Using Smartphone Sensors for Improving Energy Expenditure Estimation

Amit Pande, Jindan Zhu, Aveek K. Das, Yunze Zeng, Prasant Mohapatra, Jay J. Han

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

Energy expenditure (EE) estimation is an important factor in tracking personal activity and preventing chronic diseases, such as obesity and diabetes. Accurate and real-time EE estimation utilizing small wearable sensors is a difficult task, primarily because the most existing schemes work offline or use heuristics. In this paper, we focus on accurate EE estimation for tracking ambulatory activities (walking, standing, climbing upstairs, or downstairs) of a typical smartphone user. We used built-in smartphone sensors (accelerometer and barometer sensor), sampled at low frequency, to accurately estimate EE. Using a barometer sensor, in addition to an accelerometer sensor, greatly increases the accuracy of EE estimation. Using bagged regression trees, a machine learning technique, we developed a generic regression model for EE estimation that yields upto 96% correlation with actual EE. We compare our results against the state-of-the-art calorimetry equations and consumer electronics devices (Fitbit and Nike+ FuelBand). The newly developed EE estimation algorithm demonstrated superior accuracy compared with currently available methods. The results were calibrated against COSMED K4b2 calorimeter readings.

Original languageEnglish (US)
Article number7272038
JournalIEEE Journal of Translational Engineering in Health and Medicine
Volume3
DOIs
StatePublished - 2015

Fingerprint

Smartphones
Energy Metabolism
Sensors
Barometers
Accelerometers
Calorimetry
Consumer electronics
Smartphone
Medical problems
Calorimeters
Walking
Learning systems
Reading
Chronic Disease
Obesity
Equipment and Supplies

Keywords

  • Accelerometer
  • Barometer
  • Energy Expenditure
  • Machine Learning

ASJC Scopus subject areas

  • Biomedical Engineering
  • Medicine(all)

Cite this

Using Smartphone Sensors for Improving Energy Expenditure Estimation. / Pande, Amit; Zhu, Jindan; Das, Aveek K.; Zeng, Yunze; Mohapatra, Prasant; Han, Jay J.

In: IEEE Journal of Translational Engineering in Health and Medicine, Vol. 3, 7272038, 2015.

Research output: Contribution to journalArticle

Pande, Amit ; Zhu, Jindan ; Das, Aveek K. ; Zeng, Yunze ; Mohapatra, Prasant ; Han, Jay J. / Using Smartphone Sensors for Improving Energy Expenditure Estimation. In: IEEE Journal of Translational Engineering in Health and Medicine. 2015 ; Vol. 3.
@article{9fc6a2360b3c43119245d13436cbd7cd,
title = "Using Smartphone Sensors for Improving Energy Expenditure Estimation",
abstract = "Energy expenditure (EE) estimation is an important factor in tracking personal activity and preventing chronic diseases, such as obesity and diabetes. Accurate and real-time EE estimation utilizing small wearable sensors is a difficult task, primarily because the most existing schemes work offline or use heuristics. In this paper, we focus on accurate EE estimation for tracking ambulatory activities (walking, standing, climbing upstairs, or downstairs) of a typical smartphone user. We used built-in smartphone sensors (accelerometer and barometer sensor), sampled at low frequency, to accurately estimate EE. Using a barometer sensor, in addition to an accelerometer sensor, greatly increases the accuracy of EE estimation. Using bagged regression trees, a machine learning technique, we developed a generic regression model for EE estimation that yields upto 96{\%} correlation with actual EE. We compare our results against the state-of-the-art calorimetry equations and consumer electronics devices (Fitbit and Nike+ FuelBand). The newly developed EE estimation algorithm demonstrated superior accuracy compared with currently available methods. The results were calibrated against COSMED K4b2 calorimeter readings.",
keywords = "Accelerometer, Barometer, Energy Expenditure, Machine Learning",
author = "Amit Pande and Jindan Zhu and Das, {Aveek K.} and Yunze Zeng and Prasant Mohapatra and Han, {Jay J.}",
year = "2015",
doi = "10.1109/JTEHM.2015.2480082",
language = "English (US)",
volume = "3",
journal = "IEEE Journal of Translational Engineering in Health and Medicine",
issn = "2168-2372",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Using Smartphone Sensors for Improving Energy Expenditure Estimation

AU - Pande, Amit

AU - Zhu, Jindan

AU - Das, Aveek K.

AU - Zeng, Yunze

AU - Mohapatra, Prasant

AU - Han, Jay J.

PY - 2015

Y1 - 2015

N2 - Energy expenditure (EE) estimation is an important factor in tracking personal activity and preventing chronic diseases, such as obesity and diabetes. Accurate and real-time EE estimation utilizing small wearable sensors is a difficult task, primarily because the most existing schemes work offline or use heuristics. In this paper, we focus on accurate EE estimation for tracking ambulatory activities (walking, standing, climbing upstairs, or downstairs) of a typical smartphone user. We used built-in smartphone sensors (accelerometer and barometer sensor), sampled at low frequency, to accurately estimate EE. Using a barometer sensor, in addition to an accelerometer sensor, greatly increases the accuracy of EE estimation. Using bagged regression trees, a machine learning technique, we developed a generic regression model for EE estimation that yields upto 96% correlation with actual EE. We compare our results against the state-of-the-art calorimetry equations and consumer electronics devices (Fitbit and Nike+ FuelBand). The newly developed EE estimation algorithm demonstrated superior accuracy compared with currently available methods. The results were calibrated against COSMED K4b2 calorimeter readings.

AB - Energy expenditure (EE) estimation is an important factor in tracking personal activity and preventing chronic diseases, such as obesity and diabetes. Accurate and real-time EE estimation utilizing small wearable sensors is a difficult task, primarily because the most existing schemes work offline or use heuristics. In this paper, we focus on accurate EE estimation for tracking ambulatory activities (walking, standing, climbing upstairs, or downstairs) of a typical smartphone user. We used built-in smartphone sensors (accelerometer and barometer sensor), sampled at low frequency, to accurately estimate EE. Using a barometer sensor, in addition to an accelerometer sensor, greatly increases the accuracy of EE estimation. Using bagged regression trees, a machine learning technique, we developed a generic regression model for EE estimation that yields upto 96% correlation with actual EE. We compare our results against the state-of-the-art calorimetry equations and consumer electronics devices (Fitbit and Nike+ FuelBand). The newly developed EE estimation algorithm demonstrated superior accuracy compared with currently available methods. The results were calibrated against COSMED K4b2 calorimeter readings.

KW - Accelerometer

KW - Barometer

KW - Energy Expenditure

KW - Machine Learning

UR - http://www.scopus.com/inward/record.url?scp=84946593023&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84946593023&partnerID=8YFLogxK

U2 - 10.1109/JTEHM.2015.2480082

DO - 10.1109/JTEHM.2015.2480082

M3 - Article

VL - 3

JO - IEEE Journal of Translational Engineering in Health and Medicine

JF - IEEE Journal of Translational Engineering in Health and Medicine

SN - 2168-2372

M1 - 7272038

ER -