Optimize the Work Zone Safety with Spatial Information Technology and Eye Tracker
archive: archived pipeline: cataloged verified
Get this paper ↗ (full text — opens at the source; we link to it, we don't host it)
Summary
This study addresses the critical need to improve work zone safety in the construction industry, which suffers from high rates of injury and death. The research investigates how eye-tracking technology can optimize hazard identification by examining the factors influencing workers’ Hazard Identification Rate (HIR) and the efficacy of safety training. The project was motivated by the lack of empirical evidence regarding how standard safety training impacts workers’ visual search strategies and hazard recognition performance. The methodology comprised two main components. First, a systematic literature review analyzed 81 publications from Web of Science, Scopus, and the ASCE library to establish the background of eye-tracking applications in construction safety. This bibliometric analysis covered time-series trends, geographic distribution, publication venues, and author correlations, while summarizing experimental procedures and metrics. Second, an empirical experiment was conducted to test three specific research aims: identifying factors influencing HIR, verifying the efficiency of immediate safety training, and illustrating the effect of training on visual search strategies across different participant groups. The experiment utilized eye-tracking devices to record visual data, analyzing metrics such as fixation count, duration, and saccadic amplitude. Participants were categorized based on characteristics such as field of study, possession of safety training certificates, and related work experience. The findings reveal that a worker’s field of study significantly influences their Hazard Identification Rate, whereas holding safety training certificates or possessing related work experience does not. Furthermore, the study demonstrated that brief safety training affects high-HIR and low-HIR groups differently. Specifically, the training altered visual scan paths and eye-tracking metrics in distinct ways for these two groups, indicating that training efficacy is not uniform across all workers. The literature review component confirmed that eye-tracking technology is an emerging research topic, with publication trends increasing sharply after 2016, led primarily by researchers in the United States and China. The significance of this research lies in its recommendation for organizations to adopt varied safety training methods tailored to different worker profiles. Since standard training does not uniformly improve hazard recognition, understanding the differential effects on visual search strategies allows for more targeted interventions. The study highlights the value of eye-tracking technology in quantifying hazard recognition abilities and providing objective data to guide construction safety improvements, moving beyond subjective assessments to data-driven optimization of worker safety protocols.
Key finding
Field of study significantly influences workers' hazard identification rates, while safety training certificates and work experience do not, and immediate safety training impacts high- and low-identification rate groups differently.
Methodology
lab_experiment
Provenance
The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed. Discovered via bulk_ingest_rosap on 2026-05-23 (6 acquisition events logged).
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | success | rosap | — | — | 2 | 2026-05-23 |
| archive | success | — | — | — | 1 | 2026-05-23 |
| extract | success | cached | — | — | 2 | 2026-06-10 |
| clean | success | — | — | — | 1 | 2026-06-01 |
| chunk | success | — | — | — | 1 | 2026-06-01 |
| embed | success | — | — | — | 1 | 2026-06-02 |
| enrich | success | — | — | — | 1 | 2026-05-23 |
| promote | success | — | — | — | 1 | 2026-05-23 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 3 | 2026-06-10 |
| tag | success | vector_similarity | — | — | 19 | 2026-06-11 |
| verify | success | — | — | — | 2 | 2026-06-10 |
Summary generated by qwen3.6-27b-prismaquant on 2026-06-10; verification: verified.
Topics
Ranked by relevance to this paper. Hover a topic for its definition.
- hazard perception training
- hazard perception
- looked but failed to see
- gaze based attention detection
- eye movements scanning
Information type
What kind of knowledge this paper contributes, grouped by family — independent of topic (what it is about) and method (how it was studied).
- Methodological Resource: tool software