Next Article in Journal
A Blockchain-Based Location Privacy Protection Incentive Mechanism in Crowd Sensing Networks
Next Article in Special Issue
LSTM-Guided Coaching Assistant for Table Tennis Practice
Previous Article in Journal
Electrical Characteristics and pH Response of a Parylene-H Sensing Membrane in a Si-Nanonet Ion-Sensitive Field-Effect Transistor
Previous Article in Special Issue
Realization and Technology Acceptance Test of a Wearable Cardiac Health Monitoring and Early Warning System with Multi-Channel MCGs and ECG
Open AccessArticle

Identifying Free-Living Physical Activities Using Lab-Based Models with Wearable Accelerometers

1
School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ 85281, USA
2
College of Health Solutions, Arizona State University, Phoenix, AZ 85281, USA
3
Departamento de Formación, Pontificia Universidad Javeriana, Bogotá D.C. 110231, Colombia
*
Author to whom correspondence should be addressed.
Sensors 2018, 18(11), 3893; https://doi.org/10.3390/s18113893
Received: 11 October 2018 / Revised: 5 November 2018 / Accepted: 6 November 2018 / Published: 12 November 2018
(This article belongs to the Special Issue Data Analytics and Applications of the Wearable Sensors in Healthcare)
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. View Full-Text
Keywords: physical activity classification; free-living; GENEactiv accelerometer; machine learning; Gaussian mixture model; hidden Markov model; wavelets physical activity classification; free-living; GENEactiv accelerometer; machine learning; Gaussian mixture model; hidden Markov model; wavelets
Show Figures

Figure 1

MDPI and ACS Style

Dutta, A.; Ma, O.; Toledo, M.; Pregonero, A.F.; Ainsworth, B.E.; Buman, M.P.; Bliss, D.W. Identifying Free-Living Physical Activities Using Lab-Based Models with Wearable Accelerometers. Sensors 2018, 18, 3893. https://doi.org/10.3390/s18113893

AMA Style

Dutta A, Ma O, Toledo M, Pregonero AF, Ainsworth BE, Buman MP, Bliss DW. Identifying Free-Living Physical Activities Using Lab-Based Models with Wearable Accelerometers. Sensors. 2018; 18(11):3893. https://doi.org/10.3390/s18113893

Chicago/Turabian Style

Dutta, Arindam; Ma, Owen; Toledo, Meynard; Pregonero, Alberto F.; Ainsworth, Barbara E.; Buman, Matthew P.; Bliss, Daniel W. 2018. "Identifying Free-Living Physical Activities Using Lab-Based Models with Wearable Accelerometers" Sensors 18, no. 11: 3893. https://doi.org/10.3390/s18113893

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop