{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T19:46:25Z","timestamp":1773863185279,"version":"3.50.1"},"reference-count":46,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2020,1,21]],"date-time":"2020-01-21T00:00:00Z","timestamp":1579564800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>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.<\/jats:p>","DOI":"10.3390\/s20030588","type":"journal-article","created":{"date-parts":[[2020,1,21]],"date-time":"2020-01-21T11:25:59Z","timestamp":1579605959000},"page":"588","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":36,"title":["Using Accelerometer and GPS Data for Real-Life Physical Activity Type Detection"],"prefix":"10.3390","volume":"20","author":[{"given":"Hoda","family":"Allahbakhshi","sequence":"first","affiliation":[{"name":"Department of Geography, Geographic Information Systems Unit, University of Zurich (UZH), Winterthurerstrasse 190, 8057 Zurich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3693-0763","authenticated-orcid":false,"given":"Lindsey","family":"Conrow","sequence":"additional","affiliation":[{"name":"Department of Geography, Geographic Information Systems Unit, University of Zurich (UZH), Winterthurerstrasse 190, 8057 Zurich, Switzerland"},{"name":"University Research Priority Program \u201cDynamics of Healthy Aging\u201d, University of Zurich, Andreasstrasse 15, 8050 Zurich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5431-2729","authenticated-orcid":false,"given":"Babak","family":"Naimi","sequence":"additional","affiliation":[{"name":"Department of Geosciences and Geography, University of Helsinki, P.O. Box 64, 00014 Helsinki, Finland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2425-0077","authenticated-orcid":false,"given":"Robert","family":"Weibel","sequence":"additional","affiliation":[{"name":"Department of Geography, Geographic Information Systems Unit, University of Zurich (UZH), Winterthurerstrasse 190, 8057 Zurich, Switzerland"},{"name":"University Research Priority Program \u201cDynamics of Healthy Aging\u201d, University of Zurich, Andreasstrasse 15, 8050 Zurich, Switzerland"}]}],"member":"1968","published-online":{"date-parts":[[2020,1,21]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"124","DOI":"10.1016\/j.compenvurbsys.2017.09.012","article-title":"Physical activity classification in free-living conditions using smartphone accelerometer data and exploration of predicted results","volume":"67","author":"Lee","year":"2018","journal-title":"Comput. Environ. Urban Syst."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"2720","DOI":"10.1001\/jama.1988.03720180046031","article-title":"Walking for Health and Fitness","volume":"259","author":"Rippe","year":"1988","journal-title":"JAMA"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1042","DOI":"10.1152\/japplphysiol.00984.2012","article-title":"Impact of study design on development and evaluation of an activity-type classifier","volume":"114","author":"Golubic","year":"2013","journal-title":"J. Appl. Physiol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1267","DOI":"10.3390\/s140101267","article-title":"Recommendations for Standardizing Validation Procedures Assessing Physical Activity of Older Persons by Monitoring Body Postures and Movements","volume":"14","author":"Lindemann","year":"2014","journal-title":"Sensors"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"75","DOI":"10.3389\/fphys.2019.00075","article-title":"The Key Factors in Physical Activity Type Detection Using Real-Life Data: A Systematic Review","volume":"10","author":"Allahbakhshi","year":"2019","journal-title":"Front. Physiol."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"880","DOI":"10.1123\/jpah.10.6.880","article-title":"Assessment of physical activity and energy expenditure by GPS combined with accelerometry in real-life conditions","volume":"10","author":"Nguyen","year":"2012","journal-title":"J. Phys. Act. Health"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"2656","DOI":"10.1109\/TBME.2011.2160723","article-title":"Identifying Types of Physical Activity with a Single Accelerometer: Evaluating Laboratory-trained Algorithms in Daily Life","volume":"58","author":"Gyllensten","year":"2011","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_8","first-page":"127","article-title":"Method for Recognition of the Physical Activity of Human Being Using a Wearable Accelerometer","volume":"20","year":"2014","journal-title":"Elektron. Elektrotechnika"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1649","DOI":"10.1093\/comjnl\/bxt075","article-title":"Recognizing Daily and Sports Activities in Two Open Source Machine Learning Environments Using Body-Worn Sensor Units","volume":"57","author":"Barshan","year":"2013","journal-title":"Comput. J."