% 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{Memon:865715,
author = {Memon, Mohammad Shahbaz},
title = {{S}tandards-based {M}odels and {A}rchitectures to
{A}utomate {S}calable and {D}istributed {D}ata {P}rocessing
and {A}nalysis},
school = {University of Iceland},
type = {Dissertation},
reportid = {FZJ-2019-05050},
pages = {102 pp.},
year = {2019},
note = {Dissertation, University of Iceland, 2019},
abstract = {Scientific communities engaging in big data analysis face
numerous challenges in managing complex computations and the
related data on emerging and distributed computing
infrastructures. Large-scale data analysis requires
applications with simplified access to multiple resource
management systems. Several generic or domain-specific
technologies have been developed to exploit diversified
computing environments, but due to the heterogeneity of
computing and data architectures they are not capable of
enabling real science cases. Scientific gateways and
workflows are one such example which requires the management
of jobs on multiple kinds of batch systems using
heterogeneous supercomputing architectures and access to
advanced distributed file systems. To support these
requirements, a unified architectural framework is presented
in this dissertation that coalesces the right combination of
standards and adequate middleware realisation. This
framework manages concurrent access for diversified user
communities through consistent and robust computing and data
interfaces oriented to current application and
infrastructure demands. The investigations reported in this
dissertation were mainly motivated by physical and
machine-learning models, represented by two scientific case
studies: biophysics and Earth sciences. In the field of
biophysics, the UltraScan scientific gateway is enhanced to
enable the processing of domain-specific data through
standards-based job and data management interfaces in HPC
environments. The second domain deals with Earth sciences
and automates the processing of machine-learning algorithms
(e.g. classification of remote sensing images) using
scalable and parallel implementations. As proof of concept,
both the case studies are supported through open source
implementations, in the form of middleware realisation,
client APIs and their integration with state-of-the-art
science gateway frameworks.},
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)11},
url = {https://juser.fz-juelich.de/record/865715},
}