var bibbase_data = {"data":"\"Loading..\"\n\n
\n\n \n\n \n\n \n \n\n \n\n \n \n\n \n\n \n
\n generated by\n \n \"bibbase.org\"\n\n \n
\n \n\n
\n\n \n\n\n
\n\n Excellent! Next you can\n create a new website with this list, or\n embed it in an existing web page by copying & pasting\n any of the following snippets.\n\n
\n JavaScript\n (easiest)\n
\n \n <script src=\"https://bibbase.org/show?bib=https://raw.githubusercontent.com/GezimSejdiu/gezimsejdiu.github.io/master/publications.bib&jsonp=1&fullnames=1&theme=side&jsonp=1\"></script>\n \n
\n\n PHP\n
\n \n <?php\n $contents = file_get_contents(\"https://bibbase.org/show?bib=https://raw.githubusercontent.com/GezimSejdiu/gezimsejdiu.github.io/master/publications.bib&jsonp=1&fullnames=1&theme=side\");\n print_r($contents);\n ?>\n \n
\n\n iFrame\n (not recommended)\n
\n \n <iframe src=\"https://bibbase.org/show?bib=https://raw.githubusercontent.com/GezimSejdiu/gezimsejdiu.github.io/master/publications.bib&jsonp=1&fullnames=1&theme=side\"></iframe>\n \n
\n\n

\n For more details see the documention.\n

\n
\n
\n\n
\n\n This is a preview! To use this list on your own web site\n or create a new web site from it,\n create a free account. The file will be added\n and you will be able to edit it in the File Manager.\n We will show you instructions once you've created your account.\n
\n\n
\n\n

To the site owner:

\n\n

Action required! Mendeley is changing its\n API. In order to keep using Mendeley with BibBase past April\n 14th, you need to:\n

    \n
  1. renew the authorization for BibBase on Mendeley, and
    2. \n
  2. update the BibBase URL\n in your page the same way you did when you initially set up\n this page.\n
    3. \n
\n

\n\n

\n \n \n Fix it now\n

\n
\n\n
\n\n\n
\n \n \n
\n
\n  \n 2022\n \n \n (1)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n Efficient semantic summary graphs for querying large knowledge graphs.\n \n \n \n \n\n\n \n Emetis Niazmand; Gezim Sejdiu; Damien Graux; and Maria-Esther Vidal.\n\n\n \n\n\n\n International Journal of Information Management Data Insights, 2(1): 100082. 2022.\n \n\n\n\n
\n\n\n\n \n \n \"EfficientPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n  \n \n 5 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n 
@article{NIAZMAND2022100082,\ntitle = {Efficient semantic summary graphs for querying large knowledge graphs},\njournal = {International Journal of Information Management Data Insights},\nvolume = {2},\nnumber = {1},\npages = {100082},\nyear = {2022},\nissn = {2667-0968},\ndoi = {https://doi.org/10.1016/j.jjimei.2022.100082},\nurl = {https://www.sciencedirect.com/science/article/pii/S2667096822000258},\nauthor = {Emetis Niazmand and Gezim Sejdiu and Damien Graux and Maria-Esther Vidal},\nkeywords = {Knowledge graph, Summarization graph, SPARQL evaluation, Embedding model, Distributed context},\nabstract = {Knowledge Graphs (KGs) integrate heterogeneous data, but one challenge is the development of efficient tools for allowing end users to extract useful insights from these sources of knowledge. In such a context, reducing the size of a Resource Description Framework (RDF) graph while preserving all information can speed up query engines by limiting data shuffle, especially in a distributed setting. This paper presents two algorithms for RDF graph summarization: Grouping Based Summarization (GBS) and Query Based Summarization (QBS). The latter is an optimized and lossless approach for the former method. We empirically study the effectiveness of the proposed lossless RDF graph summarization to retrieve complete data, by rewriting an RDF Query Language called SPARQL query with fewer triple patterns using a semantic similarity. We conduct our experimental study in instances of four datasets with different sizes. Compared with the state-of-the-art query engine Sparklify executed over the original RDF graphs as a baseline, QBS query execution time is reduced by up to 80% and the summarized RDF graph is decreased by up to 99%.}\n}
\n
\n\n\n
\n Knowledge Graphs (KGs) integrate heterogeneous data, but one challenge is the development of efficient tools for allowing end users to extract useful insights from these sources of knowledge. In such a context, reducing the size of a Resource Description Framework (RDF) graph while preserving all information can speed up query engines by limiting data shuffle, especially in a distributed setting. This paper presents two algorithms for RDF graph summarization: Grouping Based Summarization (GBS) and Query Based Summarization (QBS). The latter is an optimized and lossless approach for the former method. We empirically study the effectiveness of the proposed lossless RDF graph summarization to retrieve complete data, by rewriting an RDF Query Language called SPARQL query with fewer triple patterns using a semantic similarity. We conduct our experimental study in instances of four datasets with different sizes. Compared with the state-of-the-art query engine Sparklify executed over the original RDF graphs as a baseline, QBS query execution time is reduced by up to 80% and the summarized RDF graph is decreased by up to 99%.\n
\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2020\n \n \n (4)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n Efficient Distributed In-Memory Processing of RDF Datasets.\n \n \n \n \n\n\n \n Gezim Sejdiu.\n\n\n \n\n\n\n Ph.D. Thesis, Rheinische Friedrich-Wilhelms-Universität Bonn, 2020.\n \n\n\n\n
\n\n\n\n \n \n \"EfficientPaper\n  \n \n \n \"EfficientSlides\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n  \n \n 34 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@PhDThesis{gezim-sejdiu-2020-phd-thesis,\n  Author                   = {{Gezim Sejdiu}},\n  Title                    = {Efficient {D}istributed {I}n-{M}emory {P}rocessing of {RDF D}atasets},\n  School                   = {Rheinische Friedrich-Wilhelms-Universität Bonn},\n  Year                     = 2020,\n  Abstract                 = {Over the past decade, vast amounts of machine-readable structured information have become available through the automation of research processes as well as the increasing popularity of knowledge graphs and semantic technologies. Today, we count more than 10,000 datasets made available online following Semantic Web standards. A major and yet unsolved challenge that research faces today is to perform scalable analysis of large-scale knowledge graphs in order to facilitate applications in various domains including life sciences, publishing, and the internet of things. The main objective of this thesis is to lay foundations for efficient algorithms performing analytics, i.e. exploration, quality assessment, and querying over semantic knowledge graphs at a scale that has not been possible before. First, we propose a novel approach for statistical