@article{ref1,
title="Using GPS, GIS, and accelerometer data to predict transportation modes",
journal="Medicine and science in sports and exercise",
year="2015",
author="Brondeel, Ruben and Pannier, Bruno and Chaix, Basile",
volume="47",
number="12",
pages="2669-2675",
abstract="INTRODUCTION: Active transportation is a substantial source of physical activity, which has a positive influence on many health outcomes. A survey of transportation modes for each trip is challenging, time-consuming, and requires substantial financial investments. This study proposes a passive collection method and the prediction of modes at the trip level using random forests. <br><br>METHODS: The RECORD GPS Study collected real-life trip data from 236 participants over 7 days, including the transportation mode, GPS, GIS, and accelerometer data. A prediction model of transportation modes was constructed using the random forests method. Finally, we investigated the performance of models based on a limited number of participants/trips to predict transportation modes for a large number of trips. <br><br>RESULTS: The full model had a correct prediction rate of 90%. A simpler model of GPS explanatory variables combined with GIS variables performed nearly as well. Relatively good predictions could be made using a model based on the 991 trips of the first 30 participants. <br><br>CONCLUSION: This study uses real-life data from a large sample set to test a method for predicting transportation modes at the trip level, thereby providing a useful complement to time unit-level prediction methods. By enabling predictions based on a limited number of observations, this method may decrease the workload for participants/researchers and provide relevant trip-level data to investigate relationships between transportation and health.<p /> <p>Language: en</p>",
language="en",
issn="0195-9131",
doi="10.1249/MSS.0000000000000704",
url="http://dx.doi.org/10.1249/MSS.0000000000000704"
}