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1123\/jpah.2011-0347","article-title":"Detection of Physical Activity Types Using Triaxial Accelerometers","volume":"11","author":"Skotte","year":"2014","journal-title":"J. Phys. Act. Health"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1016\/j.gaitpost.2015.10.016","article-title":"Instrumented shoes for activity classification in the elderly","volume":"44","author":"Major","year":"2016","journal-title":"Gait Posture"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"386","DOI":"10.1109\/JSEN.2016.2628346","article-title":"A Survey on Activity Detection and Classification Using Wearable Sensors","volume":"17","author":"Cornacchia","year":"2016","journal-title":"IEEE Sens. J."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"972","DOI":"10.1249\/MSS.0b013e318164c407","article-title":"Prediction of Activity Mode with Global Positioning System and Accelerometer Data","volume":"40","author":"Troped","year":"2008","journal-title":"Med. Sci. Sports Exerc."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"392","DOI":"10.1123\/pes.22.3.392","article-title":"Describing patterns of physical activity in adolescents using global positioning systems and accelerometry","volume":"22","author":"Maddison","year":"2010","journal-title":"Pediatr. Exerc. Sci."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1016\/j.ypmed.2010.02.002","article-title":"Using accelerometers and GPS units to identify the proportion of daily physical activity located in parks with playgrounds in New Zealand children","volume":"50","author":"Quigg","year":"2010","journal-title":"Prev. Med."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1016\/j.ypmed.2010.06.001","article-title":"Greenspace and children\u2019s physical activity: A GPS \/ GIS analysis of the PEACH project","volume":"51","author":"Wheeler","year":"2010","journal-title":"Prev. Med."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1186\/s12942-016-0065-5","article-title":"Characterizing physical activity and food urban environments: A GIS-based multicomponent proposal","volume":"15","author":"Cebrecos","year":"2016","journal-title":"Int. J. Health Geogr."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1016\/j.landurbplan.2013.09.006","article-title":"Using participatory GIS to measure physical activity and urban park benefits","volume":"121","author":"Brown","year":"2014","journal-title":"Landsc. Urban Plan."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1186\/1479-5868-8-71","article-title":"Using Geographic Information Systems (GIS) to assess the role of the built environment in influencing obesity: A glossary","volume":"8","author":"Pearce","year":"2011","journal-title":"Int. J. Behav. Nutr. Phys. Act."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1186\/1742-5573-4-16","article-title":"The effects of neighborhood density and street connectivity on walking behavior: The Twin Cities walking study","volume":"4","author":"Oakes","year":"2007","journal-title":"Epidemiol. Perspect. Innov."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1552","DOI":"10.2105\/AJPH.93.9.1552","article-title":"Neighborhood-Based Differences in Physical Activity: An Environment Scale Evaluation","volume":"93","author":"Saelens","year":"2003","journal-title":"Am. J. Public Health"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1016\/j.healthplace.2011.09.003","article-title":"A study of community design, greenness, and physical activity in children using satellite, GPS and accelerometer data","volume":"18","author":"Almanza","year":"2011","journal-title":"Health Place"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"429","DOI":"10.1016\/j.amepre.2009.12.032","article-title":"The built environment and location-based physical activity","volume":"38","author":"Troped","year":"2010","journal-title":"Am. J. Prev. Med."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1522","DOI":"10.1111\/tgis.12485","article-title":"Automatic physical activity and in-vehicle status classification based on GPS and accelerometer data: A hierarchical classification approach using machine learning techniques","volume":"22","author":"Lee","year":"2018","journal-title":"Trans. GIS"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1016\/j.healthplace.2015.08.005","article-title":"Public transit generates new physical activity: Evidence from individual GPS 583 and accelerometer data before and after light rail construction in a neighborhood of Salt Lake City, Utah, USA","volume":"36","author":"Miller","year":"2015","journal-title":"Health Place"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"338","DOI":"10.1038\/sj.ejcn.1600403","article-title":"Could a satellite-based navigation system (GPS) be used to assess the physical activity of individuals on earth?","volume":"51","author":"Schutz","year":"1997","journal-title":"Eur. J. Clin. Nutr."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"124","DOI":"10.1249\/mss.0b013e3181590bc2","article-title":"Assessment of Speed and Position during Human Locomotion Using Nondifferential GPS","volume":"40","author":"Townshend","year":"2008","journal-title":"Med. Sci. Sports Exerc."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1891","DOI":"10.1016\/j.jbiomech.2004.02.031","article-title":"Accuracy of non-differential GPS for the determination of speed over ground","volume":"37","author":"Witte","year":"2004","journal-title":"J. Biomech."