检索结果-内蒙古大学图书馆

Enhancing Building Semantic Segmentation Accuracy with Super Resolution and Deep Learning: Investigating the Impact of Spatial Resolution on Various Datasets

arXiv

引用

arXiv 2023年

作者： Guo, Zhiling Shi, Xiaodan Zhang, Haoran Huang, Dou Song, Xiaoya Yan, Jinyue Shibasaki, Ryosuke Department of Building Environment and Energy Engineering The Hong Kong Polytechnic University Kowloon Hong Kong Center for Spatial Information Science The University of Tokyo Kashiwa Japan School of Architecture Harbin Institute of Technology Harbin China

The development of remote sensing and deep learning techniques has enabled building semantic segmentation with high accuracy and efficiency. Despite their success in different tasks, the discussions on the impact of spatial resolution on deep learning based building semantic segmentation are quite inadequate, which makes choosing a higher cost-effective data source a big challenge. To address the issue mentioned above, in this study, we create remote sensing images among three study areas into multiple spatial resolutions by super-resolution and down-sampling. After that, two representative deep learning architectures: UNet and FPN, are selected for model training and testing. The experimental results obtained from three cities with two deep learning models indicate that the spatial resolution greatly influences building segmentation results, and with a better cost-effectiveness around 0.3m, which we believe will be an important insight for data selection and preparation. © 2023, CC BY-NC-SA.

关键词： Cost effectiveness

来源：评论

学校读者我要写书评

暂无评论

Experimental validation of the design formulas for vibration control of stay cables using external dampers

Journal of Infrastructure Intelligence and Resilience

引用

Journal of Infrastructure Intelligence and Resilience 2022年第2期1卷

作者： Liao, Xiaowei Dong, Shenhao Duan, Yuanfeng Ni, Y.Q. College of Civil Engineering Zhejiang University of Technology Hangzhou310023 China Department of Civil Engineering College of Civil Engineering and Architecture Zhejiang University Hangzhou310058 China Department of Civil and Environmental Engineering The Hong Kong Polytechnic University Hung Hom Kowloon China Hung Hom Kowloon China

Transversely installing the dampers on the stay cable has been widely adopted to control its excessive vibration. However, the optimum damper size and its damping efficiency is subject to the effect of damper parameters, including the damper coefficient, damper inner stiffness and support stiffness, damper concentrated mass. Based on the attainable damping-ratio formulas of the stay cable–damper system proposed by authors, this study carries out a serials of experimental study on the cable-damper system to investigate the effect of the above-mentioned damper parameters and to consolidate the accuracy of the proposed damping-ratio equation. A scaled sagged stay cable has been built, and a small-size shear-mode viscoelastic damper has been developed. Results indicate that the larger damper stiffness and the lower support stiffness degrade the achievable damping ratio. Increasing the damper mass properly seems to improve the achievable damping ratio but still needs more full-scale test verification. The sag effect of the cable reduces considerably the attainable damping ratio for the first-order mode while affect marginally for the higher mode. Experimental results of the attainable damping-ratio considering the effect of the damper parameters commonly align with the theoretical values from the design formula. Therefore, the design formula is qualified to facilitate the design of the damper size. © 2022

关键词： Stiffness

来源：评论

学校读者我要写书评

暂无评论

Curved footbridges supported by a shell obtained through thrust network analysis

引用

Journal of Traffic and Transportation engineering(English Edition) 2019年第1期6卷 65-75页

作者： Luigi Fenu Eleonora Congiu Davide Lavorato Bruno Briseghella Giuseppe Carlo Marano Department of Civil and Environmental Engineering and Architecture University of Cagliari Department of Architecture University of Roma Tre College of Civil Engineering Fuzhou University Department of Sciences of Civil Engineering and Architecture Polytechnic University of Bari

After Maillart's concrete curved arch bridges were built before the Second World War, in the second half of the past century and this century, many curved bridges have been built with both steel and concrete. Conversely, since the construction of Musmeci's shell supported bridge in Potenza, few shell bridges have been constructed. This paper explains how to design a curved footbridge supported by an anticlastic shell by shaping the shell via a thrust network analysis(TNA). By taking advantage of the peculiar properties of anticlastic membranes, the unconventional method of shaping a shell by a TNA is illustrated. The shell top edge that supports the deck has an assigned layout, which is provided by the road curved layout. The form of the bottom edge is obtained by the form-finding procedure as a thrust line, by applying the thrust network analysis(TNA) in a non-standard manner,shaping the shell by applying the boundary conditions and allowing relaxation. The influence of the boundary conditions on the bridge shape obtained as an envelope of thrust lines is investigated. A finite element analysis was performed. The results indicate that the obtained shell form is effective in transferring deck loads to foundations via compressive stresses and taking advantage of concrete mechanical properties.