calculations of large RDF datasets, which scales out to clusters of machines. In particular, we describe the first distributed in-memory approach for computing 32 different statistical criteria for RDF datasets using Apache Spark. Many applications such as data integration, search, and interlinking, may take full advantage of the data when having a priori statistical information about its internal structure and coverage. However, such applications may suffer from low quality and not being able to leverage the full advantage of the data when the size of data goes beyond the capacity of the resources available. Thus, we introduce a distributed approach of quality assessment of large RDF datasets. It is the first distributed, in-memory approach for computing different quality metrics for large RDF datasets using Apache Spark. We also provide a quality assessment pattern that can be used to generate new scalable metrics that can be applied to big data. Based on the knowledge of the internal statistics of a dataset and its quality, users typically want to query and retrieve large amounts of information. As a result, it has become difficult to efficiently process these large RDF datasets. Indeed, these processes require, both efficient storage strategies and query-processing engines, to be able to scale in terms of data size. Therefore, we propose a scalable approach to evaluate SPARQL queries over distributed RDF datasets by translating SPARQL queries into Spark executable code. We conducted several empirical evaluations to assess the scalability, effectiveness, and efficiency of our proposed approaches. More importantly, various use cases i.e. Ethereum analysis, Mining Big Data Logs, and Scalable Integration of POIs, have been developed and leverages by our approach. The empirical evaluations and concrete applications provide evidence that our methodology and techniques proposed during this thesis help to effectively analyze and process large-scale RDF datasets. All the proposed approaches during this thesis are integrated into the larger SANSA framework.},\n  Url                      = {http://hdl.handle.net/20.500.11811/8735},\n  UrlSlides                = {https://www.slideshare.net/GezimSejdiu/efficient-distributed-inmemory-processing-of-rdf-datasets-phd-viva}\n}\n\n
\n
\n\n\n
\n Over the past decade, vast amounts of machine-readable structured information have become available through the automation of research processes as well as the increasing popularity of knowledge graphs and semantic technologies. Today, we count more than 10,000 datasets made available online following Semantic Web standards. A major and yet unsolved challenge that research faces today is to perform scalable analysis of large-scale knowledge graphs in order to facilitate applications in various domains including life sciences, publishing, and the internet of things. The main objective of this thesis is to lay foundations for efficient algorithms performing analytics, i.e. exploration, quality assessment, and querying over semantic knowledge graphs at a scale that has not been possible before. First, we propose a novel approach for statistical calculations of large RDF datasets, which scales out to clusters of machines. In particular, we describe the first distributed in-memory approach for computing 32 different statistical criteria for RDF datasets using Apache Spark. Many applications such as data integration, search, and interlinking, may take full advantage of the data when having a priori statistical information about its internal structure and coverage. However, such applications may suffer from low quality and not being able to leverage the full advantage of the data when the size of data goes beyond the capacity of the resources available. Thus, we introduce a distributed approach of quality assessment of large RDF datasets. It is the first distributed, in-memory approach for computing different quality metrics for large RDF datasets using Apache Spark. We also provide a quality assessment pattern that can be used to generate new scalable metrics that can be applied to big data. Based on the knowledge of the internal statistics of a dataset and its quality, users typically want to query and retrieve large amounts of information. As a result, it has become difficult to efficiently process these large RDF datasets. Indeed, these processes require, both efficient storage strategies and query-processing engines, to be able to scale in terms of data size. Therefore, we propose a scalable approach to evaluate SPARQL queries over distributed RDF datasets by translating SPARQL queries into Spark executable code. We conducted several empirical evaluations to assess the scalability, effectiveness, and efficiency of our proposed approaches. More importantly, various use cases i.e. Ethereum analysis, Mining Big Data Logs, and Scalable Integration of POIs, have been developed and leverages by our approach. The empirical evaluations and concrete applications provide evidence that our methodology and techniques proposed during this thesis help to effectively analyze and process large-scale RDF datasets. All the proposed approaches during this thesis are integrated into the larger SANSA framework.\n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n MINDS: a translator to embed mathematical expressions inside SPARQL queries.\n \n \n \n \n\n\n \n Damien Graux; Gezim Sejdiu; Claus Stadler; Giulio Napolitano; and Jens Lehmann.\n\n\n \n\n\n\n In 16th International Conference on Semantic Systems (SEMANTiCS), 2020. \n \n\n\n\n
\n\n\n\n \n \n \"MINDS:Paper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@InProceedings{graux-2020-minds-semantics,\n  Title                    = {{MINDS}: a translator to embed mathematical expressions inside {SPARQL} queries},\n  Author                   = {Damien Graux and Gezim Sejdiu and Claus Stadler and Giulio Napolitano and Jens Lehmann},\n  Booktitle                = {16th International Conference on Semantic Systems (SEMANTiCS)},\n  Year                     = {2020},\n  Url                      = {https://dgraux.github.io/publications/MINDS_Semantics_2020.pdf}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n DISE: A Distributed in-Memory SPARQL Processing Engine over Tensor Data.\n \n \n \n \n\n\n \n Hajira Jabeen; Eskender Haziiev; Gezim Sejdiu; and Jens Lehmann.\n\n\n \n\n\n\n In 14th IEEE International Conference on Semantic Computing (ICSC'20), 2020. \n \n\n\n\n
\n\n\n\n \n \n \"DISE:Paper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 10 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n\n\n\n
\n 
