In Review
Kristyna Kvapilova, Souravik Dutta, Palwasha Afsar, Yuxiang Chen, Farook Hamzeh, Carlos Cruz-Noguez, Rafiq Ahmad
Advanced Engineering Informatics
Advanced Engineering Informatics
Cite
Cite
APA
Click to copy
Kvapilova, K., Dutta, S., Afsar, P., Chen, Y., Hamzeh, F., Cruz-Noguez, C., & Ahmad, R. Comprehensive Review of AI Techniques and Sensing Technologies for Safety in Masonry Construction. Advanced Engineering Informatics.
Chicago/Turabian
Click to copy
Kvapilova, Kristyna, Souravik Dutta, Palwasha Afsar, Yuxiang Chen, Farook Hamzeh, Carlos Cruz-Noguez, and Rafiq Ahmad. “Comprehensive Review of AI Techniques and Sensing Technologies for Safety in Masonry Construction.” Advanced Engineering Informatics, n.d.
MLA
Click to copy
Kvapilova, Kristyna, et al. “Comprehensive Review of AI Techniques and Sensing Technologies for Safety in Masonry Construction.” Advanced Engineering Informatics.
BibTeX Click to copy
@unpublished{kristyna-a,
title = {Comprehensive Review of AI Techniques and Sensing Technologies for Safety in Masonry Construction},
journal = {Advanced Engineering Informatics},
author = {Kvapilova, Kristyna and Dutta, Souravik and Afsar, Palwasha and Chen, Yuxiang and Hamzeh, Farook and Cruz-Noguez, Carlos and Ahmad, Rafiq}
}
Abstract
The masonry industry remains one of the most labor-intensive and accident-prone sectors of construction, where heavy manual work and complex site conditions continue to drive high injury rates despite established safety measures. This review investigates the current state of Artificial Intelligence (AI) techniques and sensing technologies for improving masonry safety within the emerging Industry 5.0 framework. A three-stage review methodology was adopted, beginning with a literature search and screening of the Scopus database using the PRISMA protocol that identified 128 relevant articles. Next, a systematic review classified the selected studies into four categories – safety application areas, dataset development, AI methods, and sensing technologies – followed by comparative analysis of their reported performance, advantages, and limitations. Finally, a critical review synthesized cross-cutting challenges and future research opportunities. The findings show that Computer Vision (CV) and Natural Language Processing (NLP) enable real-time hazard detection, accident classification, and predictive analytics, while wearable sensors and Unmanned Aerial Vehicles (UAVs) provide complementary monitoring of worker physiology and site conditions, often achieving accuracies above 80-90% in controlled experiments. Nevertheless, barriers such as limited masonry-specific datasets, environmental sensitivity of vision systems, sensing errors, high hardware costs, and privacy concerns constrain large-scale implementation. The review concludes that advancing masonry safety will require robust standardized datasets, algorithmic resilience to field conditions, and integrated multi-modal platforms that combine AI and sensing technologies within human-centric Industry 5.0 frameworks. Competent adoption of some of the emerging technologies such as collaborative robotics and Virtual Reality (VR) are also suggested as possible solutions for masonry safety. These insights provide a roadmap for researchers, practitioners, and policymakers seeking scalable, ethical, and proactive safety solutions.
Keywords
Masonry
Safety
Systematic review
AIX
Computer vision
Sensors
Safety
Systematic review
AIX
Computer vision
Sensors