TY - GEN
T1 - Continuous alertness assessments
T2 - 2019 CHI Conference on Human Factors in Computing Systems, CHI 2019
AU - Tag, Benjamin
AU - Vargo, Andrew W.
AU - Gupta, Aman
AU - Chernyshov, George
AU - Kunze, Kai
AU - Dingler, Tilman
N1 - Funding Information:
We would like to thank all participants of our study. We further would like to thank Shoya Ishimaru from the University of Kaiserslautern and DFKI Kaiserslautern for his support and advice on eye blink detection. This research was supported by JST (Sakigake/Presto), Grant No: JP-MJPR16D4.
Publisher Copyright:
© 2019 Copyright held by the owner/author(s).
PY - 2019/5/2
Y1 - 2019/5/2
N2 - As the day progresses, cognitive functions are subject to fluctuations. While the circadian process results in diurnal peaks and drops, the homeostatic process manifests itself in a steady decline of alertness across the day. Awareness of these changes allows the design of proactive recommender and warning systems, which encourage demanding tasks during periods of high alertness and flag accident-prone activities in low alertness states. In contrast to conventional alertness assessments, which are often limited to lab conditions, bulky hardware, or interruptive self-assessments, we base our approach on eye blink frequency data known to directly relate to fatigue levels. Using electrooculography sensors integrated into regular glasses’ frames, we recorded the eye movements of 16 participants over the course of two weeks in-the-wild and built a robust model of diurnal alertness changes. Our proposed method allows for unobtrusive and continuous monitoring of alertness levels throughout the day.
AB - As the day progresses, cognitive functions are subject to fluctuations. While the circadian process results in diurnal peaks and drops, the homeostatic process manifests itself in a steady decline of alertness across the day. Awareness of these changes allows the design of proactive recommender and warning systems, which encourage demanding tasks during periods of high alertness and flag accident-prone activities in low alertness states. In contrast to conventional alertness assessments, which are often limited to lab conditions, bulky hardware, or interruptive self-assessments, we base our approach on eye blink frequency data known to directly relate to fatigue levels. Using electrooculography sensors integrated into regular glasses’ frames, we recorded the eye movements of 16 participants over the course of two weeks in-the-wild and built a robust model of diurnal alertness changes. Our proposed method allows for unobtrusive and continuous monitoring of alertness levels throughout the day.
KW - Circadian computing
KW - Cognition-aware systems
KW - Electrooculography
KW - Eye blink
KW - Fatigue
UR - http://www.scopus.com/inward/record.url?scp=85067596200&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85067596200&partnerID=8YFLogxK
U2 - 10.1145/3290605.3300694
DO - 10.1145/3290605.3300694
M3 - Conference contribution
AN - SCOPUS:85067596200
T3 - Conference on Human Factors in Computing Systems - Proceedings
BT - CHI 2019 - Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems
PB - Association for Computing Machinery
Y2 - 4 May 2019 through 9 May 2019
ER -