Building representative velocity profiles using FastDTW and spectral clustering

Jürgen Lohrer, Markus Lienkamp

Publikation: Beitrag in Buch/Bericht/KonferenzbandKonferenzbeitragBegutachtung

10 Zitate (Scopus)

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.

OriginalspracheEnglisch
Titel2015 14th International Conference on ITS Telecommunications, ITST 2015
Herausgeber (Verlag)Institute of Electrical and Electronics Engineers Inc.
Seiten45-49
Seitenumfang5
ISBN (elektronisch)9781467393829
DOIs
PublikationsstatusVeröffentlicht - 8 Jan. 2016
Veranstaltung14th International Conference on ITS Telecommunications, ITST 2015 - Copenhagen, Dänemark
Dauer: 2 Dez. 20154 Dez. 2015

Publikationsreihe

Name2015 14th International Conference on ITS Telecommunications, ITST 2015

Konferenz

Konferenz14th International Conference on ITS Telecommunications, ITST 2015
Land/GebietDänemark
OrtCopenhagen
Zeitraum2/12/154/12/15

Fingerprint

Untersuchen Sie die Forschungsthemen von „Building representative velocity profiles using FastDTW and spectral clustering“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren