Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
3.4
3.1
Journals
Buildings
Special Issues
Deep Learning Models in Buildings
share announcement

Deep Learning Models in Buildings

A special issue of Buildings (ISSN 2075-5309). This special issue belongs to the section "Construction Management, and Computers & Digitization".

Deadline for manuscript submissions: 31 December 2024 | Viewed by 1750

Special Issue Editors

Dr. Tae Wan Kim

E-Mail
Guest Editor
Division of Architecture and Urban Design, Incheon National University, Incheon 22012, Republic of Korea
Interests: automation in construction; offsite construction; decision support systems; digital twin and simulation
Special Issues, Collections and Topics in MDPI journals
Dr. Jun Young Jang

E-Mail
Guest Editor
Division of Architecture and Urban Design, Incheon National University, Incheon 22012, Republic of Korea
Interests: automation in construction; offsite construction; decision support systems; computer vision; knowledge graph

Special Issue Information

Dear Colleagues,

This Special Issue explores the cutting-edge integration of deep learning technologies within the construction management and building sectors, emphasizing the transformative impact these technologies have on enhancing efficiency, sustainability and innovation in building design, construction and maintenance. This issue delves into how deep learning models, as a subset of artificial intelligence (AI), are revolutionizing the approach to analyzing and managing vast amounts of data within the production and management of buildings. By leveraging complex algorithms, these models provide unprecedented insights into optimizing building performance, energy usage and material selection, thereby supporting the construction industry's shift toward more sustainable and smart building solutions.

The contributions within this Special Issue highlight the application of deep learning in various stages of the building lifecycle, from predictive maintenance and automated defect detection to energy consumption optimization and enhanced design decision-making. This focus on deep learning models showcases their potential to drive advancements in construction management practices, promoting not only environmental sustainability, but also operational efficiency and cost-effectiveness in the face of evolving industry challenges.

Topics include, but are not limited to:

  • Deep learning applications and strategies in energy-efficient building design;
  • The role of AI in enhancing building sustainability;
  • Predictive analytics for the maintenance and operations of smart buildings;
  • Deep learning algorithms for automated defect detection in construction;
  • Optimization of construction material usage through machine learning models;
  • The impact of AI on the lifecycle assessment of building projects;
  • Integration knowledge graph and AI for building production and management;
  • Advanced data analytics for improving construction supply chain sustainability;
  • Techniques for processing and analyzing large-scale construction data using AI;
  • Integration of IoT and deep learning for intelligent building systems;
  • Case studies on the use of deep learning in construction project management;
  • Ethical and societal considerations of AI in the construction industry.

Dr. Tae Wan Kim
Dr. Jun Young Jang
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Buildings is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • smart building technologies
  • building performance optimization
  • predictive maintenance in buildings
  • automated defect detection
  • construction data analysis
  • energy consumption optimization
  • AI-driven design decision-making
  • deep learning in construction

Published Papers (3 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

32 pages, 4331 KiB  
Article
Hybrid Data Augmentation for Enhanced Crack Detection in Building Construction
by Seung-Mo Choi, Hee-Sung Cha and Shaohua Jiang
Buildings 2024, 14(7), 1929; https://doi.org/10.3390/buildings14071929 - 25 Jun 2024
Viewed by 187
Abstract
Quality management in construction projects necessitates early defect detection, traditionally conducted manually by supervisors, resulting in inefficiencies and human errors. Addressing this challenge, research has delved into automating defect detection using computer vision technology, yet progress has been impeded by data limitations. Numerous [...] Read more.
Quality management in construction projects necessitates early defect detection, traditionally conducted manually by supervisors, resulting in inefficiencies and human errors. Addressing this challenge, research has delved into automating defect detection using computer vision technology, yet progress has been impeded by data limitations. Numerous studies have explored generating virtual images to tackle this issue. However, these endeavors have fallen short in providing image data adaptable to detecting defects amidst evolving on-site construction conditions. This study aims to surmount this obstacle by constructing a hybrid dataset that amalgamates virtual image data with real-world data, thereby enhancing the accuracy of deep learning models. Virtual images and mask images for the model are concurrently generated through a 3D virtual environment and automatic rendering algorithm. Virtual image data are built by employing a developed annotation system to automatically annotate through mask images. This method improved efficiency by automating the process from virtual image creation to annotation. Furthermore, this research has employed a hierarchical classification system in generating virtual image datasets to reflect the different types of defects that can occur. Experimental findings demonstrate that the hybrid datasets enhanced the F1-Score by 4.4%, from 0.4154 to 0.4329, compared to virtual images alone, and by 10%, from 0.4499 to 0.4990, compared to sole reliance on real image augmentation, underscoring its superiority. This investigation contributes to unmanned, automated quality inspection aligning with smart construction management, potentially bolstering productivity in the construction industry. Full article
(This article belongs to the Special Issue Deep Learning Models in Buildings)
24 pages, 2408 KiB  
Article
DfMA Integrated Assessment Model for Selecting Optimal Design Alternatives in OSC Projects
by Seoyoung Jung, Seulki Lee and Jungho Yu
Buildings 2024, 14(6), 1727; https://doi.org/10.3390/buildings14061727 - 8 Jun 2024
Viewed by 531
Abstract
To select the optimal design alternative in off-site construction (OSC) projects, the building industry has turned to design for manufacturing and assembly (DfMA). However, most DfMA developments in the OSC field until now have been on improving the production process in OSC projects [...] Read more.
To select the optimal design alternative in off-site construction (OSC) projects, the building industry has turned to design for manufacturing and assembly (DfMA). However, most DfMA developments in the OSC field until now have been on improving the production process in OSC projects and guideline strategies on how to apply them. The application of DfMA guidelines only provides background knowledge to designers on how to design. However, it cannot inspect whether the DfMA concept is fully reflected in a design draft to examine the suitability to the OSC production environment, and it cannot determine the optimal alternative from among multiple design alternatives. Thus, this study developed an integrated assessment model of OSC-DfMA consisting of the OSC-DfMA production suitability assessment model and the OSC-DfMA production efficiency assessment model to support decision-making for selecting the optimal design alternative of an OSC project. In this study, the scope of the main research was limited to precast concrete (PC)-based OSC projects. Firstly, we developed an OSC-DfMA production suitability assessment model to review whether design drafts are suitable in the OSC production environment by applying checklist and matrix techniques. Secondly, we developed an OSC-DfMA production efficiency assessment model to select an optimal alternative in terms of production efficiency among multiple design drafts. Thirdly, we conducted a case study to validate the usefulness of the OSC-DfMA assessment model developed in this study. Finally, we discuss the possibility of using AI technology to consider the facility capacity and resource constraints during the production of OSC building components. The study results are of practical value in providing the basis for expanding the applicability of DfMA by proposing a DfMA assessment model suitable for OSC contexts. Full article
(This article belongs to the Special Issue Deep Learning Models in Buildings)
►▼ Show Figures

Figure 1

15 pages, 3105 KiB  
Article
Comparison of OSC (Off-Site Construction) Level Measurement Methods
by Chulwoo Im, Jung-In Kim, Inhan Kim and Jungho Yu
Buildings 2024, 14(5), 1281; https://doi.org/10.3390/buildings14051281 - 1 May 2024
Viewed by 663
Abstract
Studies have shown that the implementation of OSC (off-site construction) is beneficial. However, most studies have relied on simulated project data to forecast the potential advantages of OSC, often using surveys or expert consultations as their primary research methods. Others have based their [...] Read more.
Studies have shown that the implementation of OSC (off-site construction) is beneficial. However, most studies have relied on simulated project data to forecast the potential advantages of OSC, often using surveys or expert consultations as their primary research methods. Others have based their analyses on a specific sample size, focusing on cost savings and reduced construction time. Such approaches inherently possess limitations. In this study, we define “OSC level measurement” as the comprehensive process of quantifying the application of OSC elements throughout the project lifecycle. Numerous studies have proposed methods for OSC level measurements. However, they vary in their applicability to different facility types and project phases and employ country-specific quantification items and methods. These variations complicate the comparison or integration of OSC measurement methods on an international scale. The comprehensiveness of the representations in the existing industry foundation classes (IFCs), which is required to carry out automated OSC level measurement, is not yet investigated. This study aimed to systematically compare and analyze various methods for measuring OSC levels in construction projects. We intend to provide researchers and professionals with the necessary characteristics and requirements to develop standardized OSC level measurement methods in the future. The key takeaways emphasize the need for establishing the necessary standardization of the list of OSC elements, creating a framework for standardized quantification items using IFC elements based on BIM data to measure the extent of OSC elements’ application, and unifying the quantification methods for assessing the proportion of OSC elements. Ultimately, this standardization will pave the way for more informed decision making, innovation, and the implementation of sustainable solutions in the construction industry. Full article
(This article belongs to the Special Issue Deep Learning Models in Buildings)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-3
Back to TopTop