Human risky behaviour recognition during ladder climbing based on multi-modal feature fusion and adaptive graph convolutional network

The construction industry has the highest number of fatal accidents compared to other industries. However, manual safety compliance monitoring is complex and difficult for safety engineers, and more automated solutions need to be found. The main research objective was to review the state of the art of real-time monitoring technologies used to assess the risk of falling from height in the construction sector. A systematic review is proposed in order to summarise the technologies used for real-time monitoring in the construction sector, following the PRISMA methodology. Only studies that assessed the risk of falling in real time were selected. From an initial set of 1289 articles, 40 were classified as strictly relevant to addressing the research questions. Various technologies that use artificial intelligence have been designed to monitor workers in real time and to send alerts to workers at any time in the event of a risk situation, thus preventing accidents. This study showed that new technologies are being introduced to predict the risk of a fall in real time, changing the approach from reactive to proactive and allowing this monitoring to improve workplace surveillance and safety. Further research is needed to develop effective systems that are easy for people to use without compromising productivity.

show abstract

Machine learning algorithms for safer construction sites: Critical review

Junjia,

Alias,

Haron

et al. 2024

Build. Eng.

View full text Add to dashboard Cite

Machine learning, a key thruster of Construction 4.0, has seen exponential publication growth in the last ten years. Many studies have identified ML as the future, but few have critically examined the applications and limitations of various algorithms in construction management. Therefore, this article comprehensively reviewed the top 100 articles from 2018 to 2023 about ML algorithms applied in construction risk management, provided their strengths and limitations, and identified areas for improvement. The study found that integrating various data sources, including historical project data, environmental factors, and stakeholder information, has become a common trend in construction risk. However, the challenges associated with the need for extensive and high-quality datasets, models’ interpretability, and construction projects’ dynamic nature pose significant barriers. The recommendations presented in this paper can facilitate interdisciplinary collaboration between traditional construction and machine learning, thereby enhancing the development of specialized algorithms for real-world projects.

show abstract

Human risky behaviour recognition during ladder climbing based on multi-modal feature fusion and adaptive graph convolutional network

Cited by 3 publications

References 39 publications

SlowFast Adaptive Graph Convolutional Network with Multi-Modal Feature Aggregation for Skeleton-Based Action Recognition: Case Study of Human Ladder Climbing

SlowFast Adaptive Graph Convolutional Network with Multi-Modal Feature Aggregation for Skeleton-Based Action Recognition: Case Study of Human Ladder Climbing

An Evaluation of the Technologies Used for the Real-Time Monitoring of the Risk of Falling from Height in Construction—Systematic Review

Machine learning algorithms for safer construction sites: Critical review

Contact Info

Product

Resources

About