Spatial movement pattern discovery with LCS-based path similarity measure

Ping Yan, Daniel D. Zeng

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

1 Scopus citations

Abstract

Location-enhanced applications are a rapidly emerging area of ubiquitous computing. They are starting to achieve mass adoption in people's everyday life. Moving objects can be tracked with navigation and orientation sensors such as GPS devices or RFID tags. Their movements can be represented as sequences of time-stamped locations. Studying such spatiotemporal movement series to discover spatial sequential patterns holds promises in many real-world settings. A few interesting applications of such kind are vehicle travel pattern discovery and travel route prediction, or customer shopping traverse pattern discovery. Traditional spatial data mining methods suitable in Euclidean space are not directly applicable for these sequential settings. We propose a Longest Common Subsequence (LCS)-based algorithm to cluster movement trajectories for travel pattern discovery. Experiments are performed on a GPS trace dataset of vehicle travel trajectories in Athens, Greece. We visualize the clustering results and compare them with a baseline outcome using Google Earth. The evaluation results show that the proposed LCS-based approach can be used to support effective pattern discovery for moving object travel trajectories.

Original languageEnglish (US)
Title of host publication15th Americas Conference on Information Systems 2009, AMCIS 2009
Pages394-401
Number of pages8
StatePublished - Dec 1 2009
Event15th Americas Conference on Information Systems 2009, AMCIS 2009 - San Francisco, CA, United States
Duration: Aug 6 2009Aug 9 2009

Publication series

Name15th Americas Conference on Information Systems 2009, AMCIS 2009
Volume1

Other

Other15th Americas Conference on Information Systems 2009, AMCIS 2009
CountryUnited States
CitySan Francisco, CA
Period8/6/098/9/09

Keywords

  • Clustering
  • LCS algorithm
  • Movement tracking
  • Pattern discovery
  • Ubiquitous computing

ASJC Scopus subject areas

  • Computer Science Applications
  • Computer Networks and Communications
  • Information Systems
  • Library and Information Sciences

Fingerprint Dive into the research topics of 'Spatial movement pattern discovery with LCS-based path similarity measure'. Together they form a unique fingerprint.

  • Cite this

    Yan, P., & Zeng, D. D. (2009). Spatial movement pattern discovery with LCS-based path similarity measure. In 15th Americas Conference on Information Systems 2009, AMCIS 2009 (pp. 394-401). (15th Americas Conference on Information Systems 2009, AMCIS 2009; Vol. 1).