Using Deep Learning for Energy Expenditure Estimation with wearable sensors

Jindan Zhu, Amit Pande, Prasant Mohapatra, Jay J. Han

Research output: Chapter in Book/Report/Conference proceedingConference contribution

13 Citations (Scopus)

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 languageEnglish (US)
Title of host publication2015 17th International Conference on E-Health Networking, Application and Services, HealthCom 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages501-506
Number of pages6
ISBN (Electronic)9781467383257
DOIs
StatePublished - Apr 15 2016
Event17th International Conference on E-Health Networking, Application and Services, HealthCom 2015 - Boston, United States
Duration: Oct 13 2015Oct 17 2015

Other

Other17th International Conference on E-Health Networking, Application and Services, HealthCom 2015
CountryUnited States
CityBoston
Period10/13/1510/17/15

Fingerprint

neural network
Energy Metabolism
expenditures
Convolution
Learning
Neural networks
energy
Neural Networks (Computer)
learning
Disease
Sensors
Medical problems
Calorimeters
Accelerometers
Linear regression
Mean square error
Walking
chronic illness
Reading
Linear Models

ASJC Scopus subject areas

  • Health Policy
  • Health Information Management
  • Computer Networks and Communications
  • Computer Science Applications
  • Health Informatics
  • Surgery
  • Health(social science)

Cite this

Zhu, J., Pande, A., Mohapatra, P., & Han, J. J. (2016). Using Deep Learning for Energy Expenditure Estimation with wearable sensors. In 2015 17th International Conference on E-Health Networking, Application and Services, HealthCom 2015 (pp. 501-506). [7454554] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/HealthCom.2015.7454554

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 proceedingConference contribution

Zhu, J, Pande, A, Mohapatra, P & Han, JJ 2016, Using Deep Learning for Energy Expenditure Estimation with wearable sensors. in 2015 17th International Conference on E-Health Networking, Application and Services, HealthCom 2015., 7454554, Institute of Electrical and Electronics Engineers Inc., pp. 501-506, 17th International Conference on E-Health Networking, Application and Services, HealthCom 2015, Boston, United States, 10/13/15. https://doi.org/10.1109/HealthCom.2015.7454554
Zhu J, Pande A, Mohapatra P, Han JJ. Using Deep Learning for Energy Expenditure Estimation with wearable sensors. In 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 https://doi.org/10.1109/HealthCom.2015.7454554
Zhu, Jindan ; Pande, Amit ; Mohapatra, Prasant ; Han, Jay J. / Using Deep Learning for Energy Expenditure Estimation with wearable sensors. 2015 17th International Conference on E-Health Networking, Application and Services, HealthCom 2015. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 501-506
@inproceedings{af2e3ffb63c147559509dc116fb46185,
title = "Using Deep Learning for Energy Expenditure Estimation with wearable sensors",
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.",
author = "Jindan Zhu and Amit Pande and Prasant Mohapatra and Han, {Jay J.}",
year = "2016",
month = "4",
day = "15",
doi = "10.1109/HealthCom.2015.7454554",
language = "English (US)",
pages = "501--506",
booktitle = "2015 17th International Conference on E-Health Networking, Application and Services, HealthCom 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

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 -