@InProceedings{2020-sansa-dise-icsc-resource,\n  Title                    = {{DISE}: {A D}istributed in-{M}emory {SPARQL P}rocessing {E}ngine over {T}ensor {D}ata},\n  Author                   = {Hajira Jabeen and Eskender Haziiev and Gezim Sejdiu and Jens Lehmann},\n  Booktitle                = {14th IEEE International Conference on Semantic Computing (ICSC'20)},\n  Year                     = {2020},\n  Keywords                 = {2020 sansa jabeen sejdiu lehmann group_sda},\n  Url                      = {http://jens-lehmann.org/files/2020/icsc_dise.pdf}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Scalable Knowledge Graph Processing Using SANSA.\n \n \n \n \n\n\n \n Hajira Jabeen; Damien Graux; and Gezim Sejdiu.\n\n\n \n\n\n\n In Valentina Janev; Damien Graux; Hajira Jabeen; and Emanuel Sallinger., editor(s), Knowledge Graphs and Big Data Processing, pages 105–121. Springer International Publishing, Cham, 2020.\n \n\n\n\n
\n\n\n\n \n \n \"ScalablePaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n  \n \n 6 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@InCollection{Jabeen2020Chapter7-SANSA-LAMBDA,\n  Title                    = {Scalable {K}nowledge {G}raph {P}rocessing {U}sing {SANSA}},\n  Author                   = {Hajira Jabeen and Damien Graux and Gezim Sejdiu},\n  Editor                   = {Valentina Janev and Damien Graux and Hajira Jabeen and Emanuel Sallinger},\n  Pages                    = {105--121},\n  Publisher                = {Springer International Publishing},\n\n  Year                     = {2020},\n\n  Address                  = {Cham},\n\n  Abstract                 = {The size and number of knowledge graphs have increased tremendously in recent years. In the meantime, the distributed data processing technologies have also advanced to deal with big data and large scale knowledge graphs. This chapter introduces Scalable Semantic Analytics Stack (SANSA), that addresses the challenge of dealing with large scale RDF data and provides a unified framework for applications like link prediction, knowledge base completion, querying, and reasoning. We discuss the motivation, background and the architecture of SANSA. SANSA is built using general-purpose processing engines Apache Spark and Apache Flink. After reading this chapter, the reader should have an understanding of the different layers and corresponding APIs available to handle Knowledge Graphs at scale using SANSA.},\n  Booktitle                = {Knowledge Graphs and Big Data Processing},\n  Doi                      = {10.1007/978-3-030-53199-7_7},\n  ISBN                     = {978-3-030-53199-7},\n  Url                      = {https://doi.org/10.1007/978-3-030-53199-7_7}\n}\n\n
\n
\n\n\n
\n The size and number of knowledge graphs have increased tremendously in recent years. In the meantime, the distributed data processing technologies have also advanced to deal with big data and large scale knowledge graphs. This chapter introduces Scalable Semantic Analytics Stack (SANSA), that addresses the challenge of dealing with large scale RDF data and provides a unified framework for applications like link prediction, knowledge base completion, querying, and reasoning. We discuss the motivation, background and the architecture of SANSA. SANSA is built using general-purpose processing engines Apache Spark and Apache Flink. After reading this chapter, the reader should have an understanding of the different layers and corresponding APIs available to handle Knowledge Graphs at scale using SANSA.\n
\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2019\n \n \n (8)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n Querying large-scale RDF datasets using the SANSA framework.\n \n \n \n \n\n\n \n Claus Stadler; Gezim Sejdiu; Damien Graux; and Jens Lehmann.\n\n\n \n\n\n\n In Proceedings of 18th International Semantic Web Conference (ISWC), Poster & Demos, 2019. \n \n\n\n\n
\n\n\n\n \n \n \"QueryingPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 2 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n\n\n\n
\n 
@InProceedings{sansa-sparklify-ISWC-demo,\n  Title                    = {Querying large-scale {RDF} datasets using the {SANSA} framework},\n  Author                   = {Claus Stadler and Gezim Sejdiu and Damien Graux and Jens Lehmann},\n  Booktitle                = {Proceedings of 18th International Semantic Web Conference (ISWC), Poster \\& Demos},\n  Year                     = {2019},\n  Keywords                 = {2019 sansa dsa stadler sejdiu graux lehmann sda},\n  Url                      = {https://gezimsejdiu.github.io/publications/sansa-sparklify-ISWC-demo.pdf}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n The Hubs and Authorities Transaction NetworkAnalysis using the SANSA framework.\n \n \n \n \n\n\n \n Danning Sui; Gezim Sejdiu; Damien Graux; and Jens Lehmann.\n\n\n \n\n\n\n In 15th International Conference on Semantic Systems (SEMANTiCS), Poster & Demos, 2019. \n \n\n\n\n
\n\n\n\n \n \n \"ThePaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n\n\n\n
\n 
@InProceedings{sansa-hubs-and-authorities-transaction-semantics19-poster,\n  Title                    = {The {H}ubs and {A}uthorities {T}ransaction {N}etwork{A}nalysis using the {SANSA} framework},\n  Author                   = {Danning Sui and Gezim Sejdiu and Damien Graux and Jens Lehmann},\n  Booktitle                = {15th International Conference on Semantic Systems (SEMANTiCS), Poster \\& Demos},\n  Year                     = {2019},\n  Keywords                 = {2019 sansa dsa sejdiu graux lehmann sda},\n  Url                      = {https://gezimsejdiu.github.io/publications/sansa-hubs-and-authorities-transaction-semantics19-poster.pdf}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n A Scalable Framework for Quality Assessment of RDF Datasets.\n \n \n \n \n\n\n \n Gezim Sejdiu; Anisa Rula; Jens Lehmann; and Hajira Jabeen.\n\n\n \n\n\n\n In Proceedings of 18th International Semantic Web Conference, 2019. \n \n\n\n\n
\n\n\n\n \n \n \"APaper\n  \n \n \n \"ASlides\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 4 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n\n\n\n
\n 
@InProceedings{sejdiu-2019-sansa-dist-quality-assessment-iswc,\n  Title                    = {A {S}calable {F}ramework for {Q}uality {A}ssessment of {RDF} {D}atasets},\n  Author                   = {Gezim Sejdiu and Anisa Rula and Jens Lehmann and Hajira Jabeen},\n  Booktitle                = {Proceedings of 18th International Semantic Web Conference},\n  Year                     = {2019},\n  Keywords                 = {2019 sansa sejdiu rula jabeen lehmann group_sda},\n  Url                      = {http://jens-lehmann.org/files/2019/iswc_dist_quality_assessment.pdf},\n  UrlSlides                = {https://www.slideshare.net/GezimSejdiu/a-scalable-framework-for-quality-assessment-of-rdf-datasets-iswc-2019-talk}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Sparklify: A Scalable Software Component for Efficient evaluation of SPARQL queries over distributed RDF datasets.\n \n \n \n \n\n\n \n Claus Stadler; Gezim Sejdiu; Damien Graux; and Jens Lehmann.\n\n\n \n\n\n\n In Proceedings of 18th International Semantic Web Conference, 2019. \n \n\n\n\n
