Abstract
Energy Expenditure (EE) Estimation is an important step in tracking personal activity and preventing chronic diseases such as obesity, diabetes and cardiovascular diseases. Accurate and online EE estimation using small wearable sensors is a difficult task, primarily because most existing schemes work offline or using heuristics. In this work, we focus on accurate EE estimation for tracking ambulatory activities (walking, standing, climbing upstairs or downstairs) of individuals wearing mobile sensors. We use Convolution Neural Networks (CNNs) to automatically detect important features from data collected from triaxial accelerometer and heart rate sensors. Using CNNs, we find a significant improvement in EE estimation compared to other state-of-the-art models. We compare our results against state-of-the-art Activity-Specific Linear Regression as well as Artificial Neural Networks (ANN) based models. Using a universal CNN model, we obtain an overall low Root Mean Square Error (RMSE) of 1.12 which is 30% and 35% lower than existing models. The results were calibrated against a COSMED K4b2 indirect calorimeter readings.
| Original language | English (US) |
|---|---|
| Title of host publication | 2015 17th International Conference on E-Health Networking, Application and Services, HealthCom 2015 |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 501-506 |
| Number of pages | 6 |
| ISBN (Electronic) | 9781467383257 |
| DOIs | |
| State | Published - Apr 15 2016 |
| Event | 17th International Conference on E-Health Networking, Application and Services, HealthCom 2015 - Boston, United States Duration: Oct 13 2015 → Oct 17 2015 |
Other
| Other | 17th International Conference on E-Health Networking, Application and Services, HealthCom 2015 |
|---|---|
| Country | United States |
| City | Boston |
| Period | 10/13/15 → 10/17/15 |
Fingerprint
ASJC Scopus subject areas
- Health Policy
- Health Information Management
- Computer Networks and Communications
- Computer Science Applications
- Health Informatics
- Surgery
- Health(social science)
Cite this
Using Deep Learning for Energy Expenditure Estimation with wearable sensors. / Zhu, Jindan; Pande, Amit; Mohapatra, Prasant; Han, Jay J.
2015 17th International Conference on E-Health Networking, Application and Services, HealthCom 2015. Institute of Electrical and Electronics Engineers Inc., 2016. p. 501-506 7454554.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Using Deep Learning for Energy Expenditure Estimation with wearable sensors
AU - Zhu, Jindan
AU - Pande, Amit
AU - Mohapatra, Prasant
AU - Han, Jay J.
PY - 2016/4/15
Y1 - 2016/4/15
N2 - Energy Expenditure (EE) Estimation is an important step in tracking personal activity and preventing chronic diseases such as obesity, diabetes and cardiovascular diseases. Accurate and online EE estimation using small wearable sensors is a difficult task, primarily because most existing schemes work offline or using heuristics. In this work, we focus on accurate EE estimation for tracking ambulatory activities (walking, standing, climbing upstairs or downstairs) of individuals wearing mobile sensors. We use Convolution Neural Networks (CNNs) to automatically detect important features from data collected from triaxial accelerometer and heart rate sensors. Using CNNs, we find a significant improvement in EE estimation compared to other state-of-the-art models. We compare our results against state-of-the-art Activity-Specific Linear Regression as well as Artificial Neural Networks (ANN) based models. Using a universal CNN model, we obtain an overall low Root Mean Square Error (RMSE) of 1.12 which is 30% and 35% lower than existing models. The results were calibrated against a COSMED K4b2 indirect calorimeter readings.
AB - Energy Expenditure (EE) Estimation is an important step in tracking personal activity and preventing chronic diseases such as obesity, diabetes and cardiovascular diseases. Accurate and online EE estimation using small wearable sensors is a difficult task, primarily because most existing schemes work offline or using heuristics. In this work, we focus on accurate EE estimation for tracking ambulatory activities (walking, standing, climbing upstairs or downstairs) of individuals wearing mobile sensors. We use Convolution Neural Networks (CNNs) to automatically detect important features from data collected from triaxial accelerometer and heart rate sensors. Using CNNs, we find a significant improvement in EE estimation compared to other state-of-the-art models. We compare our results against state-of-the-art Activity-Specific Linear Regression as well as Artificial Neural Networks (ANN) based models. Using a universal CNN model, we obtain an overall low Root Mean Square Error (RMSE) of 1.12 which is 30% and 35% lower than existing models. The results were calibrated against a COSMED K4b2 indirect calorimeter readings.
UR - http://www.scopus.com/inward/record.url?scp=84966473909&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84966473909&partnerID=8YFLogxK
U2 - 10.1109/HealthCom.2015.7454554
DO - 10.1109/HealthCom.2015.7454554
M3 - Conference contribution
AN - SCOPUS:84966473909
SP - 501
EP - 506
BT - 2015 17th International Conference on E-Health Networking, Application and Services, HealthCom 2015
PB - Institute of Electrical and Electronics Engineers Inc.
ER -