Inferring human mobility patterns from taxicab location traces

Raghu Ganti, Mudhakar Srivatsa, Anand Ranganathan, Jiawei Han

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Taxicabs equipped with real-time location sensing devices are increasingly becoming popular. Such location traces are a rich source of information and can be used for congestion pricing, taxicab placement, and improved city planning. An important problem to enable these application is to identify human mobility patterns from the taxicab traces, which translates to being able to identify pickup and drop off points for a particular trip. In this paper, we show that while past approaches are effective in detecting hotspots using location traces, they are largely ineffective in identifying trips (pairs of pickup and drop off points). We propose the use of a graph theory concept - stretch factor in a novel manner to identify trip(s) made by a taxicab and show that a Hidden Markov Model based algorithm can identify trips (using real datasets from taxicab deployments in Shanghai and partially simulated datasets from Stockholm) with precision and recall of 90-94% -, a significant improvement over past approaches that result in a precision and recall of about 50-60%.

Original languageEnglish (US)
Title of host publicationUbiComp 2013 - Proceedings of the 2013 ACM International Joint Conference on Pervasive and Ubiquitous Computing
Pages459-468
Number of pages10
DOIs
StatePublished - 2013
Event2013 ACM International Joint Conference on Pervasive and Ubiquitous Computing, UbiComp 2013 - Zurich, Switzerland
Duration: Sep 8 2013Sep 12 2013

Publication series

NameUbiComp 2013 - Proceedings of the 2013 ACM International Joint Conference on Pervasive and Ubiquitous Computing

Other

Other2013 ACM International Joint Conference on Pervasive and Ubiquitous Computing, UbiComp 2013
CountrySwitzerland
CityZurich
Period9/8/139/12/13

Keywords

  • Hidden markov models
  • Human mobility patterns
  • Taxi cab occupancy
  • Trajectory analysis

ASJC Scopus subject areas

  • Software

Fingerprint Dive into the research topics of 'Inferring human mobility patterns from taxicab location traces'. Together they form a unique fingerprint.

Cite this