This is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.
Dev Biswas,
Abstract
The construction field keeps running into problems with quality control, safety protocols, and meeting
deadlines. These troubles often result in big cost overruns and project holdups. Traditional inspection
and site management approaches rely heavily on manual work. They base everything on individual
judgments. Human errors creep in pretty easily. Plus, these methods just give spotty glimpses of the site
as it changes over time. This paper lays out a full framework using artificial intelligence to change how
quality assurance and monitoring happen in construction. It moves away from occasional checkups that
react after the fact. Instead, it focuses on ongoing, forward-looking supervision. The setup pulls in
computer vision tools working on images from different sources. Fixed cameras offer steady views of
the action. Worker-worn sensors capture close-up details. Drones bring in overhead perspectives. Deep
learning models sit at the heart of it all. Convolutional neural networks get trained to spot oddities on
their own. They pick out mismatches with building information models. Safety rule breaks and quality
lapses show up right away. That includes things like correct placement of rebar. Preparing concrete
surfaces needs close inspection too. And making sure personal protective gear gets used properly
matters a lot. Natural language processing helps sift through daily logs. It analyzes incident reports for
signs of bigger risks down the line. Predictive tools draw on past project data. They factor in current
metrics as well. All this helps forecast quality issues ahead of time. Delays in schedules become
predictable. So interventions can kick in early.
Keywords: Artificial intelligence, building information modeling, convolutional neural networks, internet of things, natural language processing, quality control, unmanned aerial vehicles
Dev Biswas. Digital Transformation of Urban Infrastructure by the Help of AI Guardians. Recent Trends in Civil Engineering & Technology. 2026; 16(01):-.
Dev Biswas. Digital Transformation of Urban Infrastructure by the Help of AI Guardians. Recent Trends in Civil Engineering & Technology. 2026; 16(01):-. Available from: https://journals.stmjournals.com/rtcet/article=2026/view=239120
References
1. Haytham Elmousalami, Mina Maxy, Felix Kin Peng Hui , Lu Aye “Automated Sustainable
” Vol. 175, July.2025
2. Hasan, M. M., Kasedullah, M., Ripon, M. B. B., & Khan, M. . .“ -Driven Quality Control in
” .3 J .2025
3. Sara Shomal Zadeh, Sina Aalipour birgani, Meisam Khorshidi, Farhad Kooban, “ Concrete Surface
Crack Detection with Convolutional- L ” .1 J 202
4. Tarun Parmar, “ Intelligence in High-tech Manufacturing: A Review of Applications in
Quality Control O ” .10. 2022
5. Reshma Ahmed Swarna, Muhammad Minoar Hossain, Mst Rokeya Khatun, Mohammad Motiur
Rahman, “ : A Feature Fusion, Crack
Isolation, and Explainable AI- ” .3 .202
6. Harsh Gupta ; Namita Goyal ; Vandana Choudhary, “ Concrete Surface Crack Detection with
Convolutional N N ” .6. .2022
7. Rajagopalan-Sam Rajadurai and Su- K “ -Based Crack Detection on
U L ” .3 .2021
8. Dihao Ai, Guiyuan Jiang, Siew-Kei Lam, Peilan He, Chengwu Li, “ Computer vision framework for
crack detection of civil infrastructure— ” .117 J .2023
Recent Trends in Civil Engineering & Technology
| Volume | 16 |
| 01 | |
| Received | 07/01/2026 |
| Accepted | 31/01/2026 |
| Published | 06/03/2026 |
| Publication Time | 58 Days |
Login
PlumX Metrics