaches like parameterized models and data-driven techniques struggle to capture the full complexity and diversity. To address this, in this work, we introduce CARL, a hybrid approach that combines imitation learning for close proximity car-following and probabilistic sampling for larger headways. We also propose two classes of RL-based RVs: a safety RV focused on maximizing safety and an efficiency RV focused on maximizing efficiency. Our experiments show that the safety RV increases Time-to-Collision above the critical 4 second threshold and reduces Deceleration Rate to Avoid a Crash by up to 80%, while the efficiency RV achieves improvements in throughput of up to 49%. These results demonstrate the effectiveness of CARL in enhancing both safety and efficiency in mixed traffic. © 2024 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Environmental Sound Pollution Mapping Using Supervised Deep Learning 2

Environmental Sound Pollution Mapping Using Supervised Deep ...

引用

2nd International Conference on Information and Communication Technology, ICICT 2024

作者： Pathan, Shadman Mahmood Khan Imran, Sakan Binte Iqbal, M.M. Shabab Dept of Electrical and Computer Engineering Old Dominion University United States Bachelor of Medicine & Bachelor of Surgery Sir Salimullah Medical College Bangladesh Civil Engineering Kalinga Institute of Industrial Technology India

ISBN: (纸本)9798331508227

An accurate sound pollution map is necessary in urban environments where sound pollution is prevalent. However, obtaining dense sound pollution data across an area is challenging due to sparse measurements and limited availability of real data. This project aims to develop a framework for predicting dense sound pollution maps based on sparse measurements, leveraging techniques from computer vision. A U-Net Regression model is employed to reconstruct dense sound pollution maps from sparse measurements, portraying the model as a technique for generating sound pollution map images. The performance of the U-Net model is compared with the popular mapping technique called Gaussian Process Regression (GPR), demonstrating that the U-Net model achieves superior accuracy. Furthermore, the ability to generate dense sound pollution maps from sparse data collection via sensors or other methods makes our approach economically and environmentally sustainable. ©2024 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Trends,benefits,risks,and challenges of IoT implementation in residential and commercial buildings

引用

Energy and Built Environment 2022年第3期3卷 251-266页

作者： Kehinde Lawal Hamed Nabizadeh Rafsanjani School of Electrical and Computer Engineering University of GeorgiaAthensGA 30602USA School of Environmental CivilAgriculturaland Mechanical EngineeringUniversity of GeorgiaAthensGA 30602USA

Residential and commercial buildings are undergoing a dramatic change,and the Internet of Things(IoT)tech-nologies are shaping the future of these *** have recently utilized IoT in a variety of applica-tions and settings to transfer conventional buildings into smart,efficient,and secure *** functional IoT approaches have been developed,there is still a need for improvement in IoT applications and operations to understand the full potential of this *** improvement can properly be done by bridging the gaps of the current literature to provide a building block for future *** objective of this paper is to present a comprehensive review of research work on the existing technologies and applications of IoT in residential and commercial *** residential buildings,studies are divided to three major categories of home automa-tion,intelligent energy management systems,and healthcare *** commercial buildings,the current literature is divided to four categories of office buildings,healthcare facilities,educational buildings,and restau-rants and retail *** on the review of each category,the trends,current benefits and risks,and future challenges of the IoT implementation in the built environments are identified and *** particular,in-tegration of various IoT technologies with different capabilities,data storage and processing,and privacy and security risks are identified as the main challenges for IoT *** addition,our results show that the commercial building sector has received more attention compared to the residential building *** providing the directions for future research opportunities,this paper benefits IoT developers and researchers to properly identify their work boundaries and define their contributions.

关键词： Internet of things Residential buildings Commercial buildings Smart buildings Review

来源：评论

学校读者我要写书评

暂无评论

MHANDTI: Drug-Target Interaction Prediction Model Based on Heterogeneous Graph Multi-Hop Attention Networks

MHANDTI: Drug-Target Interaction Prediction Model Based on H...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Zhang, Chen Sun, Jiaqi Xing, Linlin Zhang, Longbo Cai, Hongzhen Guo, Maozu Shandong University of Technology School of Computer Science and Technology Zibo China Shandong University of Technology College of Agricultural Engineering and Food Science Zibo China Beijing University of Civil Engineering and Architecture College of Electrical and Information Engineering Beijing China

ISBN: (纸本)9798350386226

Predicting drug-target interactions (DTI) has become an important step in the drug discovery and drug repositioning process. The biological identification of DTI incurs significant financial and temporal costs, and the deployment of computational methodologies for DTI prediction can substantially curtail both the duration and economic expenditure of drug discovery or repositioning. Drawing from disparate data sources can offer a comprehensive overview and diverse perspectives for predicting drug-target interactions. However, existing methods for processing drug and target information are unable to capture long-range dependency across heterogeneous graphs. To capture more comprehensive drug and target features for DTI prediction, this article proposes a drug-target interaction prediction model based on heterogeneous graph multi-hop attention networks, called MHANDTI. Concretely, the word-level deep convolutional neural network is used to obtain the structural features of drugs and targets as attributes of drug and target entity nodes in heterogeneous graphs. For the processing of heterogeneous graphs, MHANDTI designs a multi-hop attention diffusion layer (MHADL) to establish a connection between the non-direct connection nodes, and summarize the characteristics of the adjacent nodes of the center nodes in several hops. A series of results indicate that the performance of this method is superior to the latest existing frameworks. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

MaDEVIoT: Cyberattacks on EV Charging Can Disrupt Power Grid Operation

MaDEVIoT: Cyberattacks on EV Charging Can Disrupt Power Grid...

引用

2024 IEEE Power and Energy Society Innovative Smart Grid Technologies Conference, ISGT 2024

作者： Acharya, Samrat Khan, Hafiz Anwar Ullah Karri, Ramesh Dvorkin, Yury Pacific Northwest National Laboratory RichlandWA99354 United States New York University Department of Electrical and Computer Engineering BrooklynNY11201 United States Johns Hopkins University Ralph o'Connor Sustainable Energy Institute Department of Electrical and Computer Engineering Department of Civil and Systems Engineering BaltimoreMD21218 United States

ISBN: (纸本)9798350313604

This paper examines the feasibility of demand-side cyberattacks on power grids launched via internet-connected high-power EV Charging Stations (EVCSs). By distorting power grid frequency and voltage, these attacks can trigger system-wide outages. Our case study focuses on Manhattan, New York, and reveals that such attacks will become feasible by 2030 with increased EV adoption. With a single EVCS company dominating Manhattan, compromising a single EVCS server raises serious power grid security concerns. These attacks can overload power lines and trip over-frequency (OF) protection relays, resulting in a power grid blackout. This study serves as a crucial resource for planning authorities and power grid operators involved in the EV charging infrastructure roll-out, highlighting potential cyberthreats to power grids stemming from high-power EVCSs. © 2024 IEEE.

关键词： Relay protection

来源：评论

学校读者我要写书评

暂无评论

Environmental Disinfection Based on Mobile Intelligent Networking Highly Efficient Ultraviolet Light Machines

引用

Aerosol and Air Quality Research 2024年第2期24卷 1-10页

作者： Chung, Chun-Yen Sung, Wen-Tsai Wang, Lin-Chi Siami, Lailatus Santos, John Paul Computer and Game Development Program Kun Shan University Tainan710303 Taiwan Department of Electrical Engineering National Chin-Yi University of Technology Taichung411030 Taiwan Department of Marine Environmental Engineering National Kaohsiung University of Science and Technology Kaohsiung81157 Taiwan Department of Environmental Engineering Chung Yuan Christian University Taoyuan32023 Taiwan Department of Civil Engineering Chung Yuan Christian University Taoyuan32023 Taiwan

Since 2019, the world has suffered from the outbreak of the "Coronavirus Disease (COVID)-19 pandemic. This study used the principle of Ultraviolet (UV)-C disinfection to produce a mobile high-power UV-C sterilizer. It focused on combining intelligent control systems, human sensors, and Internet of Things (IoT) systems to carry out disinfection tasks in unmanned indoor spaces. Because of its mobile nature, the sterilizer could be moved at any time in various learning, research, and activity rooms for disinfection. In addition to manually controlling the sterilizer, a Wi-Fi or Narrowband (NB)-IoT-enabled remote control was provided to start the disinfection process. In order to prevent ultraviolet light from harming the human body, sensors were employed self-acting to detect the presence of people and turn off the ultraviolet light when people were detected in the area. At the same time, a camera on the sterilizer would capture an image and notify the relevant personnel through a LINE notification, to prevent the human body from being exposed to ultraviolet light, causing harm to the teachers and students on campus. During operation, voice broadcast reminders and a status indicator could provide information about the operation status. After disinfection, users could view the disinfection process through a mobile device application or a webpage, which would automatically notify relevant personnel of the disinfection status through a LINE notification. In this way, the disinfection progress could be updated at anytime, anywhere and the current disinfection status in the classroom could be displayed in real-time, allowing teachers and students on campus to carry out teaching and learning in a safe and secure environment. © The Author(s).

关键词： Internet of things

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：