Offshore oil and gas extraction workers are prone to significant occupational fatigue owing to physically and cognitively demanding work in extreme temperatures over extended periods of time.  The goal of this study is to bridge data-driven fatigue assessment with actionable decision support for both workers and supervisors in high-risk industries such as emergency medical services and energy operations.

Related academic outputs:  

Fatigue in safety-critical systems like air traffic control can significantly compromise operator performance and decision-making, making it essential to understand its impact on human–system interaction. This project conducts a mixed-methods usability evaluation of an air traffic control (ATC) system to examine how fatigue affects user performance, attention allocation, and interaction strategies.

Fatigue is a well-recognized challenge among emergency medical services (EMS) providers and has been linked to degraded cognitive and operational performance, which may increase the risk of workplace injuries, medical errors, and other safety-compromising behaviors. This project focuses on modeling real-time operational fatigue among emergency medical services (EMS) providers using multimodal wearable and contextual data collected during real-world 24-hour shifts.

Physiological signals (e.g., heart rate, HRV, skin temperature), behavioral indicators, and contextual features (e.g., workload, time of day, dispatch calls) are integrated to develop machine learning models for fatigue prediction. The models aim to distinguish high- and low-fatigue states and demonstrate the feasibility of wearable-based fatigue monitoring in safety-critical, high-variability environments. 

Related academic outputs: