EasyTracker: automatic transit tracking, mapping, and arrival time prediction using smartphones

  • Authors:
  • James Biagioni;Tomas Gerlich;Timothy Merrifield;Jakob Eriksson

  • Affiliations:
  • University of Illinois at Chicago, Chicago, IL;University of Illinois at Chicago, Chicago, IL;University of Illinois at Chicago, Chicago, IL;University of Illinois at Chicago, Chicago, IL

  • Venue:
  • Proceedings of the 9th ACM Conference on Embedded Networked Sensor Systems
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

In order to facilitate the introduction of transit tracking and arrival time prediction in smaller transit agencies, we investigate an automatic, smartphone-based system which we call EasyTracker. To use EasyTracker, a transit agency must obtain smartphones, install an app, and place a phone in each transit vehicle. Our goal is to require no other input. This level of automation is possible through a set of algorithms that use GPS traces collected from instrumented transit vehicles to determine routes served, locate stops, and infer schedules. In addition, online algorithms automatically determine the route served by a given vehicle at a given time and predict its arrival time at upcoming stops. We evaluate our algorithms on real datasets from two existing transit services. We demonstrate our ability to accurately reconstruct routes and schedules, and compare our system's arrival time prediction performance with the current "state of the art" for smaller transit operators: the official schedule. Finally, we discuss our current prototype implementation and the steps required to take it from a research prototype to a real system.