Cargando…

Detecting activity locations from raw GPS data: a novel kernel-based algorithm

BACKGROUND: Health studies and mHealth applications are increasingly resorting to tracking technologies such as Global Positioning Systems (GPS) to study the relation between mobility, exposures, and health. GPS tracking generates large sets of geographic data that need to be transformed to be usefu...

Descripción completa

Detalles Bibliográficos
Autores principales: Thierry, Benoit, Chaix, Basile, Kestens, Yan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: BioMed Central 2013
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3637118/
https://www.ncbi.nlm.nih.gov/pubmed/23497213
http://dx.doi.org/10.1186/1476-072X-12-14
_version_ 1782267410801229824
author Thierry, Benoit
Chaix, Basile
Kestens, Yan
author_facet Thierry, Benoit
Chaix, Basile
Kestens, Yan
author_sort Thierry, Benoit
collection PubMed
description BACKGROUND: Health studies and mHealth applications are increasingly resorting to tracking technologies such as Global Positioning Systems (GPS) to study the relation between mobility, exposures, and health. GPS tracking generates large sets of geographic data that need to be transformed to be useful for health research. This paper proposes a method to test the performance of activity place detection algorithms, and compares the performance of a novel kernel-based algorithm with a more traditional time-distance cluster detection method. METHODS: A set of 750 artificial GPS tracks containing three stops each were generated, with various levels of noise.. A total of 9,000 tracks were processed to measure the algorithms’ capacity to detect stop locations and estimate stop durations, with varying GPS noise and algorithm parameters. RESULTS: The proposed kernel-based algorithm outperformed the traditional algorithm on most criteria associated to activity place detection, and offered a stronger resilience to GPS noise, managing to detect up to 92.3% of actual stops, and estimating stop duration within 5% error margins at all tested noise levels. CONCLUSIONS: Capacity to detect activity locations is an important feature in a context of increasing use of GPS devices in health and place research. While further testing with real-life tracks is recommended, testing algorithms’ performance with artificial track sets for which characteristics are controlled is useful. The proposed novel algorithm outperformed the traditional algorithm under these conditions.
format Online
Article
Text
id pubmed-3637118
institution National Center for Biotechnology Information
language English
publishDate 2013
publisher BioMed Central
record_format MEDLINE/PubMed
spelling pubmed-36371182013-04-27 Detecting activity locations from raw GPS data: a novel kernel-based algorithm Thierry, Benoit Chaix, Basile Kestens, Yan Int J Health Geogr Methodology BACKGROUND: Health studies and mHealth applications are increasingly resorting to tracking technologies such as Global Positioning Systems (GPS) to study the relation between mobility, exposures, and health. GPS tracking generates large sets of geographic data that need to be transformed to be useful for health research. This paper proposes a method to test the performance of activity place detection algorithms, and compares the performance of a novel kernel-based algorithm with a more traditional time-distance cluster detection method. METHODS: A set of 750 artificial GPS tracks containing three stops each were generated, with various levels of noise.. A total of 9,000 tracks were processed to measure the algorithms’ capacity to detect stop locations and estimate stop durations, with varying GPS noise and algorithm parameters. RESULTS: The proposed kernel-based algorithm outperformed the traditional algorithm on most criteria associated to activity place detection, and offered a stronger resilience to GPS noise, managing to detect up to 92.3% of actual stops, and estimating stop duration within 5% error margins at all tested noise levels. CONCLUSIONS: Capacity to detect activity locations is an important feature in a context of increasing use of GPS devices in health and place research. While further testing with real-life tracks is recommended, testing algorithms’ performance with artificial track sets for which characteristics are controlled is useful. The proposed novel algorithm outperformed the traditional algorithm under these conditions. BioMed Central 2013-03-16 /pmc/articles/PMC3637118/ /pubmed/23497213 http://dx.doi.org/10.1186/1476-072X-12-14 Text en Copyright © 2013 Thierry et al.; licensee BioMed Central Ltd. http://creativecommons.org/licenses/by/2.0 This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/2.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
spellingShingle Methodology
Thierry, Benoit
Chaix, Basile
Kestens, Yan
Detecting activity locations from raw GPS data: a novel kernel-based algorithm
title Detecting activity locations from raw GPS data: a novel kernel-based algorithm
title_full Detecting activity locations from raw GPS data: a novel kernel-based algorithm
title_fullStr Detecting activity locations from raw GPS data: a novel kernel-based algorithm
title_full_unstemmed Detecting activity locations from raw GPS data: a novel kernel-based algorithm
title_short Detecting activity locations from raw GPS data: a novel kernel-based algorithm
title_sort detecting activity locations from raw gps data: a novel kernel-based algorithm
topic Methodology
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3637118/
https://www.ncbi.nlm.nih.gov/pubmed/23497213
http://dx.doi.org/10.1186/1476-072X-12-14
work_keys_str_mv AT thierrybenoit detectingactivitylocationsfromrawgpsdataanovelkernelbasedalgorithm
AT chaixbasile detectingactivitylocationsfromrawgpsdataanovelkernelbasedalgorithm
AT kestensyan detectingactivitylocationsfromrawgpsdataanovelkernelbasedalgorithm