@book{AlnemrPolyvyanyyAbuJarouretal.2010, author = {Alnemr, Rehab and Polyvyanyy, Artem and AbuJarour, Mohammed and Appeltauer, Malte and Hildebrandt, Dieter and Thomas, Ivonne and Overdick, Hagen and Sch{\"o}bel, Michael and Uflacker, Matthias and Kluth, Stephan and Menzel, Michael and Schmidt, Alexander and Hagedorn, Benjamin and Pascalau, Emilian and Perscheid, Michael and Vogel, Thomas and Hentschel, Uwe and Feinbube, Frank and Kowark, Thomas and Tr{\"u}mper, Jonas and Vogel, Tobias and Becker, Basil}, title = {Proceedings of the 4th Ph.D. Retreat of the HPI Research School on Service-oriented Systems Engineering}, editor = {Meinel, Christoph and Plattner, Hasso and D{\"o}llner, J{\"u}rgen Roland Friedrich and Weske, Mathias and Polze, Andreas and Hirschfeld, Robert and Naumann, Felix and Giese, Holger}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-036-6}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-40838}, publisher = {Universit{\"a}t Potsdam}, pages = {Getr. Z{\"a}hlung}, year = {2010}, language = {en} } @article{DreselerBoissierRabletal.2020, author = {Dreseler, Markus and Boissier, Martin and Rabl, Tilmann and Uflacker, Matthias}, title = {Quantifying TPC-H choke points and their optimizations}, series = {Proceedings of the VLDB Endowment}, volume = {13}, journal = {Proceedings of the VLDB Endowment}, number = {8}, publisher = {Association for Computing Machinery}, address = {New York}, issn = {2150-8097}, doi = {10.14778/3389133.3389138}, pages = {1206 -- 1220}, year = {2020}, abstract = {TPC-H continues to be the most widely used benchmark for relational OLAP systems. It poses a number of challenges, also known as "choke points", which database systems have to solve in order to achieve good benchmark results. Examples include joins across multiple tables, correlated subqueries, and correlations within the TPC-H data set. Knowing the impact of such optimizations helps in developing optimizers as well as in interpreting TPC-H results across database systems. This paper provides a systematic analysis of choke points and their optimizations. It complements previous work on TPC-H choke points by providing a quantitative discussion of their relevance. It focuses on eleven choke points where the optimizations are beneficial independently of the database system. Of these, the flattening of subqueries and the placement of predicates have the biggest impact. Three queries (Q2, Q17, and Q21) are strongly ifluenced by the choice of an efficient query plan; three others (Q1, Q13, and Q18) are less influenced by plan optimizations and more dependent on an efficient execution engine.}, language = {en} } @book{HagedornSchoebelUflackeretal.2007, author = {Hagedorn, Benjamin and Sch{\"o}bel, Michael and Uflacker, Matthias and Copaciu, Flavius and Milanovic, Nikola}, title = {Proceedings of the fall 2006 workshop of the HPI research school on service-oriented systems engineering}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-939469-58-2}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-33052}, publisher = {Universit{\"a}t Potsdam}, pages = {Getr. Z{\"a}hlung}, year = {2007}, abstract = {1. Design and Composition of 3D Geoinformation Services Benjamin Hagedorn 2. Operating System Abstractions for Service-Based Systems Michael Sch{\"o}bel 3. A Task-oriented Approach to User-centered Design of Service-Based Enterprise Applications Matthias Uflacker 4. A Framework for Adaptive Transport in Service- Oriented Systems based on Performance Prediction Flavius Copaciu 5. Asynchronicity and Loose Coupling in Service-Oriented Architectures Nikola Milanovic}, language = {en} } @misc{HesseMatthiesSinzigetal.2019, author = {Hesse, G{\"u}nter and Matthies, Christoph and Sinzig, Werner and Uflacker, Matthias}, title = {Adding Value by Combining Business and Sensor Data}, series = {Database Systems for Advanced Applications}, volume = {11448}, journal = {Database Systems for Advanced Applications}, publisher = {Springer}, address = {Cham}, isbn = {978-3-030-18590-9}, issn = {0302-9743}, doi = {10.1007/978-3-030-18590-9_80}, pages = {528 -- 532}, year = {2019}, abstract = {Industry 4.0 and the Internet of Things are recent developments that have lead to the creation of new kinds of manufacturing data. Linking this new kind of sensor data to traditional business information is crucial for enterprises to take advantage of the data's full potential. In this paper, we present a demo which allows experiencing this data integration, both vertically between technical and business contexts and horizontally along the value chain. The tool simulates a manufacturing company, continuously producing both business and sensor data, and supports issuing ad-hoc queries that answer specific questions related to the business. In order to adapt to different environments, users can configure sensor characteristics to their needs.