Recently there has been a significant growth on the usage of personal fitness applications running on smart phones or fitness devices. These applications record millions of GPS points generated from the paths of runners. This data can be analyzed to comprehend behavior of runners within a specific location. In this study, using data generated from several sources such as Endomondo and Strava and other complementary data such as climate data, population data etc., we aim to find out the factors affecting running behavior in urban settings. For this purpose, visualizations of running activities are plotted with different variables by using BIG-DID, a software tool we developed as part of this study. Additionally, an evaluation of the tools used or can be used for data analysis and visualizations discussed. Finally, a linear regression model is introduced, which will be further developed in later stages of this study.
[1]
Ozgun Balaban,et al.
Visualizing Urban Sports Movement
,
2016
.
[2]
J. Scheerder,et al.
Understanding the game. Sport participation in Europe
,
2011
.
[3]
Jan Westerholm,et al.
Methods for deriving and calibrating privacy-preserving heat maps from mobile sports tracking application data
,
2015
.
[4]
Francine Laden,et al.
Perceived built environment and physical activity in U.S. women by sprawl and region.
,
2011,
American journal of preventive medicine.
[5]
Adrianne E. Hardman,et al.
Physical Activity and Health: The Evidence Explained
,
2003
.
[6]
Hartwig H. Hochmair,et al.
Estimating bicycle trip volume for Miami-Dade county from Strava tracking data
,
2019,
Journal of Transport Geography.