Occupational stress is defined as the harmful physical and mental responses that happen when job requirements are greater than a worker's capacity. Construction is one of the most stressful occupations because it involves physiologically and psychologically demanding tasks performed in a hazardous environment. Various survey instruments for measuring workers′ perceived mental and physical stress have been used, e.g., the perceived stress and fatigue severity scales. These methods can document subjects′ overall stress. However, they have several key limitations. They are subjective, invasive, and cannot be used for continuous stress monitoring. To address these issues, my doctoral research applies several signal processing and machine learning techniques to propose a comprehensive and efficient stress measurement framework by acquiring high-quality physiological signals from wearable biosensors at job sites. Results yielded a high of 80.13 % mental stress and 90.00% physical stress recognition accuracy. These results are promising given that stress recognition with sensitive and wired physiological devices in the clinical domain has, at best, a similar level of accuracy. The proposed physiological signal-based stress recognition framework is expected to help us better understand workplace stressors and to improve worker productivity, safety, and well-being through early detection and mitigation of factors that cause stress.

Houtan is a Ph.D. Candidate in the Tishman Construction Management Program, working under the supervision of Prof. SangHyun Lee. Houtan received his bachelor′s degree in civil engineering from Tehran Polytechnic University in 2012.