Abstract
Utilization of movement data from mobile sports tracking applications is affected by its inherent biases and sensitivity, which need to be understood when developing value-added services for, e.g., application users and city planners. We have developed a method for generating a privacy-preserving heat map with user diversity (ppDIV), in which the density of trajectories, as well as the diversity of users, is taken into account, thus preventing the bias effects caused by participation inequality. The method is applied to public cycling workouts and compared with privacy-preserving kernel density estimation (ppKDE) focusing only on the density of the recorded trajectories and privacy-preserving user count calculation (ppUCC), which is similar to the quadrat-count of individual application users. An awareness of privacy was introduced to all methods as a data pre-processing step following the principle of k-Anonymity. Calibration results for our heat maps using bicycle counting data gathered by the city of Helsinki are good (R2>0.7) and raise high expectations for utilizing heat maps in a city planning context. This is further supported by the diurnal distribution of the workouts indicating that, in addition to sports-oriented cyclists, many utilitarian cyclists are tracking their commutes. However, sports tracking data can only enrich official in-situ counts with its high spatio-temporal resolution and coverage, not replace them.
Highlights
Mobile sports tracking applications have become popular among the public audience, and a large number of smartphone users are willing to collect and compare their workouts privately, as well as to share their data within social networks or even publicly, for all application and Internet users
When integrated into a location-based service (LBS), the result of our analysis replies to the end-user's question “Where have most cyclists continued to from here?” In addition, we investigate the relation of tracking data and in-situ bicycle counting information in order to compare the quality of the derived heat maps, as well as to calibrate the heat maps based on mobile sports tracking application data, for example, for city planning purposes
In preserving heat map with user diversity (ppDIV) (Fig. 4c), we took into account the density of the workout trajectories and the diversity of users, which resulted in a heat map that closely corresponded to privacy-preserving kernel density estimation (ppKDE) but that did not suffer from the bias introduced by very active application users
Summary
Mobile sports tracking applications have become popular among the public audience, and a large number of smartphone users are willing to collect and compare their workouts privately, as well as to share their data within social networks or even publicly, for all application and Internet users. Key factors in this development have been the maturity of sensor technology, such as an accelerometer, digital compass, gyroscope, and GPS (e.g., Lane et al, 2010), available in most recent mid- and top-range smartphones; and well-documented application programming interfaces for third-party developers to create new applications for mobile platforms. We use the term “workout” throughout the paper to denote all recorded trajectories, be they recreational/exercise or utilitarian by purpose
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call