Wearable Safety Systems

Wearable carbon-monoxide detection for construction workers.

Wearable safety devices provide continuous monitoring and sensing to protect human life. Safety-critical pervasive systems are challenging to develop as these systems must be easy to use while providing the user with reliable and timely warnings. Examining the hazards faced by construction workers, many are at risk of carbon monoxide poisoning when working with gasoline powered tools in or around enclosed spaces. To address this problem, we integrated a pulse oximetry sensor into the headband of a typical construction helmet to non-invasively measure blood gas concentrations. Based upon our reliability analysis the integrated sensor can warn the worker of impending carbon monoxide poisoning with 99% reliability. This work was the first to address reliability of wearable pulse oximetry during motion and has been recognized by IEEE Transactions on Automation Science and Engineering as the best paper of 2012. Building on this work, we have developed a warning system for road-side workers and emergency personnel to estimate potential vehicle strikes.

Publications from this work:

Jason Forsyth, Tom Martin, Deborah Young-Corbett, Ed Dorsa, “Feasibility of Intelligent Monitoring of Construction Workers for Carbon Monoxide Poisoning”, IEEE Trans. on Automation Science and Engineering, Volume 9, Issue 3, pp. 505-515, July 2012 (16% acceptance rate) (2012 Best Paper Award) link

J. Forsyth, T.L. Martin, D. Young-Corbett, E. Dorsa; “Feasibility Study of a Wearable Carbon Monoxide Warning System for Construction Workers,” 2011 IEEE International Conference on Pervasive Computing and Communications (PerCom), Seattle, WA, March 21-25 2011, pp.28-36 (11% of 156 accepted as long papers) link

Jason Forsyth, Tom Martin, Darrell Bowman, “Feasibility of GPS-based Warning System for Roadside Workers”, International Conference on Connected Vehicles and Expo, November 3-7, 2014, Vienna, Austria (33% acceptance rate). link

Jason Forsyth
Associate Professor of Engineering

Jason Forsyth is an Associate Professor of Engineering at James Madison University. His major research interests are in wearable/ubiquitous computing and engineering education. His current research interests focus on on-body human activity recognition and interactive machine learning for physical therapy patients and practitioners to increase exercise adherence and clinical evaluation.