Measuring similarity between trajectories of mobile objects

Sigal Elnekave, Mark Last, Oded Maimon

Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review

6 Scopus citations

Abstract

With technological progress we encounter more available data on the locations of moving objects and therefore the need for mining moving objects data is constantly growing. Mining spatio-temporal data can direct products and services to the right customers at the right time; it can also be used for resources optimization or for understanding mobile patterns. In this chapter, we cluster trajectories in order to find movement patterns of mobile objects. We use a compact representation of a mobile trajectory, which is based on a list of minimal bounding boxes (MBBs). We introduce a new similarity measure between mobile trajectories and compare it empirically to an existing similarity measure by clustering spatio-temporal data and evaluating the quality of resulting clusters and the algorithm run times.

Original languageEnglish
Title of host publicationApplied Pattern Recognition
EditorsHorst Bunke, Abraham Kandel, Mark Last
Pages101-128
Number of pages28
DOIs
StatePublished - 13 Mar 2008

Publication series

NameStudies in Computational Intelligence
Volume91
ISSN (Print)1860-949X

ASJC Scopus subject areas

  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Measuring similarity between trajectories of mobile objects'. Together they form a unique fingerprint.

Cite this