}, language = {en} } @article{KowarkUflackerZeier2012, author = {Kowark, Thomas and Uflacker, Matthias and Zeier, Alexander}, title = {Towards a shared platform for virtual collaboration monotoring in design research}, year = {2012}, language = {en} } @misc{PerscheidFaberKrausetal.2018, author = {Perscheid, Cindy and Faber, Lukas and Kraus, Milena and Arndt, Paul and Janke, Michael and Rehfeldt, Sebastian and Schubotz, Antje and Slosarek, Tamara and Uflacker, Matthias}, title = {A tissue-aware gene selection approach for analyzing multi-tissue gene expression data}, series = {2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)}, journal = {2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)}, publisher = {IEEE}, address = {New York}, isbn = {978-1-5386-5488-0}, issn = {2156-1125}, doi = {10.1109/BIBM.2018.8621189}, pages = {2159 -- 2166}, year = {2018}, abstract = {High-throughput RNA sequencing (RNAseq) produces large data sets containing expression levels of thousands of genes. The analysis of RNAseq data leads to a better understanding of gene functions and interactions, which eventually helps to study diseases like cancer and develop effective treatments. Large-scale RNAseq expression studies on cancer comprise samples from multiple cancer types and aim to identify their distinct molecular characteristics. Analyzing samples from different cancer types implies analyzing samples from different tissue origin. Such multi-tissue RNAseq data sets require a meaningful analysis that accounts for the inherent tissue-related bias: The identified characteristics must not originate from the differences in tissue types, but from the actual differences in cancer types. However, current analysis procedures do not incorporate that aspect. As a result, we propose to integrate a tissue-awareness into the analysis of multi-tissue RNAseq data. We introduce an extension for gene selection that provides a tissue-wise context for every gene and can be flexibly combined with any existing gene selection approach. We suggest to expand conventional evaluation by additional metrics that are sensitive to the tissue-related bias. Evaluations show that especially low complexity gene selection approaches profit from introducing tissue-awareness.}, language = {en} } @article{PerscheidGrasnickUflacker2019, author = {Perscheid, Cindy and Grasnick, Bastien and Uflacker, Matthias}, title = {Integrative Gene Selection on Gene Expression Data}, series = {Journal of Integrative Bioinformatics}, volume = {16}, journal = {Journal of Integrative Bioinformatics}, number = {1}, publisher = {De Gruyter}, address = {Berlin}, issn = {1613-4516}, doi = {10.1515/jib-2018-0064}, pages = {17}, year = {2019}, abstract = {The advance of high-throughput RNA-Sequencing techniques enables researchers to analyze the complete gene activity in particular cells. From the insights of such analyses, researchers can identify disease-specific expression profiles, thus understand complex diseases like cancer, and eventually develop effective measures for diagnosis and treatment. The high dimensionality of gene expression data poses challenges to its computational analysis, which is addressed with measures of gene selection. Traditional gene selection approaches base their findings on statistical analyses of the actual expression levels, which implies several drawbacks when it comes to accurately identifying the underlying biological processes. In turn, integrative approaches include curated information on biological processes from external knowledge bases during gene selection, which promises to lead to better interpretability and improved predictive performance. Our work compares the performance of traditional and integrative gene selection approaches. Moreover, we propose a straightforward approach to integrate external knowledge with traditional gene selection approaches. We introduce a framework enabling the automatic external knowledge integration, gene selection, and evaluation. Evaluation results prove our framework to be a useful tool for evaluation and show that integration of external knowledge improves overall analysis results.}, language = {en} } @misc{PerscheidUflacker2019, author = {Perscheid, Cindy and Uflacker, Matthias}, title = {Integrating Biological Context into the Analysis of Gene Expression Data}, series = {Distributed Computing and Artificial Intelligence, Special Sessions, 15th International Conference}, volume = {801}, journal = {Distributed Computing and Artificial Intelligence, Special Sessions, 15th International Conference}, publisher = {Springer}, address = {Cham}, isbn = {978-3-319-99608-0}, issn = {2194-5357}, doi = {10.1007/978-3-319-99608-0_41}, pages = {339 -- 343}, year = {2019}, abstract = {High-throughput RNA sequencing produces large gene expression datasets whose analysis leads to a better understanding of diseases like cancer. The nature of RNA-Seq data poses challenges to its analysis in terms of its high dimensionality, noise, and complexity of the underlying biological processes. Researchers apply traditional machine learning approaches, e. g. hierarchical clustering, to analyze this data. Until it comes to validation of the results, the analysis is based on the provided data only and completely misses the biological context. However, gene expression data follows particular patterns - the underlying biological processes. In our research, we aim to integrate the available biological knowledge earlier in the analysis process. We want to adapt state-of-the-art data mining algorithms to consider the biological context in their computations and deliver meaningful results for researchers.