The aim of this diploma thesis is a detail description of current possibilities and ways of storing open data. It focuses on tools and database systems used for storing linked open data as well as on the selection of such systems for subsequent analysis and comparison. The practical part of the thesis then focuses on the comparison of selected systems based on a selected use case. This thesis introduces the fundamental terms and concepts concerning linked open data. Besides that, various approaches and formats for storing linked open data (namely file ori-ented approaches and database approaches) are analyzed. . The thesis also focuses on the RDF format and database systems. Ten triplestore database solutions (solutions for storing data in the RDF format) are introduced and described briefly. Out of these, three are cho-sen for a detailed analysis by which they are compared with one another and with a rela-tional database system. The core of the detail analysis lies in performance benchmarks. Ex-isting performance oriented benchmarks of triplestore systems are described and analyzed. In addition to that, the thesis introduces a newly developed benchmark as a collection of database queries. The benchmark is then used for the performance testing. The following systems have been tested: Apache Jena TDB/Fuseki, OpenLink Virtuoso, Oracle Spatial and Graph a Microsoft SQL Server. The main contribution of this thesis consists in a comprehensive presentation of current possibilities of storing linked open data.

No description available.

La thèse défendue dans ce manuscrit s'intéresse à la simulation multi-agents appliquée à la simulation d'individus dans des bâtiments 3D virtuels.Pour ce faire, nos travaux proposent de capitaliser l'expérience acquise dans le domaine du web sémantique sur les ontologies et les moteurs d'inférence associés pour faciliter la conception et le développement de comportements intelligents pour des agents évoluant dans des univers virtuels.L'objectif est de fournir aux agents une approche générique pour gérer leur représentation du monde et raisonner sur cette représentation.Pour cela, la problématique centrale repose sur la définition d'une ontologie décidable modélisant l'ensemble des connaissances contenues dans l'environnement virtuel 3D pour enrichir sémantiquement l'environnement d'une simulation multi-agents.Cette ontologie décidable a pour but d'offrir la possibilité d'intégrer les moteurs d'inférence sémantique au c\oe{}ur de la modélisation de comportements d'agents mobiles dans un environnement virtuel. / This thesis focuses on multi-agent simulation applied to the simulation of individuals in virtual 3D buildings. To do this, our work suggests to capitalize on the experience gained in the field of semantic web ontologies and inference engines to facilitate the design and development of intelligent behavior for agents operating in virtual worlds. The goal is to provide to agents a generic approach to managing their representation of the world and reason about this representation. For this, the central problem is based on the definition of a decidable ontology modeling all of the knowledge contained in the virtual 3D environment to enrich semantically the environment of a multi-agent simulation. This decidable ontology aims to provide an opportunity to integrate semantic inference engine at the heart of modeling behavior of mobile agents in a virtual environment.