\n\n\n\n \n \n \"Sparklify:Paper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 7 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n\n\n\n
\n 
@InProceedings{2019-sansa-sparklify-iswc,\n  Title                    = {Sparklify: {A S}calable {S}oftware {C}omponent for {E}fficient evaluation of {SPARQL} queries over distributed {RDF} datasets},\n  Author                   = {Claus Stadler and Gezim Sejdiu and Damien Graux and Jens Lehmann},\n  Booktitle                = {Proceedings of 18th International Semantic Web Conference},\n  Year                     = {2019},\n  Keywords                 = {2019 sansa stadler sejdiu graux lehmann group_sda},\n  Url                      = {http://jens-lehmann.org/files/2019/iswc_sparklify.pdf}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Towards A Scalable Semantic-based Distributed Approach for SPARQL query evaluation.\n \n \n \n \n\n\n \n Gezim Sejdiu; Damien Graux; Imran Khan; Ioanna Lytra; Hajira Jabeen; and Jens Lehmann.\n\n\n \n\n\n\n In 15th International Conference on Semantic Systems (SEMANTiCS), 2019. \n \n\n\n\n
\n\n\n\n \n \n \"TowardsPaper\n  \n \n \n \"TowardsSlides\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 3 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n\n\n\n
\n 
@InProceedings{sejdiu-2019-sansa-semantic-based-semantics,\n  Title                    = {Towards {A S}calable {S}emantic-based {D}istributed {A}pproach for {SPARQL} query evaluation},\n  Author                   = {Gezim Sejdiu and Damien Graux and Imran Khan and Ioanna Lytra and Hajira Jabeen and Jens Lehmann},\n  Booktitle                = {15th International Conference on Semantic Systems (SEMANTiCS)},\n  Year                     = {2019},\n  Keywords                 = {2019 sansa sejdiu graux lytra jabeen lehmann group_sda},\n  Url                      = {https://gezimsejdiu.github.io/publications/semantic_based_query_paper_SEMANTICS2019.pdf},\n  UrlSlides                = {https://www.slideshare.net/GezimSejdiu/towards-a-scalable-semanticbased-distributed-approach-for-sparql-query-evaluation-semantics-2019-talk}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Preface for the Knowledge Graph Building and Large Scale RDF Analytics Workshops.\n \n \n \n \n\n\n \n Pieter Heyvaert; David Chaves-Fraga; Freddy Priyatna; Anastasia Dimou; Juan Sequeda; Hajira Jabeen; Damien Graux; Gezim Sejdiu; Mohammed; Saleem; and Jens Lehmann.\n\n\n \n\n\n\n In Joint Proceedings of the 1st International Workshop on Knowledge Graph Building and 1st International Workshop on Large Scale RDF Analytics co-located with 16th Extended Semantic Web Conference (ESWC 2019), 2019. \n \n\n\n\n
\n\n\n\n \n \n \"PrefacePaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{Heyvaert2019PrefaceFT,\n  Title                    = {Preface for the {K}nowledge {G}raph {B}uilding and {L}arge {S}cale {RDF A}nalytics {W}orkshops},\n  Author                   = {Pieter Heyvaert and David Chaves-Fraga and Freddy Priyatna and Anastasia Dimou and Juan Sequeda and Hajira Jabeen and Damien Graux and Gezim Sejdiu and Mohammed and Saleem and Jens Lehmann},\n  Year                     = {2019},\n  Booktitle                = {Joint Proceedings of the 1st International Workshop on Knowledge Graph Building and 1st International Workshop on Large Scale RDF Analytics co-located with 16th Extended Semantic Web Conference (ESWC 2019)},\n  Url                      = {http://ceur-ws.org/Vol-2489/xpreface.pdf}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Clustering Pipelines of large RDF POI Data.\n \n \n \n \n\n\n \n Rajjat Dadwal; Damien Graux; Gezim Sejdiu; Hajira Jabeen; and Jens Lehmann.\n\n\n \n\n\n\n In Proceedings of 16th Extended Semantic Web Conference (ESWC 2019), Poster & Demos, 2019. \n \n\n\n\n
\n\n\n\n \n \n \"ClusteringPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n\n\n\n
\n 
@InProceedings{piping-clustering-eswc19-poster,\n  Title                    = {{C}lustering {P}ipelines of large {RDF POI D}ata},\n  Author                   = {Rajjat Dadwal and Damien Graux and Gezim Sejdiu and Hajira Jabeen and Jens Lehmann},\n  Booktitle                = {Proceedings of 16th Extended Semantic Web Conference (ESWC 2019), Poster \\& Demos},\n  Year                     = {2019},\n  Keywords                 = {2019 sansa dadwal graux sejdiu jabeen lehmann sda},\n  Url                      = {https://gezimsejdiu.github.io/publications/piping-clustering-eswc19-poster.pdf}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Jekyll RDF: Template-Based Linked Data Publication with Minimized Effort and Maximum Scalability.\n \n \n \n \n\n\n \n Natanael Arndt; Sebastian Zänker; Gezim Sejdiu; and Sebastian Tramp.\n\n\n \n\n\n\n In 19th International Conference on Web Engineering (ICWE 2019), of ICWE 2019, Daejeon, Korea, June 2019. \n \n\n\n\n
\n\n\n\n \n \n \"JekyllPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n\n\n\n
\n 
@InProceedings{arndt-n-2019--jekyll-rdf,\n  Title                    = {Jekyll RDF: Template-Based Linked Data Publication with Minimized Effort and Maximum Scalability},\n  Author                   = {Arndt, Natanael and Z{\\"{a}}nker, Sebastian and Sejdiu, Gezim and Tramp, Sebastian},\n  Booktitle                = {19th International Conference on Web Engineering (ICWE 2019)},\n  Year                     = {2019},\n\n  Address                  = {Daejeon, Korea},\n  Month                    = jun,\n  Series                   = {ICWE 2019},\n\n  Abstract                 = {Over the last decades the Web has evolved from a human--human communication network to a network of complex human--machine interactions.\nAn increasing amount of data is available as Linked Data which allows machines to “understand” the data, but RDF is not meant to be understood by humans.\nWith Jekyll RDF we present a method to close the gap between structured data and human accessible exploration interfaces by publishing RDF datasets as customizable static HTML sites.\nIt consists of an RDF resource mapping system to serve the resources under their respective IRI, a template mapping based on schema classes, and a markup language to define templates to render customized resource pages.\nUsing the template system, it is possible to create domain specific browsing interfaces for RDF data next to the Linked Data resources.\nThis enables content management and knowledge management systems to serve datasets in a highly customizable, low effort, and scalable way to be consumed by machines as well as humans.},\n  Biburl                   = {https://www.bibsonomy.org/bibtex/2a1e1c2444f057e1a826ceba4e44daf03/aksw},\n  Keywords                 = {2019 arndt es group_aksw leds},\n  Url                      = {https://svn.aksw.org/papers/2019/ICWE_JekyllRDF/public.pdf}\n}\n\n
