Date of Award
12-2025
Document Type
Dissertation
Degree Name
Doctor of Philosophy (PhD)
Department
Civil Engineering
Committee Chair/Advisor
Tuyen Le
Committee Member
Kalyan R. Piratla
Committee Member
Kapil Chalil Madathil
Committee Member
Chao Fan
Abstract
This research develops data-driven and AI-enhanced approaches to improve worker safety in highway construction environments. The study integrates advanced analytics and auditory signal enhancement to identify high-risk worker behaviors and improve real-time safety warnings. The work consists of three core studies. The first study applies Sequential Pattern Mining and Social Network Analysis to more than 1,000 construction accident reports to identify high-risk worker actions and their hidden sequential relationships with accident types and consequences. These insights reveal sector-specific risk patterns, supporting the creation of targeted, data-informed safety interventions. The second study introduces an AI-based auditory enhancement model built on a Conformer-based Metric Generative Adversarial Network (CMGAN). Designed for noisy construction environments, the model enhances the clarity of safety-critical signals, including backup alarms and intrusion alerts. By combining local acoustic feature extraction, long-range temporal modeling, and adversarial training with perceptual loss functions, the model suppresses background noise while preserving essential warning cues, even under extreme noise conditions. The third study develops a real-time auditory enhancement prototype using the lightweight DeepFilterNet algorithm. Implemented on a low-cost Raspberry Pi 5 and designed for integration into portable hearing protection devices, the system delivers low-latency enhancement of safety-critical signals. Field tests and listener surveys demonstrate improved audibility and preserved signal characteristics, confirming the feasibility of real-time deployment in active highway construction sites. Overall, this research enhances the understanding of high-risk worker behaviors and demonstrates the practical application of AI-driven auditory safety technologies with the potential to improve overall safety practices in the highway construction industry.
Recommended Citation
Nguyen, Thinh, "Accident Data Analytics and AI-based Auditory Enhancement for Highway Construction Safety" (2025). All Dissertations. 4124.
https://open.clemson.edu/all_dissertations/4124
Author ORCID Identifier
https://orcid.org/0000-0002-1846-0764