% 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{Riedel:276330,
      author       = {Riedel, Morris and Goetz, M. and Richerzhagen, M. and
                      Glock, P. and Bodenstein, C. and Memon, Ahmed and Memon,
                      Mohammad Shahbaz},
      title        = {{S}calable and parallel machine learning algorithms for
                      statistical data mining - {P}ractice $\&$ experience},
      publisher    = {IEEE},
      reportid     = {FZJ-2015-06790},
      pages        = {204 - 209},
      year         = {2015},
      comment      = {2015 38th International Convention on Information and
                      Communication Technology, Electronics and Microelectronics
                      (MIPRO) : [Proceedings] - IEEE, 2015. - ISBN
                      978-9-5323-3082-3 -},
      booktitle     = {2015 38th International Convention on
                       Information and Communication
                       Technology, Electronics and
                       Microelectronics (MIPRO) :
                       [Proceedings] - IEEE, 2015. - ISBN
                       978-9-5323-3082-3 -},
      abstract     = {Many scientific datasets (e.g. earth sciences, medical
                      sciences, etc.) increase with respect to their volume or in
                      terms of their dimensions due to the ever increasing quality
                      of measurement devices. This contribution will specifically
                      focus on how these datasets can take advantage of new `big
                      data' technologies and frameworks that often are based on
                      parallelization methods. Lessons learned with medical and
                      earth science data applications that require parallel
                      clustering and classification techniques such as support
                      vector machines (SVMs) and density-based spatial clustering
                      of applications with noise (DBSCAN) are a substantial part
                      of the contribution. In addition, selected experiences of
                      related `big data' approaches and concrete mining techniques
                      (e.g. dimensionality reduction, feature selection, and
                      extraction methods) will be addressed too. In order to
                      overcome identified challenges, we outline an architecture
                      framework design that we implement with open available tools
                      in order to enable scalable and parallel machine learning
                      applications in distributed systems.},
      month         = {May},
      date          = {2015-05-25},
      organization  = {38th International Convention on
                       Information and Communication
                       Technology, Electronics and
                       Microelectronics, Opatija (Croatia), 25
                       May 2015 - 29 May 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          = {10.1109/MIPRO.2015.7160265},
      url          = {https://juser.fz-juelich.de/record/276330},
}