Header

UZH-Logo

Maintenance Infos

Using accelerometer and GPS data for real-life physical activity type detection


Allahbakhshi, Hoda; Conrow, Lindsey; Naimi, Babak; Weibel, Robert (2020). Using accelerometer and GPS data for real-life physical activity type detection. Sensors, 20(3):588.

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.

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.

Statistics

Citations

Dimensions.ai Metrics
6 citations in Web of Science®
7 citations in Scopus®
Google Scholar™

Altmetrics

Downloads

17 downloads since deposited on 13 Mar 2020
8 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Journal Article, refereed, original work
Communities & Collections:07 Faculty of Science > Institute of Geography
08 Research Priority Programs > Dynamics of Healthy Aging
Dewey Decimal Classification:910 Geography & travel
Scopus Subject Areas:Physical Sciences > Analytical Chemistry
Life Sciences > Biochemistry
Physical Sciences > Atomic and Molecular Physics, and Optics
Physical Sciences > Instrumentation
Physical Sciences > Electrical and Electronic Engineering
Uncontrolled Keywords:Electrical and Electronic Engineering, Analytical Chemistry, Atomic and Molecular Physics, and Optics, Biochemistry
Language:English
Date:21 January 2020
Deposited On:13 Mar 2020 09:33
Last Modified:30 Dec 2020 08:10
Publisher:MDPI Publishing
ISSN:1424-8220
OA Status:Gold
Free access at:Publisher DOI. An embargo period may apply.
Publisher DOI:https://doi.org/10.3390/s20030588

Download

Gold Open Access

Download PDF  'Using accelerometer and GPS data for real-life physical activity type detection'.
Preview
Content: Published Version
Language: English
Filetype: PDF
Size: 2MB
View at publisher
Licence: Creative Commons: Attribution 4.0 International (CC BY 4.0)