TY - GEN
T1 - Personalized wellbeing prediction using behavioral, physiological and weather data
AU - Yu, Han
AU - Klerman, Elizabeth B.
AU - Picard, Rosalind W.
AU - Sano, Akane
N1 - Funding Information:
This work was supported by NSF(#1840167), NIH (R01GM105018, K24-HL105664), Samsung Electronics, and NEC Corporation. We thank our SNAPSHOT study collaborators and study participants. 1Department of Electrical and Computer Engineering, Rice University. hy29@rice.edu 2Division of Sleep and Circadian Disorders, Brigham and Women’s Hospital, Harvard Medical School. 3Media Lab, Massachusetts Institute of Technology.
Publisher Copyright:
© 2019 IEEE.
PY - 2019/5
Y1 - 2019/5
N2 - We built and compared several machine learning models to predict future self-reported wellbeing labels (of mood, health, and stress) for next day and for up to 7 days in the future, using multi-modal data. The data are from surveys, wearables, mobile phones and weather information collected in a study from college students, each providing daily data for 30 or 90 days. We compared the performance of multiple models, including personalized multi-Task models and deep learning models. The best personalized multi-Task linear model showed mean absolute errors of 12.8, 11.9, and 13.7 on a continuous-100 pt scale for estimating next days mood, health, and stress value, while the best multi-Task neural network model, applied to 3-way high/med/low classification of the wellbeing values showed F1 scores of 0.71, 0.74, and 0.66 on mood, health, and stress metrics, respectively. We found that features related to weather, and morning academic activities are strongly associated with wellbeing labels. We further found greater prediction accuracy among participants with the least fluctuations in their wellbeing labels.
AB - We built and compared several machine learning models to predict future self-reported wellbeing labels (of mood, health, and stress) for next day and for up to 7 days in the future, using multi-modal data. The data are from surveys, wearables, mobile phones and weather information collected in a study from college students, each providing daily data for 30 or 90 days. We compared the performance of multiple models, including personalized multi-Task models and deep learning models. The best personalized multi-Task linear model showed mean absolute errors of 12.8, 11.9, and 13.7 on a continuous-100 pt scale for estimating next days mood, health, and stress value, while the best multi-Task neural network model, applied to 3-way high/med/low classification of the wellbeing values showed F1 scores of 0.71, 0.74, and 0.66 on mood, health, and stress metrics, respectively. We found that features related to weather, and morning academic activities are strongly associated with wellbeing labels. We further found greater prediction accuracy among participants with the least fluctuations in their wellbeing labels.
KW - 3-class classification
KW - CNN
KW - Health
KW - LSTM
KW - Mobile phone
KW - Mood
KW - Multi-Task Learning
KW - Personalized models
KW - Regression
KW - Stress
KW - Wearables
KW - Wellbeing Prediction
UR - http://www.scopus.com/inward/record.url?scp=85072888123&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85072888123&partnerID=8YFLogxK
U2 - 10.1109/BHI.2019.8834456
DO - 10.1109/BHI.2019.8834456
M3 - Conference contribution
AN - SCOPUS:85072888123
T3 - 2019 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2019 - Proceedings
BT - 2019 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2019 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2019 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2019
Y2 - 19 May 2019 through 22 May 2019
ER -