Feature weights in contractor safety performance assessment: Comparative study of expert-driven and analytics-based approaches

Automation in Construction, Journal Year: 2025, Volume and Issue: 174, P. 106142 - 106142

Published: March 31, 2025

Language: Английский

---

Leveraging convolutional neural networks for efficient classification of heavy construction equipment

Asian Journal of Civil Engineering, Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 5, 2024

Language: Английский

---

Time of Flight Distance Sensor–Based Construction Equipment Activity Detection Method

Applied Sciences, Journal Year: 2024, Volume and Issue: 14(7), P. 2859 - 2859

Published: March 28, 2024

In this study, we delve into a novel approach by employing sensor-based pattern recognition model to address the automation of construction equipment activity analysis. The integrates time flight (ToF) sensors with deep convolutional neural networks (DCNNs) accurately classify operational activities equipment, focusing on piston movements. research utilized one-twelfth-scale excavator model, processing displacement ratios its pistons unified dataset for Methodologically, study outlines setup sensor modules and their integration controller, emphasizing precision in capturing dynamics. DCNN characterized four-layered blocks, was meticulously tuned within MATLAB environment, demonstrating model’s learning capabilities through hyperparameter optimization. An analysis 2070 samples representing six distinct yielded an impressive average 95.51% recall 95.31%, overall accuracy 95.19%. When compared against other vision-based accelerometer-based methods, proposed showcases enhanced performance reliability under controlled experimental conditions. This substantiates potential practical application real-world scenarios, marking significant advancement field monitoring.

Language: Английский

---

Privilege-guided knowledge distillation for edge deployment in excavator activity recognition

Automation in Construction, Journal Year: 2024, Volume and Issue: 166, P. 105688 - 105688

Published: Aug. 9, 2024

Language: Английский

---