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1919","DOI":"10.1097\/00005768-200111000-00018","article-title":"The use of dGPS and simultaneous metabolic measurements during orienteering","volume":"33","author":"Larsson","year":"2001","journal-title":"Med. Sci. Sports Exerc."},{"key":"ref_30","first-page":"164","article-title":"Improvement of walking speed prediction by accelerometry and altimetry, validated by satellite positioning","volume":"38","author":"Perrin","year":"2000","journal-title":"Med. Biol. Eng."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1145\/1689239.1689243","article-title":"Using mobile phones to determine transportation modes","volume":"6","author":"Reddy","year":"2010","journal-title":"ACM Trans. Sens. Netw."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"2","DOI":"10.3389\/fpubh.2014.00036","article-title":"Identifying Active Travel Behaviors in Challenging Environments Using GPS, Accelerometers, and Machine Learning Algorithms","volume":"2","author":"Ellis","year":"2014","journal-title":"Front. Public Health"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"2669","DOI":"10.1249\/MSS.0000000000000704","article-title":"Using GPS, GIS, and Accelerometer Data to Predict Transportation Modes","volume":"47","author":"Brondeel","year":"2015","journal-title":"Med. Sci. Sports Exerc."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1109\/TITB.2007.899496","article-title":"Detection of Daily Activities and Sports with Wearable Sensors in Controlled and Uncontrolled Conditions","volume":"12","author":"Ermes","year":"2008","journal-title":"IEEE Trans. Inf. Technol. Biomed."},{"key":"ref_35","first-page":"5126816","article-title":"A Mobile Application for Easy Design and Testing of Algorithms to Monitor Physical Activity in the Workplace","volume":"2016","author":"Spinsante","year":"2016","journal-title":"Mob. Inf. Syst."},{"key":"ref_36","first-page":"66","article-title":"Development of the World Health Organization Global Physical 609 Activity Questionnaire (GPAQ)","volume":"14","author":"Armstrong","year":"2016","journal-title":"Public Health"},{"key":"ref_37","unstructured":"Allahbakhshi, H., Haosheng, H., and Weibel, R. (2018, January 12\u201315). A Study Design for Physical Activity 611 Reference Data Collection Using GPS and Accelerometer. Proceedings of the 21th AGILE 612 Conference on Geographic Information Science, Lund, Sweden."},{"key":"ref_38","unstructured":"Allahbakhshi, H., and Weibel, R. (2020). Transferability of PA type detection models between different age cohorts. in press."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"312","DOI":"10.1016\/j.trc.2007.05.002","article-title":"Current map-616 matching algorithms for transport applications: State-of-the art and future research directions","volume":"15","author":"Quddus","year":"2007","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"ref_40","unstructured":"(2019, August 15). OpenStreetMap Contributors. \u201cOpenStreetMap\u201d. Available online: www.openstreetmap.org."},{"key":"ref_41","unstructured":"R Core Team (2013). R: A Language and Environment for Statistical Computing, R Foundation for Statistical Computing. Available online: http:\/\/www.r-project.org\/."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Wright, M.N., and Ziegler, A. (2017). ranger: A Fast Implementation of Random Forests for High Dimensional Data in C++ and R. J. Stat. Softw., 77.","DOI":"10.18637\/jss.v077.i01"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1249\/MSS.0b013e3181e5797d","article-title":"Evaluation of Neural Networks to Identify Types of Activity Using Accelerometers","volume":"43","author":"Garre","year":"2011","journal-title":"Med. Sci. Sports Exerc."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"545","DOI":"10.1016\/j.patcog.2018.04.022","article-title":"Learning structures of interval-based Bayesian networks in probabilistic generative model for human complex activity recognition","volume":"81","author":"Liu","year":"2018","journal-title":"Pattern Recognit."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Wang, C., Gong, L., Lu, Y., Sun, F., Xu, C., Li, X., and Zhou, X. (2017, January 5\u20138). A Power-Efficient Accelerator Based on FPGAs for LSTM Network. Proceedings of the 2017 IEEE International Conference on Cluster Computing (CLUSTER), Honolulu, HI, USA.","DOI":"10.1109\/CLUSTER.2017.45"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Guan, Y., Yuan, Z., Sun, G., and Cong, J. (2017, January 16\u201319). FPGA-based accelerator for long short-term memory recurrent neural networks. Proceedings of the 2017 22nd Asia and South Pacific Design Automation Conference (ASP-DAC), Chiba, Japan.","DOI":"10.1109\/ASPDAC.2017.7858394"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/20\/3\/588\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T13:20:28Z","timestamp":1760361628000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/20\/3\/588"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,1,21]]},"references-count":46,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2020,2]]}},"alternative-id":["s20030588"],"URL":"https:\/\/doi.org\/10.3390\/s20030588","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,1,21]]}}}