% 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”.
@ARTICLE{Rybicki:842150,
author = {Rybicki, Jedrzej and von St. Vieth, Benedikt},
title = {{A} {F}ramework for {R}eproducible {E}valuation of
{S}emantic {S}torage {O}ptions},
journal = {International Journal on Advances in
Software[[Elektronische Ressource]]},
volume = {10},
number = {$3\&4$},
issn = {1942-2628},
address = {[S.l.]},
publisher = {IARIA},
reportid = {FZJ-2018-00424},
pages = {345-354},
year = {2017},
abstract = {spite the urgent need to conduct computer-driven
experiments in a reproducible fashion, there is no
widely-accepted, established approach to this problem. The
rise of Open Data surely helps in understanding and
verifying some of the research findings, but the true
verification comes from a means to reproduce the original
tests. This paper proposes a framework for conducting such
reproducible experiments. It leverages Docker to facilitate
exchange of, not just source code used in test trails but
rather whole, ready-to-run experimental environments. The
lightweight virtualization provided by Docker makes it very
portable across a wide variety of hardware and software
platforms. We explain the framework in detail, discuss its
advantages as well as shortcomings, and assess how
future-proof it is. The usability of the proposed framework
was verified by conducting a reproducible evaluation of the
possible storage options for semantic annotations. This use
case emerged in the context of a particular distributed
infrastructure, where users requested a possibility to
annotate stored digital objects. There are many possible
technologies that can be used to store semantic annotations.
We evaluated performance and suitability of relational
databases, document stores, and graph databases, to conclude
that the graph database is the best candidate to efficiently
handle the task. Although, it has also some limitations,
which we will point out. By using the proposed framework in
the aforementioned evaluation, we enable other researchers
to repeat it, but also benchmark alternative technologies if
required. Furthermore, the framework can be reused in an
iterative process of performance tuning of the selected
storage option, to quantify and verify the influence of
particular configuration changes. The main output of this
paper is a framework which allows to easily redo the
evaluation of semantic storage options.},
cin = {JSC},
ddc = {004},
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)16},
url = {https://juser.fz-juelich.de/record/842150},
}