License: Creative Commons Attribution 3.0 Unported license (CC BY 3.0)
When quoting this document, please refer to the following
DOI: 10.4230/LIPIcs.ISAAC.2017.25
URN: urn:nbn:de:0030-drops-82102
Go to the corresponding LIPIcs Volume Portal

de Berg, Mark ; Gunawan, Ade ; Roeloffzen, Marcel

Faster DBScan and HDBScan in Low-Dimensional Euclidean Spaces

LIPIcs-ISAAC-2017-25.pdf (0.6 MB)


We present a new algorithm for the widely used density-based clustering method DBScan. Our algorithm computes the DBScan-clustering in O(n log n) time in R^2, irrespective of the scale parameter \eps, but assuming the second parameter MinPts is set to a fixed constant, as is the case in practice.
We also present an O(n log n) randomized algorithm for HDBScan in the plane---HDBScans is a hierarchical version of DBScan introduced recently---and we show how to compute an approximate version of HDBScan in near-linear time in any fixed dimension.

BibTeX - Entry

  author =	{Mark de Berg and Ade Gunawan and Marcel Roeloffzen},
  title =	{{Faster DBScan and HDBScan in Low-Dimensional Euclidean Spaces}},
  booktitle =	{28th International Symposium on Algorithms and Computation (ISAAC 2017)},
  pages =	{25:1--25:13},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-054-5},
  ISSN =	{1868-8969},
  year =	{2017},
  volume =	{92},
  editor =	{Yoshio Okamoto and Takeshi Tokuyama},
  publisher =	{Schloss Dagstuhl--Leibniz-Zentrum fuer Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{},
  URN =		{urn:nbn:de:0030-drops-82102},
  doi =		{10.4230/LIPIcs.ISAAC.2017.25},
  annote =	{Keywords: Density-based clustering, hierarchical clustering}

Keywords: Density-based clustering, hierarchical clustering
Collection: 28th International Symposium on Algorithms and Computation (ISAAC 2017)
Issue Date: 2017
Date of publication: 07.12.2017

DROPS-Home | Fulltext Search | Imprint | Privacy Published by LZI