\n
\n\n\n
\n Over the last decades the Web has evolved from a human–human communication network to a network of complex human–machine interactions. An increasing amount of data is available as Linked Data which allows machines to “understand” the data, but RDF is not meant to be understood by humans. With Jekyll RDF we present a method to close the gap between structured data and human accessible exploration interfaces by publishing RDF datasets as customizable static HTML sites. It consists of an RDF resource mapping system to serve the resources under their respective IRI, a template mapping based on schema classes, and a markup language to define templates to render customized resource pages. Using the template system, it is possible to create domain specific browsing interfaces for RDF data next to the Linked Data resources. This enables content management and knowledge management systems to serve datasets in a highly customizable, low effort, and scalable way to be consumed by machines as well as humans.\n
\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2018\n \n \n (5)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n STATisfy Me: What are my Stats?.\n \n \n \n \n\n\n \n Gezim Sejdiu; Ivan Ermilov; Jens Lehmann; and Mohamed-Nadjib Mami.\n\n\n \n\n\n\n In Proceedings of 17th International Semantic Web Conference, Poster & Demos, 2018. \n \n\n\n\n
\n\n\n\n \n \n \"STATisfyPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 2 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n\n\n\n
\n 
@InProceedings{sejdiu-2018-statisfy-iswc-poster,\n  Title                    = {{STAT}isfy {M}e: {W}hat are my {S}tats?},\n  Author                   = {Sejdiu, Gezim and Ermilov, Ivan and Lehmann, Jens and Mami, Mohamed-Nadjib},\n  Booktitle                = {Proceedings of 17th International Semantic Web Conference, Poster \\& Demos},\n  Year                     = {2018},\n  Keywords                 = {2018 bde sejdiu lehmann group_aksw iermilov mami},\n  Url                      = {http://jens-lehmann.org/files/2018/iswc_statisfy_pd.pdf}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n DistLODStats: Distributed Computation of RDF Dataset Statistics.\n \n \n \n \n\n\n \n Gezim Sejdiu; Ivan Ermilov; Jens Lehmann; and Mohamed Nadjib-Mami.\n\n\n \n\n\n\n In Proceedings of 17th International Semantic Web Conference, 2018. \n \n\n\n\n
\n\n\n\n \n \n \"DistLODStats:Paper\n  \n \n \n \"DistLODStats:Slides\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n  \n \n 3 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n\n\n\n
\n 
@InProceedings{sejdiu-2018-dist-lod-stats-iswc,\n  Title                    = {Dist{LODS}tats: {D}istributed {C}omputation of {RDF D}ataset {S}tatistics},\n  Author                   = {Sejdiu, Gezim and Ermilov, Ivan and Lehmann, Jens and Nadjib-Mami, Mohamed},\n  Booktitle                = {Proceedings of 17th International Semantic Web Conference},\n  Year                     = {2018},\n\n  Abstract                 = {Over the last years, the Semantic Web has been growing steadily. Today, we count more than 10,000 datasets made available online following Semantic Web standards.\n Nevertheless, many applications, such as data integration, search, and interlinking, may not take the full advantage of the data without having a priori statistical information about its internal structure and coverage.\n In fact, there are already a number of tools, which offer such statistics, providing basic information about RDF datasets and vocabularies.\n However, those usually show severe deficiencies in terms of performance once the dataset size grows beyond the capabilities of a single machine.\n In this paper, we introduce a software component for statistical calculations of large RDF datasets, which scales out to clusters of machines.\n More specifically, we describe the first distributed in-memory approach for computing 32 different statistical criteria for RDF datasets using Apache Spark.\n The preliminary results show that our distributed approach improves upon a previous centralized approach we compare against and provides approximately linear horizontal scale-up.\n The criteria are extensible beyond the 32 default criteria, is integrated into the larger SANSA framework and employed in at least four major usage scenarios beyond the SANSA community.},\n  Keywords                 = {2018 bde sejdiu lehmann group_aksw iermilov},\n  Url                      = {http://jens-lehmann.org/files/2018/iswc_distlodstats.pdf},\n  UrlSlides                = {https://www.slideshare.net/GezimSejdiu/distlodstats-distributed-computation-of-rdf-dataset-statistics-iswc-2018-talk}\n}\n\n
\n
\n\n\n
\n Over the last years, the Semantic Web has been growing steadily. Today, we count more than 10,000 datasets made available online following Semantic Web standards. Nevertheless, many applications, such as data integration, search, and interlinking, may not take the full advantage of the data without having a priori statistical information about its internal structure and coverage. In fact, there are already a number of tools, which offer such statistics, providing basic information about RDF datasets and vocabularies. However, those usually show severe deficiencies in terms of performance once the dataset size grows beyond the capabilities of a single machine. In this paper, we introduce a software component for statistical calculations of large RDF datasets, which scales out to clusters of machines. More specifically, we describe the first distributed in-memory approach for computing 32 different statistical criteria for RDF datasets using Apache Spark. The preliminary results show that our distributed approach improves upon a previous centralized approach we compare against and provides approximately linear horizontal scale-up. The criteria are extensible beyond the 32 default criteria, is integrated into the larger SANSA framework and employed in at least four major usage scenarios beyond the SANSA community.\n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Profiting from Kitties on Ethereum: Leveraging Blockchain RDF with SANSA.\n \n \n \n \n\n\n \n Damien Graux; Gezim Sejdiu; Hajira Jabeen; Jens Lehmann; Danning Sui; Dominik Muhs; and Johannes Pfeffer.\n\n\n \n\n\n\n In 14th International Conference on Semantic Systems, Poster & Demos, 2018. \n \n\n\n\n
\n\n\n\n \n \n \"ProfitingPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n\n\n\n
\n 
