Next Article in Journal
Auto-Correction of 3D-Orientation of IMUs on Electric Bicycles
Next Article in Special Issue
Data Analytics and Applications of the Wearable Sensors in Healthcare: An Overview
Previous Article in Journal
Review on Smart Electro-Clothing Systems (SeCSs)
Previous Article in Special Issue
Allumo: Preprocessing and Calibration Software for Wearable Accelerometers Used in Posture Tracking
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

Using Accelerometer and GPS Data for Real-Life Physical Activity Type Detection

1
Department of Geography, Geographic Information Systems Unit, University of Zurich (UZH), Winterthurerstrasse 190, 8057 Zurich, Switzerland
2
University Research Priority Program “Dynamics of Healthy Aging”, University of Zurich, Andreasstrasse 15, 8050 Zurich, Switzerland
3
Department of Geosciences and Geography, University of Helsinki, P.O. Box 64, 00014 Helsinki, Finland
*
Author to whom correspondence should be addressed.
Sensors 2020, 20(3), 588; https://doi.org/10.3390/s20030588
Submission received: 14 December 2019 / Revised: 16 January 2020 / Accepted: 17 January 2020 / Published: 21 January 2020
(This article belongs to the Special Issue Data Analytics and Applications of the Wearable Sensors in Healthcare)

Abstract

This paper aims to examine the role of global positioning system (GPS) sensor data in real-life physical activity (PA) type detection. Thirty-three young participants wore devices including GPS and accelerometer sensors on five body positions and performed daily PAs in two protocols, namely semi-structured and real-life. One general random forest (RF) model integrating data from all sensors and five individual RF models using data from each sensor position were trained using semi-structured (Scenario 1) and combined (semi-structured + real-life) data (Scenario 2). The results showed that in general, adding GPS features (speed and elevation difference) to accelerometer data improves classification performance particularly for detecting non-level and level walking. Assessing the transferability of the models on real-life data showed that models from Scenario 2 are strongly transferable, particularly when adding GPS data to the training data. Comparing individual models indicated that knee-models provide comparable classification performance (above 80%) to general models in both scenarios. In conclusion, adding GPS data improves real-life PA type classification performance if combined data are used for training the model. Moreover, the knee-model provides the minimal device configuration with reliable accuracy for detecting real-life PA types.
Keywords: physical activity type; real-life; GPS; GIS physical activity type; real-life; GPS; GIS

Share and Cite

MDPI and ACS Style

Allahbakhshi, H.; Conrow, L.; Naimi, B.; Weibel, R. Using Accelerometer and GPS Data for Real-Life Physical Activity Type Detection. Sensors 2020, 20, 588. https://doi.org/10.3390/s20030588

AMA Style

Allahbakhshi H, Conrow L, Naimi B, Weibel R. Using Accelerometer and GPS Data for Real-Life Physical Activity Type Detection. Sensors. 2020; 20(3):588. https://doi.org/10.3390/s20030588

Chicago/Turabian Style

Allahbakhshi, Hoda, Lindsey Conrow, Babak Naimi, and Robert Weibel. 2020. "Using Accelerometer and GPS Data for Real-Life Physical Activity Type Detection" Sensors 20, no. 3: 588. https://doi.org/10.3390/s20030588

APA Style

Allahbakhshi, H., Conrow, L., Naimi, B., & Weibel, R. (2020). Using Accelerometer and GPS Data for Real-Life Physical Activity Type Detection. Sensors, 20(3), 588. https://doi.org/10.3390/s20030588

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop