Building representative velocity profiles using FastDTW and spectral clustering

Jürgen Lohrer, Markus Lienkamp

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

10 Scopus citations

Abstract

The use of map based representative velocity profiles allows to predict the future state of a vehicle. The suggested approach is based on Fast Dynamic Time Warping. Spectral clustering is used to distinguish velocity profiles. Applying abstraction can significantly reduce computation time with a minor effect on cluster allocation. Outlier removal increases the quality of cluster identification. The approach was applied to the road network of Munich, to prove the universal applicability.

Original languageEnglish
Title of host publication2015 14th International Conference on ITS Telecommunications, ITST 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages45-49
Number of pages5
ISBN (Electronic)9781467393829
DOIs
StatePublished - 8 Jan 2016
Event14th International Conference on ITS Telecommunications, ITST 2015 - Copenhagen, Denmark
Duration: 2 Dec 20154 Dec 2015

Publication series

Name2015 14th International Conference on ITS Telecommunications, ITST 2015

Conference

Conference14th International Conference on ITS Telecommunications, ITST 2015
Country/TerritoryDenmark
CityCopenhagen
Period2/12/154/12/15

Keywords

  • Fast Dynamic Time Warping
  • Spectral Clustering
  • Speed Profiles
  • Time Series Classification

Fingerprint

Dive into the research topics of 'Building representative velocity profiles using FastDTW and spectral clustering'. Together they form a unique fingerprint.

Cite this