@InProceedings{graux-2018-sansa-ethereum-semantics-poster,\n  Title                    = {Profiting from {K}itties on {E}thereum: {L}everaging {B}lockchain {RDF} with {SANSA}},\n  Author                   = {Graux, Damien and Sejdiu, Gezim and Jabeen, Hajira and Lehmann, Jens and Sui, Danning and Muhs, Dominik and Pfeffer, Johannes},\n  Booktitle                = {14th International Conference on Semantic Systems, Poster \\& Demos},\n  Year                     = {2018},\n\n  Keywords                 = {2018 bde graux sejdiu lehmann group_aksw jabeen},\n  Url                      = {http://jens-lehmann.org/files/2018/semantics_ethereum_pd.pdf}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Divided we stand out! Forging Cohorts fOr Numeric Outlier Detection in large scale knowledge graphs (CONOD).\n \n \n \n \n\n\n \n Hajira Jabeen; Rajjat Dadwal; Gezim Sejdiu; and Jens Lehmann.\n\n\n \n\n\n\n In 21st International Conference on Knowledge Engineering and Knowledge Management (EKAW'2018), 2018. \n \n\n\n\n
\n\n\n\n \n \n \"DividedPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n\n\n\n
\n 
@InProceedings{jabeen-2018-sansa-outlier-ekaw,\n  Title                    = {Divided we stand out! {F}orging {C}ohorts f{O}r {N}umeric {O}utlier {D}etection in large scale knowledge graphs ({CONOD})},\n  Author                   = {Jabeen, Hajira and Dadwal, Rajjat and Sejdiu, Gezim and Lehmann, Jens},\n  Booktitle                = {21st International Conference on Knowledge Engineering and Knowledge Management (EKAW'2018)},\n  Year                     = {2018},\n\n  Keywords                 = {2018 sansa jabeen sejdiu lehmann group_aksw},\n  Url                      = {http://jens-lehmann.org/files/2018/ekaw_conod.pdf}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n MINDS: a translator to embed mathematical expressions inside SPARQL queries.\n \n \n \n \n\n\n \n Damien Graux; Gezim Sejdiu; Claus Stadler; Giulio Napolitano; and Jens Lehmann.\n\n\n \n\n\n\n Technical Report University of Bonn, Smart Data Analytics, 2018.\n \n\n\n\n
\n\n\n\n \n \n \"MINDS:Paper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@techreport{graux-minds,\n  Title                    = {{MINDS}: a translator to embed mathematical expressions inside {SPARQL} queries},\n  Author                   = {Damien Graux and Gezim Sejdiu and Claus Stadler and Giulio Napolitano and Jens Lehmann},\n  Year                     = {2018},\n  Institution              = {University of Bonn, Smart Data Analytics},\n  Url                      = {https://smartdataanalytics.github.io/minds/MINDS_v0.1_report.pdf}\n}\n\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2017\n \n \n (5)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n Distributed Semantic Analytics using the SANSA Stack.\n \n \n \n \n\n\n \n Jens Lehmann; Gezim Sejdiu; Lorenz Bühmann; Patrick Westphal; Claus Stadler; Ivan Ermilov; Simon Bin; Nilesh Chakraborty; Muhammad Saleem; Axel-Cyrille Ngomo Ngonga; and Hajira Jabeen.\n\n\n \n\n\n\n In Proceedings of 16th International Semantic Web Conference - Resources Track (ISWC'2017), 2017. \n \n\n\n\n
\n\n\n\n \n \n \"DistributedPaper\n  \n \n \n \"DistributedSlides\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n  \n \n 6 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n\n\n\n
\n 
@InProceedings{lehmann-2017-sansa-iswc,\n  Title                    = {Distributed {S}emantic {A}nalytics using the {SANSA S}tack},\n  Author                   = {Lehmann, Jens and Sejdiu, Gezim and B\\"uhmann, Lorenz and Westphal, Patrick and Stadler, Claus and Ermilov, Ivan and Bin, Simon and Chakraborty, Nilesh and Saleem, Muhammad and Ngonga, Axel-Cyrille Ngomo and Jabeen, Hajira},\n  Booktitle                = {Proceedings of 16th International Semantic Web Conference - Resources Track (ISWC'2017)},\n  Year                     = {2017},\n\n  Abstract                 = {Over the past decade, vast amounts of machine-readable structured information have become available through the automation of research processes as well as the increasing popularity of knowledge graphs and semantic technologies. A major research challenge today is to perform scalable analysis of large-scale knowledge graphs to facilitate applications like link prediction, knowledge base completion and question answering. Most analytics approaches, which scale horizontally (i.e., can be executed in a distributed environment) work on simple feature-vector-based input rather than more expressive knowledge structures. On the other hand, analytics methods which exploit expressive structures usually do not scale well to very large knowledge bases. This software framework paper describes the ongoing project Semantic Analytics Stack (SANSA) which supports expressive and scalable semantic analytics by providing functionality for distributed in-memory computing for RDF data. The library provides APIs for RDF storage, querying using SPARQL and forward chaining inference. It includes several machine learning algorithms for RDF knowledge graphs. The article describes the vision, architecture and use cases of SANSA.},\n  Biburl                   = {https://www.bibsonomy.org/bibtex/21ae18ac13750f9cf74227fe0a7c50104/aksw},\n  Keywords                 = {2017 bde buehmann chakraborty group_aksw iermilov lehmann ngonga saleem sbin sejdiu stadler westphal},\n  Url                      = {http://svn.aksw.org/papers/2017/ISWC_SANSA_SoftwareFramework/public.pdf},\n  UrlSlides                = {https://www.slideshare.net/JensLehmann/sansa-iswc-international-semantic-web-conference-2017-talk}\n}\n\n
\n
\n\n\n
\n Over the past decade, vast amounts of machine-readable structured information have become available through the automation of research processes as well as the increasing popularity of knowledge graphs and semantic technologies. A major research challenge today is to perform scalable analysis of large-scale knowledge graphs to facilitate applications like link prediction, knowledge base completion and question answering. Most analytics approaches, which scale horizontally (i.e., can be executed in a distributed environment) work on simple feature-vector-based input rather than more expressive knowledge structures. On the other hand, analytics methods which exploit expressive structures usually do not scale well to very large knowledge bases. This software framework paper describes the ongoing project Semantic Analytics Stack (SANSA) which supports expressive and scalable semantic analytics by providing functionality for distributed in-memory computing for RDF data. The library provides APIs for RDF storage, querying using SPARQL and forward chaining inference. It includes several machine learning algorithms for RDF knowledge graphs. The article describes the vision, architecture and use cases of SANSA.\n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n The Tale of Sansa Spark.\n \n \n \n \n\n\n \n Ivan Ermilov; Jens Lehmann; Gezim Sejdiu; Lorenz Bühmann; Patrick Westphal; Claus Stadler; Simon Bin; Nilesh Chakraborty; Henning Petzka; Muhammad Saleem; Axel-Cyrille Ngomo Ngonga; and Hajira Jabeen.\n\n\n \n\n\n\n In Proceedings of 16th International Semantic Web Conference, Poster & Demos, 2017. \n \n\nBest Demo Award.\n\n
\n\n\n\n \n \n \"ThePaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n\n\n\n
\n 
@InProceedings{iermilov-2017-sansa-iswc-demo,\n  Title                    = {The {T}ale of {S}ansa {S}park},\n  Author                   = {Ermilov, Ivan and Lehmann, Jens and Sejdiu, Gezim and B\\"uhmann, Lorenz and Westphal, Patrick and Stadler, Claus and Bin, Simon and Chakraborty, Nilesh and Petzka, Henning and Saleem, Muhammad and Ngonga, Axel-Cyrille Ngomo and Jabeen, Hajira},\n  Booktitle                = {Proceedings of 16th International Semantic Web Conference, Poster \\& Demos},\n  Year                     = {2017},\n\n  Bibbase_note             = {<span style="color: red; font-weight: bold">Best Demo Award.</span>},\n  Biburl                   = {https://www.bibsonomy.org/bibtex/2f9b5a69afa4755944984ae63f59ad146/aksw},\n  Keywords                 = {2017 bde buehmann chakraborty group_aksw iermilov lehmann mole ngonga saleem sbin sejdiu stadler westphal},\n  Url                      = {http://jens-lehmann.org/files/2017/iswc_pd_sansa.pdf}\n}\n\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n The BigDataEurope Platform - Supporting the Variety Dimension of Big Data.\n \n \n \n \n\n\n \n Sören Auer; Simon Scerri; Aad Versteden; Erika Pauwels; Angelos Charalambidis; Stasinos Konstantopoulos; Jens Lehmann; Hajira Jabeen; Ivan Ermilov; Gezim Sejdiu; Andreas Ikonomopoulos; Spyros Andronopoulos; Mandy Vlachogiannis; Charalambos Pappas; Athanasios Davettas; Iraklis A. Klampanos; Efstathios Grigoropoulos; Vangelis Karkaletsis; Victor Boer; Ronald Siebes; Mohamed Nadjib Mami; Sergio Albani; Michele Lazzarini; Paulo Nunes; Emanuele Angiuli; Nikiforos Pittaras; George Giannakopoulos; Giorgos Argyriou; George Stamoulis; George Papadakis; Manolis Koubarakis; Pythagoras Karampiperis; Axel-Cyrille Ngonga Ngomo; and Maria-Esther Vidal.\n\n\n \n\n\n\n In 17th International Conference on Web Engineering (ICWE2017), 2017. \n \n\n\n\n
\n\n\n\n \n \n \"ThePaper\n  \n \n \n \"TheSlides\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n\n\n\n
\n 
@InProceedings{Auer+ICWE-2017,\n  Title                    = {{T}he {B}ig{D}ata{E}urope {P}latform - {S}upporting the {V}ariety {D}imension of {B}ig {D}ata},\n  Author                   = {S\\"oren Auer and Simon Scerri and Aad Versteden and Erika Pauwels and Angelos Charalambidis and Stasinos Konstantopoulos and Jens Lehmann and Hajira Jabeen and Ivan Ermilov and Gezim Sejdiu and Andreas Ikonomopoulos and Spyros Andronopoulos and Mandy Vlachogiannis and Charalambos Pappas and Athanasios Davettas and Iraklis A. Klampanos and Efstathios Grigoropoulos and Vangelis Karkaletsis and Victor de Boer and Ronald Siebes and Mohamed Nadjib Mami and Sergio Albani and Michele Lazzarini and Paulo Nunes and Emanuele Angiuli and Nikiforos Pittaras and George Giannakopoulos and Giorgos Argyriou and George Stamoulis and George Papadakis and Manolis Koubarakis and Pythagoras Karampiperis and Axel-Cyrille Ngonga Ngomo and Maria-Esther Vidal},\n  Booktitle                = {17th International Conference on Web Engineering (ICWE2017)},\n  Year                     = {2017},\n\n  Abstract                 = {The management and analysis of large-scale datasets -- described with the term Big Data -- involves the three classic dimensions volume, velocity and variety. While the former two are well supported by a plethora of software components, the variety dimension is still rather neglected. We present the BDE platform -- an easy-to-deploy, easy-to-use and adaptable (cluster-based and standalone) platform for the execution of big data components and tools like Hadoop, Spark, Flink. The BDE platform was designed based upon the requirements gathered from the seven societal challenges put forward by the European Commission in the Horizon 2020 programme and targeted by the BigDataEurope pilots. As a result, the BDE platform allows to perform a variety of Big Data flow tasks like message passing (Kafka, Flume), storage (Hive, Cassandra) or publishing (GeoTriples). In order to facilitate the processing of heterogeneous data, a particular innovation of the platform is the semantic layer, which allows to directly process RDF data and to map and transform arbitrary data into RDF.},\n  Bdsk-url-1               = {http://svn.aksw.org/lod2/Paper/ISWC2012-InUse_LOD2-Stack/public.pdf},\n  Date-modified            = {2012-12-02 12:25:29 +0000},\n  Keywords                 = {group_aksw sys:relevantFor:infai sys:relevantFor:bis 2017 auer iermilov ngonga lehmann bde MOLE},\n  Url                      = {http://jens-lehmann.org/files/2017/icwe_bde.pdf},\n  UrlSlides                = {https://www.slideshare.net/BigData_Europe/icwe2017-bigdataeurope}\n}\n\n
\n
\n\n\n
\n The management and analysis of large-scale datasets – described with the term Big Data – involves the three classic dimensions volume, velocity and variety. While the former two are well supported by a plethora of software components, the variety dimension is still rather neglected. We present the BDE platform – an easy-to-deploy, easy-to-use and adaptable (cluster-based and standalone) platform for the execution of big data components and tools like Hadoop, Spark, Flink. The BDE platform was designed based upon the requirements gathered from the seven societal challenges put forward by the European Commission in the Horizon 2020 programme and targeted by the BigDataEurope pilots. As a result, the BDE platform allows to perform a variety of Big Data flow tasks like message passing (Kafka, Flume), storage (Hive, Cassandra) or publishing (GeoTriples). In order to facilitate the processing of heterogeneous data, a particular innovation of the platform is the semantic layer, which allows to directly process RDF data and to map and transform arbitrary data into RDF.\n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Managing Lifecycle of Big Data Applications.\n \n \n \n \n\n\n \n Ivan Ermilov; Axel-Cyrille Ngonga Ngomo; Aad Versteden; Hajira Jabeen; Gezim Sejdiu; Giorgos Argyriou; Luigi Selmi; Jürgen Jakobitsch; and Jens Lehmann.\n\n\n \n\n\n\n In KESW, 2017. \n \n\n\n\n
\n\n\n\n \n \n \"ManagingPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n\n\n\n
\n 
