% IMPORTANT: The following is UTF-8 encoded.  This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.

@INPROCEEDINGS{Gtz:276347,
      author       = {Götz, Markus and Bodenstein, Christian and Riedel, Morris},
      title        = {{HPDBSCAN} - {H}ighly parallel {DBSCAN}},
      publisher    = {ACM Press New York, New York, USA},
      reportid     = {FZJ-2015-06807},
      isbn         = {978-1-4503-4006-9},
      pages        = {2},
      year         = {2015},
      comment      = {Proceedings of the Workshop on Machine Learning in
                      High-Performance Computing Environments - MLHPC '15},
      booktitle     = {Proceedings of the Workshop on Machine
                       Learning in High-Performance Computing
                       Environments - MLHPC '15},
      abstract     = {Clustering algorithms in the field of data-mining are used
                      to aggregate similar objects into common groups. One of the
                      best-known of these algorithms is called DBSCAN. Its
                      distinct design enables the search for an apriori unknown
                      number of arbitrarily shaped clusters, and at the same time
                      allows to filter out noise. Due to its sequential
                      formulation, the parallelization of DBSCAN renders a
                      challenge. In this paper we present a new parallel approach
                      which we call HPDBSCAN. It employs three major techniques in
                      order to break the sequentiality, empower workload-balancing
                      as well as speed up neighborhood searches in distributed
                      parallel processing environments i) a computation split
                      heuristic for domain decomposition, ii) a data index
                      preprocessing step and iii) a rule-based cluster merging
                      scheme.As a proof-of-concept we implemented HPDBSCAN as an
                      OpenMP/MPI hybrid application. Using real-world data sets,
                      such as a point cloud from the old town of Bremen, Germany,
                      we demonstrate that our implementation is able to achieve a
                      significant speed-up and scale-up in common HPC setups.
                      Moreover, we compare our approach with previous attempts to
                      parallelize DBSCAN showing an order of magnitude improvement
                      in terms of computation time and memory consumption.},
      month         = {Nov},
      date          = {2015-11-15},
      organization  = {Workshop Workshop on Machine Learning
                       in High-Performance Computing
                       Environments, subworkshop to
                       Supercomputing 2015, Austin (Texas), 15
                       Nov 2015 - 15 Nov 2015},
      cin          = {JSC},
      cid          = {I:(DE-Juel1)JSC-20090406},
      pnm          = {512 - Data-Intensive Science and Federated Computing
                      (POF3-512)},
      pid          = {G:(DE-HGF)POF3-512},
      typ          = {PUB:(DE-HGF)8},
      doi          = {10.1145/2834892.2834894},
      url          = {https://juser.fz-juelich.de/record/276347},
}