关键词： Shell footbridges Cantilevered deck Anticlastic shell Thrust network analysis(TNA) Concrete

来源：评论

学校读者我要写书评

暂无评论

Bidirectional Cuk Converter in Partial-Power architecture with Current Mode Control for Battery Energy Storage System in Electric Vehicles

Bidirectional Cuk Converter in Partial-Power Architecture wi...

引用

European Conference on Power Electronics and Applications

作者： J.S. Artal-Sevil J. Anzola V. Ballestín-Bernad I. Aizpuru Department of Electrical Engineering Polytechnic School of Engineering and Architecture EINA. University of Zaragoza Spain Electronics and Computer Science Department Goi Eskola Politeknikoa-Orona Ideo-Fundazioa eraikina Mondragon Unibertsitatea Spain

ISBN: (数字)9789075815399

ISBN: (纸本)9781665487009

This paper presents a partial-power processing architecture intended for an on-board charger. This module is integrated into a Battery Energy Storage System (BESS). This model allows us to easily control the charge-discharge current of the LiFePO4 battery, as well as the current injection on the DC-bus (V2G). The architecture used in the partial-power processing is based on the non-isolated bidirectional Cuk converter, with average current mode control. The purpose has been to compare both topologies, Full-Power and Partial-Power, to observe the advantages and disadvantages that each on-board charger design offers. Partial architecture has some advantages such as high power density, small size, decrease stress on devices, as the DC-DC converter only processes a fraction of the total power. Thus, the purpose of this paper has been to analyze and explore the usefulness of the non-isolated bidirectional Cuk converter with partial-power processing architecture in battery charging systems in electric vehicles. The effectiveness of the strategy has been validated by the Matlab/Simulink software simulation.

关键词： Solid modeling Process control Computer architecture DC-DC power converters Software Mathematical models Batteries

来源：评论

学校读者我要写书评

暂无评论

Analysis and Implementation of different non-isolated Partial-Power Processing architectures based on the Cuk Converter

Analysis and Implementation of different non-isolated Partia...

引用

European Conference on Power Electronics and Applications

作者： J.S. Artal-Sevil J. Anzola V. Ballestín-Bernad J.L. Bernal-Agustín Department of Electrical Engineering Polytechnic School of Engineering and Architecture EINA. University of Zaragoza Spain Electronics and Computer Science Department Goi Eskola Politeknikoa-Orona Ideo-Fundazioa eraikina Mondragon Unibertsitatea Spain

ISBN: (数字)9789075815399

ISBN: (纸本)9781665487009

This paper presents the analysis and study of different partial-power processing architectures based on the Cuk converter. Thus, the non-isolated topologies analyzed have been considered operative as voltage source converter (VSC). Likewise, the study of the converters is based on the continuous conduction mode (CCM). The partial-power topology has some advantages, such as high power density, small size, the decreased voltage in semiconductor devices, etc., this is because the DC-DC converter only processes a fraction of the total power. The purpose has been to compare the different topologies, Full-Power, Partial-Power, and hybrid-converters, in order to observe the advantages and drawbacks in each case. Among the parameters to be studied is the voltage stress in semiconductors as well as the voltage gain in each architecture. The effectiveness of these new converter architectures has been validated by the Matlab/Simulink software simulation. In this way, different simulation results are presented and analyzed throughout the paper. The purpose of this paper has been to study and explore the usefulness of the non-isolated Cuk converter with partial-power processing architecture for industrial power applications.

关键词： Simulation Computer architecture Voltage Mathematical models Software Topology Stress

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-based Seismic Fragility Curves for RC Bridge Piers

引用

Procedia Structural Integrity 2023年 44卷 1736-1743页

作者： Xuguang Wang Cristoforo Demartino Giorgio Monti Giuseppe Quaranta Alessandra Fiore Zhejiang University - University of Illinois at Urbana Champaign Institute Haining 314400 Zhejiang PR China Department of Civil and Environmental Engineering University of Illinois at Urbana-Champaign Urbana IL 61801 USA Department of Structural Engineering and Geotechnics Sapienza University of Rome via A. Gramsci 53 00197 Rome Italy Department of Structural Engineering and Geotechnics Sapienza University of Rome via Eudossiana 18 00184 Rome Italy Department of Civil Engineering Sciences and Architecture Polytechnic University of Bari via Giovanni Amendola 126/B Bari Italy

A significant part of ongoing studies in the field of earthquake engineering is directed toward the seismic risk assessment of buildings and infrastructures at a territorial scale. This task is usually accomplished by grouping the structures into homogenous classes in terms of typology, for which seismic fragility curves are then obtained for different limit states via numerical simulations or from the statistical analysis of observational data when available. Particularly, the development of typological fragility curves for bridges under earthquake is useful for assessing the reliability and resilience of transportation networks in seismic areas and can be also effective decision-making support. Within this framework, the proposed study establishes a machine learning-based paradigm for the closed-form prediction of the main statistical parameters required to obtain relevant seismic fragility curves for reinforced concrete bridge piers. Initially, a huge training dataset has been obtained by Monte Carlo simulations and displacement-based bridge pier assessments by assuming data representative of the Italian highway transportation network. Next, symbolic nonlinear regression formulae for estimating the main statistical parameters of seismic fragility curves have been generated. With the aid of those formulae, the effort of calculating the seismic fragility curves is greatly reduced since the corresponding main statistical parameters can be directly calculated from a set of commonly available attributes. Therefore, the proposed study provides a helpful tool for the rapid preliminary assessment of damage and risk level of existing highway transportation networks exposed to seismic hazards.

关键词： Bridge Piers Fragility Curve Interpretable Data-driven Models Seismic Assessment

来源：评论

学校读者我要写书评

暂无评论

Energy Efficient Lighting System Control Combined with Shading System Using IoT and AI Technologies

Energy Efficient Lighting System Control Combined with Shadi...

引用

World Conference on Complex Systems (WCCS)

作者： Fadwa. Lachhab Mohamed. Bakhouya Department of Computer Science LabSIV Faculty of sciences Ibn Zohr University Agadir Morocco LIDRA Lab International University of Agadir Polytechnic School of Agadir Universiapolis Agadir Morocco LERMALab International University of Rabat College of Engineering and Architecture Sala El Jadida Morocco

ISBN: (数字)9798331519131

ISBN: (纸本)9798331519148

Lighting system in commercial and residential buildings constitutes a major source of the world energy consumption. Optimizing energy efficiency through lighting management requires an optimal control strategy in order to balance daylighting requirements while maintaining visual comfort in illuminated spaces. This paper introduces an intelligent control approach for lighting and shading system by optimizing operation modes and balancing between them while providing constant illuminance with a maximum visual comfort. In a real-lab environment, a prototype for lighting and shading system was tested and implemented, leveraging Internet of Things (IoT) and Artificial Intelligence (AI) technologies for operation and management. AI techniques are integrated to enable a smart coordination between lighting and shading systems in order to maintain the required light level. To validate the proposed approach, experiments were carried out, and the results demonstrated the solution's effectiveness by maintaining the ideal level of lighting with efficient consumption. In fact, the proposed control is capable of optimizing energy consumption by more than 45% compared to a normal lighting operation while maintaining occupants' visual comfort within a suitable illuminance.

关键词： Visualization Energy consumption Lighting Prototypes Process control Optimal control Energy efficiency Real-time systems Internet of Things Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

The role of health belief model in improving construction artisans’ mental health intervention: Nigerian stakeholders' perspective

引用

engineering, Construction and Architectural Management 2025年第13期32卷 174-192页

作者： Andrew Ebekozien Ehimemen Osebuohien Ebekozien Mohamed Ahmed Hafez Ahmed Clinton Ohis Aigbavboa Solomon Oisasoje Ayo-Odifiri Mohamad Shaharudin Samsurijan Samuel Adeniyi Adekunle Opeoluwa Akinradewo Nurudeen Ibrahim Momoh Department of Construction Management and Quantity Surveying University of Johannesburg Johannesburg South Africa Faculty of Engineering and Quantity Surveying INTI International University Nilai Malaysia Department of Quantity Surveying Auchi Polytechnic Auchi Nigeria School of Social Sciences Universiti Sains Malaysia George Town Malaysia Department of Electrical and Electronic Engineering Edo State University Uzairue Nigeria Faculty of Management Shinawatra University Pathum Thani Thailand Department of Architecture Federal University of Technology Owerri Nigeria Department of Civil Engineering College of Engineering and Technology Williams V. S. Tubman University East Harper Liberia Department of Quantity Surveying and Construction Management University of the Free State Bloemfontein South Africa Physical Planning Unit Edo State University Uzairue Nigeria

Purpose In the construction industry, artisans are important, especially in developing countries’ infrastructural development. Thus, the construction artisan’s mental well-being is critical to project productivity and efficiency. There is a perceived increase in construction artisan mental ill health, which threatens the achievement of Sustainable Development Goal 3 (SDG 3) (good health and well-being). The understanding of health belief model (HBM) constructs may improve artisans’ SDG 3. This study explored the factors hindering the adoption of interventions and suggested measures to improve managing Nigerian construction artisans’ mental health using the HBM and, by extension, improve the achievement of Goal 3. Design/methodology/approach The research employed face-to-face interviews to collect data in Abuja and Lagos, Nigeria. This study utilised 38 interviewees who were knowledgeable and accomplished saturation at the 33rd interviewee. The researchers manually analysed the collected data and reported the main results. Findings Findings show that despite the benefits of mental health interventions in the sector, there is low mental health intervention awareness and practice in the Nigerian construction sector. Also, findings reveal hindrances to using HBM as an intervention for construction artisans. Findings identified 31 hindrances and were re-grouped into artisan-related, construction firm and government. Also, attaining Goal 3 concerning artisans’ mental health may be threatened if these encumbrances are not curbed. This study suggested measures to improve Nigerian artisans’ mental health using HBM. Originality/value Recognising the crucial hindrances facing mental health intervention through HBM will be beneficial in promoting measures to improve artisans' mental health in the workplace and achieve Goal 3.

关键词： Construction artisans Health belief model (HBM) Hindrance Mental health Nigeria Sustainable development goal (SDG) 3

来源：评论

学校读者我要写书评

暂无评论

Speaker's Emotions Recognition Module Based on the GoogleLeNet Neural Network

Speaker's Emotions Recognition Module Based on the GoogleLeN...

引用

2022 International Conference on Smart Information Systems and Technologies, SIST 2022

作者： Tereikovskyi, Ihor Tereikovska, Liudmyla Kryvoruchko, Olena Tereikovskyi, Oleh Tyshchenko, Dmytro Franchuk, Tamara National Technical University Of Ukraine Igor Sikorsky Kyiv Polytechnic Institute Dept. Of System Programming And Specialized Computer Systems Kyiv Ukraine Kyiv National University Of Construction And Architecture Dept. Of Information Technology For Design And Applied Mathematics Kyiv Ukraine Kyiv National University Of Trade And Economics Dept. Of Software Engineering And Cyber Security Kyiv Ukraine National Technical University Of Ukraine Igor Sikorsky Kyiv Polytechnic Institute Dept. Of Department Of Computer Engineering Kyiv Ukraine

ISBN: (数字)9781665467902

ISBN: (纸本)9781665467902

The article is devoted to the development of means for recognition of the emotions of the speaker, based on the neural network analysis of fixed fragments of the voice signal. The possibility of improving recognition tools through the use of a convolutional neural network of the GoogLeNet type is shown. The expediency of training the network on the examples of the TESS database is determined. A procedure for representing a voice signal in the form of a square grayscale image has been developed. Based on the use of the specified database, the modification of the GoogLeNet network was carried out. The architecture and software implementation of the recognition module have been developed. With the help of computer experiments, it has been established that after 150 epochs of training on a fairly limited training sample, the modified GoogLeNet makes it possible to achieve an accuracy of recognition of the speaker's emotions of approximately 0.97 on test examples. The obtained accuracy is comparable to the accuracy of the best modern systems of this purpose and confirms the promise of using neural network models like GoogLeNet for emotion recognition based on voice signal analysis. The need for further research aimed at reducing the resource intensity of the neural network model is shown. © 2022 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Waste olivine and silica sands boost geopolymers’ performances: experimental investigation

引用

International Journal of Environmental Studies 2019年第3期76卷 491-506页

作者： Furlani, E. Magnan, M. Mingone, E. Deison, M. Aneggi, E. Andreatta, F. Fedrizzi, L. Maschio, S. Polytechnic Department of Engineering and Architecture University of Udine Udine Italy

The present research deals with the production and characterisation of geopolymers prepared by mixing metakaolin (MK), a commercial sodium silicate solution, a sodium hydroxide solution and two types of industrial by-products: one olivine (OS) and one silica sand (SS) both of them in form of loose powders. Different specimens were prepared by mixing different quantities of OS or SS to the blank geopolymeric matrix. Specimens containing MK, a commercial sodium silicate solution and a sodium hydroxide solution were also prepared as blank composition for comparison. All specimens were characterised by their compressive strength, water absorption, pore size distribution, specific surface area and microstructure. The addition of olivine or silica powders improves the performances of the resulting materials in all the compositions examined, but those containing 50 wt% of added sand (relative to the amount of MK) displayed the best mechanical behaviour. © 2019, © 2019 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Silica

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：