TY - GEN
T1 - Continuous inference of psychological stress from sensory measurements collected in the natural environment
AU - Plarre, Kurt
AU - Raij, Andrew
AU - Hossain, Syed Monowar
AU - Ali, Amin Ahsan
AU - Nakajima, Motohiro
AU - Al'Absi, Mustafa
AU - Ertin, Emre
AU - Kamarck, Thomas
AU - Kumar, Santosh
AU - Scott, Marcia
AU - Siewiorek, Daniel
AU - Smailagic, Asim
AU - Wittmers, Lorentz E.
PY - 2011
Y1 - 2011
N2 - Repeated exposures to psychological stress can lead to or worsen diseases of slow accumulation such as heart diseases and cancer. The main challenge in addressing the growing epidemic of stress is a lack of robust methods to measure a person's exposure to stress in the natural environment. Periodic self-reports collect only subjective aspects, often miss stress episodes, and impose significant burden on subjects. Physiological sensors provide objective and continuous measures of stress response, but exhibit wide between-person differences and are easily confounded by daily activities (e.g., speaking, physical movements, coffee intake, etc.). In this paper, we propose, train, and test two models for continuous prediction of stress from physiological measurements captured by unobtrusive, wearable sensors. The first model is a physiological classifier that predicts whether changes in physiology represent stress. Since the effect of stress may persist in the mind longer than its acute effect on physiology, we propose a perceived stress model to predict perception of stress. It uses the output of the physiological classifier to model the accumulation and gradual decay of stress in the mind. To account for wide between-person differences, both models self-calibrate to each subject. Both models were trained using data collected from 21 subjects in a lab study, where they were exposed to cognitive, physical, and social stressors representative of that experienced in the natural environment. Our physiological classifier achieves 90% accuracy and our perceived stress model achieves a median correlation of 0.72 with self-reported rating. We also evaluate the perceived stress model on data collected from 17 participants in a two-day field study, and find that the average rating of stress obtained from our model has a correlation of 0.71 with that obtained from periodic self-reports.
AB - Repeated exposures to psychological stress can lead to or worsen diseases of slow accumulation such as heart diseases and cancer. The main challenge in addressing the growing epidemic of stress is a lack of robust methods to measure a person's exposure to stress in the natural environment. Periodic self-reports collect only subjective aspects, often miss stress episodes, and impose significant burden on subjects. Physiological sensors provide objective and continuous measures of stress response, but exhibit wide between-person differences and are easily confounded by daily activities (e.g., speaking, physical movements, coffee intake, etc.). In this paper, we propose, train, and test two models for continuous prediction of stress from physiological measurements captured by unobtrusive, wearable sensors. The first model is a physiological classifier that predicts whether changes in physiology represent stress. Since the effect of stress may persist in the mind longer than its acute effect on physiology, we propose a perceived stress model to predict perception of stress. It uses the output of the physiological classifier to model the accumulation and gradual decay of stress in the mind. To account for wide between-person differences, both models self-calibrate to each subject. Both models were trained using data collected from 21 subjects in a lab study, where they were exposed to cognitive, physical, and social stressors representative of that experienced in the natural environment. Our physiological classifier achieves 90% accuracy and our perceived stress model achieves a median correlation of 0.72 with self-reported rating. We also evaluate the perceived stress model on data collected from 17 participants in a two-day field study, and find that the average rating of stress obtained from our model has a correlation of 0.71 with that obtained from periodic self-reports.
KW - Wearable sensors
KW - physiological monitoring
KW - stress inference
UR - http://www.scopus.com/inward/record.url?scp=79959287100&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=79959287100&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:79959287100
SN - 9781612848549
T3 - Proceedings of the 10th ACM/IEEE International Conference on Information Processing in Sensor Networks, IPSN'11
SP - 97
EP - 108
BT - Proceedings of the 10th ACM/IEEE International Conference on Information Processing in Sensor Networks, IPSN'11
T2 - 10th ACM/IEEE International Conference on Information Processing in Sensor Networks, IPSN'11
Y2 - 12 April 2011 through 14 April 2011
ER -