% 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”.

@PHDTHESIS{Gtz:841390,
      author       = {Götz, Markus},
      title        = {{S}calable {D}ata {A}nalysis in {H}igh {P}erformance
                      {C}omputing},
      school       = {Universität Island},
      type         = {Dissertation},
      address      = {Reykjavik},
      publisher    = {Háskólaprent, Universität Island},
      reportid     = {FZJ-2017-08465},
      isbn         = {978-9935-9383-2-9},
      pages        = {156 p.},
      year         = {2017},
      note         = {Dissertation, Universität Island, 2017},
      abstract     = {Over the last decades one could observe a drastic increase
                      in the generation and storage of data in both, industry and
                      science. While the field of data analysis is not new, it is
                      now facing the challenge of coping with an increasing size,
                      bandwidth and complexity of data. This renders traditional
                      analysis methods and algorithms ineffective. This problem
                      has been coined as the Big Data challenge. Concretely in
                      science the major data producers are large-scale monolithic
                      experiments and the outputs of domain simulations. Up until
                      now, most of this data has not yet been completely analyzed,
                      but rather stored in data repositories for later
                      consideration due to the lack of efficient means of
                      processing. As a consequence, there is a need for
                      large-scale data analysis frameworks and algorithm libraries
                      allowing to study these datasets. In context of scientific
                      applications, potentially coupled with legacy simulations,
                      the designated target platform are heterogeneous
                      high-performance computing systems.This thesis proposes a
                      design and prototypical realization of such a framework
                      based on the experience collected from empirical
                      applications. For this, selected scientific use cases, with
                      an emphasis on earth sciences, were studied. In particular,
                      these are object segmentation in point cloud data and
                      biological imagery, outlier detection in oceanographic
                      time-series data as well as land cover type classification
                      in remote sensing images. In order to deal with the data
                      amounts, two analysis algorithms have been parallelized for
                      shared- and distributed-memory systems. Concretely, these
                      are HPDBSCAN, a density-based clustering algorithm, as well
                      as Distributed Max-Trees, a filtering step for images. The
                      presented parallelization strategies have been abstracted
                      into a generalized paradigm, enabling the formulation of
                      scalable algorithms for other similar analysis methods.
                      Moreover, it permits the definition of requirements for the
                      design of a large-scale data analysis framework and
                      algorithm library for heterogeneous, distributed
                      high-performance computing systems. In line with that, the
                      thesis presents a prototypical realization called Juelich
                      Machine Learning Library (JuML), providing essential
                      low-level components and readily usable analysis algorithm
                      implementations.},
      cin          = {JSC},
      cid          = {I:(DE-Juel1)JSC-20090406},
      pnm          = {512 - Data-Intensive Science and Federated Computing
                      (POF3-512) / PhD no Grant - Doktorand ohne besondere
                      Förderung (PHD-NO-GRANT-20170405)},
      pid          = {G:(DE-HGF)POF3-512 / G:(DE-Juel1)PHD-NO-GRANT-20170405},
      typ          = {PUB:(DE-HGF)3 / PUB:(DE-HGF)11},
      url          = {https://juser.fz-juelich.de/record/841390},
}