From raw to refined: Data preprocessing for construction machine learning (ML), deep learning (DL), and reinforcement learning (RL) models

SZ Golazad, A Mohammadi, A Rashidi… - Automation in …, 2024 - Elsevier
As the use of predictive models in construction rapidly increases, the need for preprocessing
raw construction data has become more critical. This systematic review investigates data …

Monitoring and evaluating the status and behaviour of construction workers using wearable sensing technologies

M Wang, J Chen, J Ma - Automation in Construction, 2024 - Elsevier
Wearable sensing technologies (WSTs) are valuable in monitoring status and behaviour of
construction workers, providing insights into their response under varying conditions and …

Blockchain-based on-site activity management for smart construction process quality traceability

H Wu, H Li, X Luo, S Jiang - IEEE Internet of Things Journal, 2023 - ieeexplore.ieee.org
Onsite construction activities (OCAs) are essential components affecting construction
process quality. Tracing OCAs can control the construction process with high-resolution …

Real-time machine learning-based recognition of human thermal comfort-related activities using inertial measurement unit data

C Fan, W He, L Liao - Energy and Buildings, 2023 - Elsevier
The real-time detection of indoor thermal comfort can bring significant benefits for energy-
efficient controls over the heating, ventilation and air conditioning (HVAC) systems. At …

[HTML][HTML] Deep learning-based automated productivity monitoring for on-site module installation in off-site construction

J Baek, D Kim, B Choi - Developments in the Built Environment, 2024 - Elsevier
Effectively monitoring and analyzing on-site module installation for modular integrated
construction (MiC) is essential to properly coordinating the MiC process. In this study, the …

Identifying Unsafe Behavior of Construction Workers: A Dynamic Approach Combining Skeleton Information and Spatiotemporal Features

H Wu, Y Han, M Zhang, BD Abebe… - Journal of …, 2023 - ascelibrary.org
Vision-based methods for action recognition are valuable for supervising construction
workers' unsafe behaviors. However, current monitoring methods have limitations in …

[HTML][HTML] Automated recognition of construction worker activities using multimodal decision-level fusion

Y Gong, JO Seo, KS Kang, M Shi - Automation in Construction, 2025 - Elsevier
This paper proposes an automated approach for construction worker activity recognition by
integrating video and acceleration data, employing a decision-level fusion method that …

Recognizing sitting activities of excavator operators using multi-sensor data fusion with machine learning and deep learning algorithms

J Li, G Chen, MF Antwi-Afari - Automation in Construction, 2024 - Elsevier
Recognizing excavator operators' sitting activities is crucial for improving their health, safety,
and productivity. Moreover, it provides essential information for comprehending operators' …

Activity sampling in the construction industry: a review and research agenda

TY Lee, F Ahmad, MA Sarijari - International Journal of Productivity …, 2024 - emerald.com
Purpose Activity sampling is a technique to monitor onsite labourers' time utilisation, which
can provide helpful information for the management level to implement suitable labour …

A teacher–student deep learning strategy for extreme low resolution unsafe action recognition in construction projects

M Yang, C Wu, Y Guo, Y He, R Jiang, J Jiang… - Advanced Engineering …, 2024 - Elsevier
A large proportion of construction accidents are caused by workers' unsafe actions. Due to
the complexity of the work environment and excessive demands of safety supervision on …