Where academic tradition
meets the exciting future

You are here: TUCS > PUBLICATIONS > Publication Search > Generating Heat Maps of Popula...

Generating Heat Maps of Popular Routes Online from Massive Mobile Sports Tracking Application Data in Milliseconds While Respecting Privacy

Jani Sainio, Jan Westerholm, Juha Oksanen, Generating Heat Maps of Popular Routes Online from Massive Mobile Sports Tracking Application Data in Milliseconds While Respecting Privacy. ISPRS International Journal of Geo-Information 4(4), 1813–1826, 2015.

http://dx.doi.org/10.3390/ijgi4041813

Abstract:

The breakthrough of GPS-equipped smartphones has enabled the collection of track data from human mobility on massive scales that can be used in route recommendation, urban planning and traffic management. In this work we present a fast map server that can generate and visualize heat maps of popular routes online from massive sports track data based on client preferences, e.g., running routes lasting less than an hour. The heat maps shown respect user privacy by not showing routes with less than a predefined number of different users, for instance five. The results are represented to the client using a dynamic tile layer. The current implementation uses data collected by the Sports Tracker mobile application with over 800,000 different tracks and 2.8 billion GPS data points. Stress tests indicate that the server can handle hundreds of simultaneous client requests in a single server configuration.

BibTeX entry:

@ARTICLE{aconv26489,
  title = {Generating Heat Maps of Popular Routes Online from Massive Mobile Sports Tracking Application Data in Milliseconds While Respecting Privacy},
  author = {Sainio, Jani and Westerholm, Jan and Oksanen, Juha},
  journal = {ISPRS International Journal of Geo-Information},
  volume = {4},
  number = {4},
  publisher = {MDPI International Society for Photogrammetry and Remote Sensing},
  pages = {1813–1826},
  year = {2015},
  keywords = {big data; heat map; data privacy},
  ISSN = {2220-9964},
}

Belongs to TUCS Research Unit(s): Software Engineering Laboratory (SE Lab)

Edit publication