@InProceedings{KESW_2017_BDE,\n  Title                    = {Managing Lifecycle of Big Data Applications},\n  Author                   = {Ermilov, Ivan and Ngomo, Axel-Cyrille Ngonga and Versteden, Aad and Jabeen, Hajira and Sejdiu, Gezim and Argyriou, Giorgos and Selmi, Luigi and Jakobitsch, J{\\"u}rgen and Lehmann, Jens},\n  Booktitle                = {KESW},\n  Year                     = {2017},\n\n  Biburl                   = {https://www.bibsonomy.org/bibtex/2f5ee59fb595ade7ece4c840ad4a95741/aksw},\n  Keywords                 = {bde group_aksw iermilov lehmann ngonga simba},\n  Url                      = {https://svn.aksw.org/papers/2017/KESW_BDE_Workflow/public.pdf}\n}\n\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Distributed Knowledge Graph Processing in SANSA.\n \n \n \n \n\n\n \n Jens Lehmann; Gezim Sejdiu; and Hajira Jabeen.\n\n\n \n\n\n\n HPI Future SOC Lab: Proceedings 2017, 130: 21. 2017.\n \n\n\n\n
\n\n\n\n \n \n \"DistributedPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@article{lehmann2017distributed,\n  Title                   = {Distributed Knowledge Graph Processing in SANSA},\n  Author                  = {Jens Lehmann and Gezim Sejdiu and Hajira Jabeen},\n  Journal                 = {HPI Future SOC Lab: Proceedings 2017},\n  Volume                  = {130},\n  Pages                   = {21},\n  Year                    = {2017},\n  Publisher               = {Universit{\\"a}tsverlag Potsdam},\n  Url                     = {https://scholar.google.com/scholar?oi=bibs&cluster=6701703243740603519&btnI=1}\n}\n\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2016\n \n \n (1)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n LITMUS: An Open Extensible Framework for Benchmarking RDF Data Management Solutions.\n \n \n \n\n\n \n Harsh Thakkar; Mohnish Dubey; Gezim Sejdiu; Axel-Cyrille Ngonga Ngomo; Jeremy Debattista; Christoph Lange; Jens Lehmann; Sören Auer; and Maria-Esther Vidal.\n\n\n \n\n\n\n 2016.\n \n\n\n\n
\n\n\n\n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@Other{ThakkarEtAl:LITMUS16,\n  Title                    = {{LITMUS}: {A}n {O}pen {E}xtensible {F}ramework for {B}enchmarking {RDF} {D}ata {M}anagement {S}olutions},\n  Author                   = {Harsh Thakkar and Mohnish Dubey and Gezim Sejdiu and Ngonga Ngomo, Axel-Cyrille and Jeremy Debattista and Christoph Lange and Jens Lehmann and S{\\"o}ren Auer and Maria-Esther Vidal},\n  Date                     = {2016-08-09},\n  Eprint                   = {1608.02800},\n  Eprintclass              = {cs.PF},\n  Eprinttype               = {arxiv},\n  File                     = {http:/arxiv.org/pdf/1608.02800:Djvu},\n  Pubs                     = {clange,vidal},\n  Year                     = {2016}\n}\n\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2014\n \n \n (2)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n Semantic Ranking of Web Pages : The Wikipedia Case Study.\n \n \n \n \n\n\n \n Gezim Sejdiu.\n\n\n \n\n\n\n Master's thesis, Faculty of Electrical and Computer Engineering, University of Prishtina, Kosova, 7 2014.\n \n\n\n\n
\n\n\n\n \n \n \"SemanticPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 10 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n\n\n\n
\n 
@MastersThesis{sejdiu2014,\n  Title                    = {Semantic {R}anking of {W}eb {P}ages : {T}he {W}ikipedia {C}ase {S}tudy},\n  Author                   = {Gezim Sejdiu},\n  School                   = {Faculty of {E}lectrical and {C}omputer {E}ngineering},\n  Year                     = {2014},\n\n  Address                  = {University of Prishtina, Kosova},\n  Month                    = {7},\n\n  Keywords                 = {2014 sejdiu},\n  Url                      = {https://gezimsejdiu.github.io/publications/gezim_sejdiu_master_thesis_sq.pdf}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Ranking Authors on the Web: A Semantic AuthorRank.\n \n \n \n \n\n\n \n Lule Ahmedi; Lavdim Halilaj; Gezim Sejdiu; and Labinot Bajraktari.\n\n\n \n\n\n\n In Şule Gündüz-Öğüdücü; and A. Şima Etaner-Uyar., editor(s), Social Networks: Analysis and Case Studies, pages 19–40. Springer Vienna, Vienna, 2014.\n \n\n\n\n
\n\n\n\n \n \n \"RankingPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n\n\n\n
\n 
@InCollection{Ahmedi2014,\n  Title                    = {Ranking {A}uthors on the {W}eb: {A} {S}emantic {A}uthor{R}ank},\n  Author                   = {Ahmedi, Lule and Halilaj, Lavdim and Sejdiu, Gezim and Bajraktari, Labinot},\n  Editor                   = {G{\\"u}nd{\\"u}z-{\\"O}{\\u{g}}{\\"u}d{\\"u}c{\\"u}, {\\c{S}}ule and Etaner-Uyar, A. {\\c{S}}ima},\n  Pages                    = {19--40},\n  Publisher                = {Springer Vienna},\n  Year                     = {2014},\n\n  Address                  = {Vienna},\n\n  Abstract                 = {Author ranking is growing in popularity since search engines are considering the author's reputation of a Web page when generating search results. A question that naturally arises is whether we should rank authors on the Web as we rank Web pages by considering their links. In addition, over what links to actually calculate author ranking? We have adopted an extended FOAF ontology, the so-called Co-AuthorOnto ontology, able to represent authors, but also their co-author links on the Web. We further extended Co-AuthorOnto with PageRank and AuthorRank metrics for ranking authors based on their co-author links. Important to note is that both PageRank and AuthorRank are implemented in Semantic Web Rule Language (SWRL), which represents a novelty and fits well with the semantic modeling of authors and their co-author relationships within FOAF. Preliminary semantic ranking results are demonstrated, showcasing also the huge potential of this ranking approach for adopting it by search engines where our future work will focus.},\n  Booktitle                = {Social Networks: Analysis and Case Studies},\n  Doi                      = {10.1007/978-3-7091-1797-2_2},\n  Keywords                 = {sejdiu},\n  Url                      = {http://luleahmedi.uni-pr.edu/docs/pubs/SemAuthorRank2014.pdf}\n}\n\n
\n
\n\n\n
\n Author ranking is growing in popularity since search engines are considering the author's reputation of a Web page when generating search results. A question that naturally arises is whether we should rank authors on the Web as we rank Web pages by considering their links. In addition, over what links to actually calculate author ranking? We have adopted an extended FOAF ontology, the so-called Co-AuthorOnto ontology, able to represent authors, but also their co-author links on the Web. We further extended Co-AuthorOnto with PageRank and AuthorRank metrics for ranking authors based on their co-author links. Important to note is that both PageRank and AuthorRank are implemented in Semantic Web Rule Language (SWRL), which represents a novelty and fits well with the semantic modeling of authors and their co-author relationships within FOAF. Preliminary semantic ranking results are demonstrated, showcasing also the huge potential of this ranking approach for adopting it by search engines where our future work will focus.\n
\n\n\n
\n\n\n\n\n\n
\n
\n\n\n\n\n
\n\n\n \n\n \n \n \n \n\n
\n"}; document.write(bibbase_data.data);