}, language = {en} } @misc{PodlesnyKayemvonSchorlemeretal.2018, author = {Podlesny, Nikolai Jannik and Kayem, Anne V. D. M. and von Schorlemer, Stephan and Uflacker, Matthias}, title = {Minimising Information Loss on Anonymised High Dimensional Data with Greedy In-Memory Processing}, series = {Database and Expert Systems Applications, DEXA 2018, PT I}, volume = {11029}, journal = {Database and Expert Systems Applications, DEXA 2018, PT I}, publisher = {Springer}, address = {Cham}, isbn = {978-3-319-98809-2}, issn = {0302-9743}, doi = {10.1007/978-3-319-98809-2_6}, pages = {85 -- 100}, year = {2018}, abstract = {Minimising information loss on anonymised high dimensional data is important for data utility. Syntactic data anonymisation algorithms address this issue by generating datasets that are neither use-case specific nor dependent on runtime specifications. This results in anonymised datasets that can be re-used in different scenarios which is performance efficient. However, syntactic data anonymisation algorithms incur high information loss on high dimensional data, making the data unusable for analytics. In this paper, we propose an optimised exact quasi-identifier identification scheme, based on the notion of k-anonymity, to generate anonymised high dimensional datasets efficiently, and with low information loss. The optimised exact quasi-identifier identification scheme works by identifying and eliminating maximal partial unique column combination (mpUCC) attributes that endanger anonymity. By using in-memory processing to handle the attribute selection procedure, we significantly reduce the processing time required. We evaluated the effectiveness of our proposed approach with an enriched dataset drawn from multiple real-world data sources, and augmented with synthetic values generated in close alignment with the real-world data distributions. Our results indicate that in-memory processing drops attribute selection time for the mpUCC candidates from 400s to 100s, while significantly reducing information loss. In addition, we achieve a time complexity speed-up of O(3(n/3)) approximate to O(1.4422(n)).}, language = {en} } @book{RanaMohapatraSidorovaetal.2022, author = {Rana, Kaushik and Mohapatra, Durga Prasad and Sidorova, Julia and Lundberg, Lars and Sk{\"o}ld, Lars and Lopes Grim, Lu{\´i}s Fernando and Sampaio Gradvohl, Andr{\´e} Leon and Cremerius, Jonas and Siegert, Simon and Weltzien, Anton von and Baldi, Annika and Klessascheck, Finn and Kalancha, Svitlana and Lichtenstein, Tom and Shaabani, Nuhad and Meinel, Christoph and Friedrich, Tobias and Lenzner, Pascal and Schumann, David and Wiese, Ingmar and Sarna, Nicole and Wiese, Lena and Tashkandi, Araek Sami and van der Walt, Est{\´e}e and Eloff, Jan H. P. and Schmidt, Christopher and H{\"u}gle, Johannes and Horschig, Siegfried and Uflacker, Matthias and Najafi, Pejman and Sapegin, Andrey and Cheng, Feng and Stojanovic, Dragan and Stojnev Ilić, Aleksandra and Djordjevic, Igor and Stojanovic, Natalija and Predic, Bratislav and Gonz{\´a}lez-Jim{\´e}nez, Mario and de Lara, Juan and Mischkewitz, Sven and Kainz, Bernhard and van Hoorn, Andr{\´e} and Ferme, Vincenzo and Schulz, Henning and Knigge, Marlene and Hecht, Sonja and Prifti, Loina and Krcmar, Helmut and Fabian, Benjamin and Ermakova, Tatiana and Kelkel, Stefan and Baumann, Annika and Morgenstern, Laura and Plauth, Max and Eberhard, Felix and Wolff, Felix and Polze, Andreas and Cech, Tim and Danz, Noel and Noack, Nele Sina and Pirl, Lukas and Beilharz, Jossekin Jakob and De Oliveira, Roberto C. L. and Soares, F{\´a}bio Mendes and Juiz, Carlos and Bermejo, Belen and M{\"u}hle, Alexander and Gr{\"u}ner, Andreas and Saxena, Vageesh and Gayvoronskaya, Tatiana and Weyand, Christopher and Krause, Mirko and Frank, Markus and Bischoff, Sebastian and Behrens, Freya and R{\"u}ckin, Julius and Ziegler, Adrian and Vogel, Thomas and Tran, Chinh and Moser, Irene and Grunske, Lars and Sz{\´a}rnyas, G{\´a}bor and Marton, J{\´o}zsef and Maginecz, J{\´a}nos and Varr{\´o}, D{\´a}niel and Antal, J{\´a}nos Benjamin}, title = {HPI Future SOC Lab - Proceedings 2018}, number = {151}, editor = {Meinel, Christoph and Polze, Andreas and Beins, Karsten and Strotmann, Rolf and Seibold, Ulrich and R{\"o}dszus, Kurt and M{\"u}ller, J{\"u}rgen}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-547-7}, issn = {1613-5652}, doi = {10.25932/publishup-56371}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-563712}, publisher = {Universit{\"a}t Potsdam}, pages = {x, 277}, year = {2022}, abstract = {The "HPI Future SOC Lab" is a cooperation of the Hasso Plattner Institute (HPI) and industry partners. Its mission is to enable and promote exchange and interaction between the research community and the industry partners. The HPI Future SOC Lab provides researchers with free of charge access to a complete infrastructure of state of the art hard and software. This infrastructure includes components, which might be too expensive for an ordinary research environment, such as servers with up to 64 cores and 2 TB main memory. The offerings address researchers particularly from but not limited to the areas of computer science and business information systems. Main areas of research include cloud computing, parallelization, and In-Memory technologies. This technical report presents results of research projects executed in 2018. Selected projects have presented their results on April 17th and November 14th 2017 at the Future SOC Lab Day events.}, language = {en} }