TY - GEN
T1 - Detecting Granular Eating Behaviors from Body-worn Audio and Motion Sensors
AU - Mirtchouk, Mark
AU - Kleinberg, Samantha
N1 - Publisher Copyright:
© 2021 IEEE
PY - 2021
Y1 - 2021
N2 - Wearable sensor technology has made it possible to gain insight into dietary activity, learning not only when people are eating, but identifying fine-grained behaviors such as chews per minute, and causes of food choices. This may enable interventions to maintain health and assist individuals with chronic diseases such as diabetes (e.g. by providing insulin dosing assistance). However, existing work on dietary monitoring has focused on identifying meal times, rather than fine grained behavior such as chewing. A key barrier is the difficulty of obtaining granular ground truth. In free-living environments it is difficult to obtain the high-quality video needed, and annotating large datasets is labor intensive and does not scale well. To address this, we introduce a new multi-stage initialization approach for Stochastic Variational Deep Kernel Learning (SVDKL) that enables learning from data with a mix of coarse labels (meal times) and granular ones (chews, intakes). Our approach outperforms the state of the art on both free-living and laboratory datasets, with 84% recall and 67% precision for detecting chews compared to prior results of 73% precision and 34% recall on the same data. Ultimately, our work may enable more types of human activity recognition from real-world environments at a lower cost.
AB - Wearable sensor technology has made it possible to gain insight into dietary activity, learning not only when people are eating, but identifying fine-grained behaviors such as chews per minute, and causes of food choices. This may enable interventions to maintain health and assist individuals with chronic diseases such as diabetes (e.g. by providing insulin dosing assistance). However, existing work on dietary monitoring has focused on identifying meal times, rather than fine grained behavior such as chewing. A key barrier is the difficulty of obtaining granular ground truth. In free-living environments it is difficult to obtain the high-quality video needed, and annotating large datasets is labor intensive and does not scale well. To address this, we introduce a new multi-stage initialization approach for Stochastic Variational Deep Kernel Learning (SVDKL) that enables learning from data with a mix of coarse labels (meal times) and granular ones (chews, intakes). Our approach outperforms the state of the art on both free-living and laboratory datasets, with 84% recall and 67% precision for detecting chews compared to prior results of 73% precision and 34% recall on the same data. Ultimately, our work may enable more types of human activity recognition from real-world environments at a lower cost.
UR - http://www.scopus.com/inward/record.url?scp=85125471839&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85125471839&partnerID=8YFLogxK
U2 - 10.1109/BHI50953.2021.9508519
DO - 10.1109/BHI50953.2021.9508519
M3 - Conference contribution
AN - SCOPUS:85125471839
T3 - BHI 2021 - 2021 IEEE EMBS International Conference on Biomedical and Health Informatics, Proceedings
BT - BHI 2021 - 2021 IEEE EMBS International Conference on Biomedical and Health Informatics, Proceedings
T2 - 2021 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2021
Y2 - 27 July 2021 through 30 July 2021
ER -