Title:
Integrating Artificial Intelligence into Workplace Safety Systems: A Convergent Mixed-methods Evaluation of YOLO-Based Hazard Detection in New York State

Authors:
Dr. Robb Shawe, USA

Abstract:

This article evaluates the effectiveness of integrating a YOLO-based computer vision system into workplace hazard detection across construction, manufacturing, and healthcare environments in New York State. Using a convergent mixed-methods design, quantitative data were collected through performance comparisons between YOLO-based detection and manual inspection, including measures of detection accuracy, recall, and time-to-detection. Qualitative data were obtained through semi-structured interviews with employees, supervisors, and safety managers to assess usability, trust, and the feasibility of integration. Results indicate that YOLO-based systems significantly outperform manual inspections in both detection accuracy and response time while enhancing compliance monitoring, particularly for personal protective equipment (PPE). Qualitative findings reveal increased situational awareness, improved safety culture, and strong support for AI-assisted monitoring when implemented with human oversight. Integrated analysis demonstrates that AI-enabled hazard-detection functions are most effective as a socio-technical augmentation rather than a replacement for human judgment. The findings provide empirical evidence supporting the role of artificial intelligence in advancing Safety 4.0 initiatives, improving regulatory compliance, and strengthening proactive safety management systems.

DOI: http://dx.doi.org/10.51505/ijaemr.2026.11314