TY - GEN
T1 - Passive Sensor Data Based Future Mood, Health, and Stress Prediction
T2 - 42nd Annual International Conferences of the IEEE Engineering in Medicine and Biology Society, EMBC 2020
AU - Yu, Han
AU - Sano, Akane
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/7
Y1 - 2020/7
N2 - Predicting one's mood, health, and stress in the future may provide useful feedback before wellbeing related problems become severe. Previously, researchers developed participant-dependent wellbeing prediction models using mobile and wearable sensors, where the models were trained and tested with the same group of people. However, in real-world applications, it is essential to consider the adaptability of the developed models to new users for predicting new users' wellbeing immediately and accurately. In this paper, we built wellbeing prediction models using passively sensed data from wearable sensors, mobile phones, and weather API, and deep learning methods, and evaluated the models with the data from new users. We compared deep long short-term memory (LSTM) network and the combination of convolutional neural network (CNN) and the LSTM model. We found that our deep LSTM model provided performances, in mean absolute error (MAE), as 15.7, 15.6, and 16.8 out of 100 in predicting self-reported mood, health, and stress respectively for new users. Furthermore, we applied a fine-tuning transfer learning method based on our deep LSTM model, which provided new participants with more accurate predictions, especially when the volume of new participants' data was limited. The transfer learning model improved the MAE performances to 13.5, 13.2, and 14.4 out of 100 for mood, health, and stress, respectively.
AB - Predicting one's mood, health, and stress in the future may provide useful feedback before wellbeing related problems become severe. Previously, researchers developed participant-dependent wellbeing prediction models using mobile and wearable sensors, where the models were trained and tested with the same group of people. However, in real-world applications, it is essential to consider the adaptability of the developed models to new users for predicting new users' wellbeing immediately and accurately. In this paper, we built wellbeing prediction models using passively sensed data from wearable sensors, mobile phones, and weather API, and deep learning methods, and evaluated the models with the data from new users. We compared deep long short-term memory (LSTM) network and the combination of convolutional neural network (CNN) and the LSTM model. We found that our deep LSTM model provided performances, in mean absolute error (MAE), as 15.7, 15.6, and 16.8 out of 100 in predicting self-reported mood, health, and stress respectively for new users. Furthermore, we applied a fine-tuning transfer learning method based on our deep LSTM model, which provided new participants with more accurate predictions, especially when the volume of new participants' data was limited. The transfer learning model improved the MAE performances to 13.5, 13.2, and 14.4 out of 100 for mood, health, and stress, respectively.
KW - CNN
KW - CNN-LSTM
KW - Health
KW - LSTM
KW - Mood
KW - Participant-independent
KW - Passive Sensing
KW - Regression
KW - Stress
KW - Transfer Learning
KW - Wellbeing Prediction
UR - http://www.scopus.com/inward/record.url?scp=85091047788&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85091047788&partnerID=8YFLogxK
U2 - 10.1109/EMBC44109.2020.9176242
DO - 10.1109/EMBC44109.2020.9176242
M3 - Conference contribution
AN - SCOPUS:85091047788
T3 - Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
SP - 5884
EP - 5887
BT - 42nd Annual International Conferences of the IEEE Engineering in Medicine and Biology Society
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 20 July 2020 through 24 July 2020
ER -