Abstract

The purpose of this study was to classify, and model various physical activities performed by a diverse group of participants in a supervised lab-based protocol and utilize the model to identify physical activity in a free-living setting. Wrist-worn accelerometer data were collected from (N = 152) adult participants; age 18–64 years, and processed the data to identify and model unique physical activities performed by the participants in controlled settings. The Gaussian mixture model (GMM) and the hidden Markov model (HMM) algorithms were used to model the physical activities with time and frequency-based accelerometer features. An overall model accuracy of 92.7% and 94.7% were achieved to classify 24 physical activities using GMM and HMM, respectively. The most accurate model was then used to identify physical activities performed by 20 participants, each recorded for two free-living sessions of approximately six hours each. The free-living activity intensities were estimated with 80% accuracy and showed the dominance of stationary and light intensity activities in 36 out of 40 recorded sessions. This work proposes a novel activity recognition process to identify unsupervised free-living activities using lab-based classification models. In summary, this study contributes to the use of wearable sensors to identify physical activities and estimate energy expenditure in free-living settings.

Original languageEnglish (US)
Article number3893
JournalSensors (Switzerland)
Volume18
Issue number11
DOIs
StatePublished - Nov 12 2018

Fingerprint

accelerometers
Accelerometers
Exercise
Hidden Markov models
Wrist
Energy Metabolism
wrist
Light
luminous intensity

Keywords

  • Free-living
  • Gaussian mixture model
  • GENEactiv accelerometer
  • Hidden Markov model
  • Machine learning
  • Physical activity classification
  • Wavelets

ASJC Scopus subject areas

  • Analytical Chemistry
  • Atomic and Molecular Physics, and Optics
  • Biochemistry
  • Instrumentation
  • Electrical and Electronic Engineering

Cite this

Identifying free-living physical activities using lab-based models with wearable accelerometers. / Dutta, Arindam; Ma, Owen; Toledo, Meynard; Pregonero, Alberto Florez; Ainsworth, Barbara; Buman, Matthew; Bliss, Daniel.

In: Sensors (Switzerland), Vol. 18, No. 11, 3893, 12.11.2018.

Research output: Contribution to journalArticle

@article{12ea92316dea4ab09b47eb43bae37f94,
title = "Identifying free-living physical activities using lab-based models with wearable accelerometers",
abstract = "The purpose of this study was to classify, and model various physical activities performed by a diverse group of participants in a supervised lab-based protocol and utilize the model to identify physical activity in a free-living setting. Wrist-worn accelerometer data were collected from (N = 152) adult participants; age 18–64 years, and processed the data to identify and model unique physical activities performed by the participants in controlled settings. The Gaussian mixture model (GMM) and the hidden Markov model (HMM) algorithms were used to model the physical activities with time and frequency-based accelerometer features. An overall model accuracy of 92.7{\%} and 94.7{\%} were achieved to classify 24 physical activities using GMM and HMM, respectively. The most accurate model was then used to identify physical activities performed by 20 participants, each recorded for two free-living sessions of approximately six hours each. The free-living activity intensities were estimated with 80{\%} accuracy and showed the dominance of stationary and light intensity activities in 36 out of 40 recorded sessions. This work proposes a novel activity recognition process to identify unsupervised free-living activities using lab-based classification models. In summary, this study contributes to the use of wearable sensors to identify physical activities and estimate energy expenditure in free-living settings.",
keywords = "Free-living, Gaussian mixture model, GENEactiv accelerometer, Hidden Markov model, Machine learning, Physical activity classification, Wavelets",
author = "Arindam Dutta and Owen Ma and Meynard Toledo and Pregonero, {Alberto Florez} and Barbara Ainsworth and Matthew Buman and Daniel Bliss",
year = "2018",
month = "11",
day = "12",
doi = "10.3390/s18113893",
language = "English (US)",
volume = "18",
journal = "Sensors (Switzerland)",
issn = "1424-8220",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "11",

}

TY - JOUR

T1 - Identifying free-living physical activities using lab-based models with wearable accelerometers

AU - Dutta, Arindam

AU - Ma, Owen

AU - Toledo, Meynard

AU - Pregonero, Alberto Florez

AU - Ainsworth, Barbara

AU - Buman, Matthew

AU - Bliss, Daniel

PY - 2018/11/12

Y1 - 2018/11/12

N2 - The purpose of this study was to classify, and model various physical activities performed by a diverse group of participants in a supervised lab-based protocol and utilize the model to identify physical activity in a free-living setting. Wrist-worn accelerometer data were collected from (N = 152) adult participants; age 18–64 years, and processed the data to identify and model unique physical activities performed by the participants in controlled settings. The Gaussian mixture model (GMM) and the hidden Markov model (HMM) algorithms were used to model the physical activities with time and frequency-based accelerometer features. An overall model accuracy of 92.7% and 94.7% were achieved to classify 24 physical activities using GMM and HMM, respectively. The most accurate model was then used to identify physical activities performed by 20 participants, each recorded for two free-living sessions of approximately six hours each. The free-living activity intensities were estimated with 80% accuracy and showed the dominance of stationary and light intensity activities in 36 out of 40 recorded sessions. This work proposes a novel activity recognition process to identify unsupervised free-living activities using lab-based classification models. In summary, this study contributes to the use of wearable sensors to identify physical activities and estimate energy expenditure in free-living settings.

AB - The purpose of this study was to classify, and model various physical activities performed by a diverse group of participants in a supervised lab-based protocol and utilize the model to identify physical activity in a free-living setting. Wrist-worn accelerometer data were collected from (N = 152) adult participants; age 18–64 years, and processed the data to identify and model unique physical activities performed by the participants in controlled settings. The Gaussian mixture model (GMM) and the hidden Markov model (HMM) algorithms were used to model the physical activities with time and frequency-based accelerometer features. An overall model accuracy of 92.7% and 94.7% were achieved to classify 24 physical activities using GMM and HMM, respectively. The most accurate model was then used to identify physical activities performed by 20 participants, each recorded for two free-living sessions of approximately six hours each. The free-living activity intensities were estimated with 80% accuracy and showed the dominance of stationary and light intensity activities in 36 out of 40 recorded sessions. This work proposes a novel activity recognition process to identify unsupervised free-living activities using lab-based classification models. In summary, this study contributes to the use of wearable sensors to identify physical activities and estimate energy expenditure in free-living settings.

KW - Free-living

KW - Gaussian mixture model

KW - GENEactiv accelerometer

KW - Hidden Markov model

KW - Machine learning

KW - Physical activity classification

KW - Wavelets

UR - http://www.scopus.com/inward/record.url?scp=85056525702&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85056525702&partnerID=8YFLogxK

U2 - 10.3390/s18113893

DO - 10.3390/s18113893

M3 - Article

VL - 18

JO - Sensors (Switzerland)

JF - Sensors (Switzerland)

SN - 1424-8220

IS - 11

M1 - 3893

ER -