@phdthesis{Abedjan2014,
  author    = {Abedjan, Ziawasch},
  title     = {Improving RDF data with data mining},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-71334},
  school      = {Universit{\"a}t Potsdam},
  year      = {2014},
  abstract  = {Linked Open Data (LOD) comprises very many and often large public data sets and knowledge bases. Those datasets are mostly presented in the RDF triple structure of subject, predicate, and object, where each triple represents a statement or fact. Unfortunately, the heterogeneity of available open data requires significant integration steps before it can be used in applications. Meta information, such as ontological definitions and exact range definitions of predicates, are desirable and ideally provided by an ontology. However in the context of LOD, ontologies are often incomplete or simply not available. Thus, it is useful to automatically generate meta information, such as ontological dependencies, range definitions, and topical classifications. Association rule mining, which was originally applied for sales analysis on transactional databases, is a promising and novel technique to explore such data. We designed an adaptation of this technique for min-ing Rdf data and introduce the concept of "mining configurations", which allows us to mine RDF data sets in various ways. Different configurations enable us to identify schema and value dependencies that in combination result in interesting use cases. To this end, we present rule-based approaches for auto-completion, data enrichment, ontology improvement, and query relaxation. Auto-completion remedies the problem of inconsistent ontology usage, providing an editing user with a sorted list of commonly used predicates. A combination of different configurations step extends this approach to create completely new facts for a knowledge base. We present two approaches for fact generation, a user-based approach where a user selects the entity to be amended with new facts and a data-driven approach where an algorithm discovers entities that have to be amended with missing facts. As knowledge bases constantly grow and evolve, another approach to improve the usage of RDF data is to improve existing ontologies. Here, we present an association rule based approach to reconcile ontology and data. Interlacing different mining configurations, we infer an algorithm to discover synonymously used predicates. Those predicates can be used to expand query results and to support users during query formulation. We provide a wide range of experiments on real world datasets for each use case. The experiments and evaluations show the added value of association rule mining for the integration and usability of RDF data and confirm the appropriateness of our mining configuration methodology.},
  language  = {en}
}
@book{AbedjanGolabNaumannetal.,
  author    = {Abedjan, Ziawasch and Golab, Lukasz and Naumann, Felix and Papenbrock, Thorsten},
  title     = {Data Profiling},
  series = {Synthesis lectures on data management, 52},
  journal   = {Synthesis lectures on data management, 52},
  publisher = {Morgan \& Claypool Publishers},
  address   = {San Rafael},
  isbn      = {978-1-68173-446-0},
  pages     = {xviii, 136},
  language  = {en}
}
@book{AbedjanNaumann2011,
  author    = {Abedjan, Ziawasch and Naumann, Felix},
  title     = {Advancing the discovery of unique column combinations},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-148-6},
  issn      = {1613-5652},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-53564},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {25},
  year      = {2011},
  abstract  = {Unique column combinations of a relational database table are sets of columns that contain only unique values. Discovering such combinations is a fundamental research problem and has many different data management and knowledge discovery applications. Existing discovery algorithms are either brute force or have a high memory load and can thus be applied only to small datasets or samples. In this paper, the wellknown GORDIAN algorithm and "Apriori-based" algorithms are compared and analyzed for further optimization. We greatly improve the Apriori algorithms through efficient candidate generation and statistics-based pruning methods. A hybrid solution HCAGORDIAN combines the advantages of GORDIAN and our new algorithm HCA, and it significantly outperforms all previous work in many situations.},
  language  = {en}
}
@article{AdnanMatthewsHackletal.2020,
  author    = {Adnan, Hassan Sami and Matthews, Sam and Hackl, M. and Das, P. P. and Manaswini, Manisha and Gadamsetti, S. and Filali, Maroua and Owoyele, Babajide and Santuber, Joaqu{\´i}n and Edelman, Jonathan},
  title     = {Human centered AI design for clinical monitoring and data management},
  series = {European journal of public health : official journal of the European Health Association},
  volume    = {30},
  journal   = {European journal of public health : official journal of the European Health Association},
  number    = {5},
  publisher = {Oxford Univ. Press},
  address   = {Oxford},
  issn      = {1101-1262},
  doi       = {10.1093/eurpub/ckaa165.225},
  pages     = {V86 -- V86},
  year      = {2020},
  abstract  = {In clinical settings, significant resources are spent on data collection and monitoring patients' health parameters to improve decision-making and provide better care. With increased digitization, the healthcare sector is shifting towards implementing digital technologies for data management and in administration. New technologies offer better treatment opportunities and streamline clinical workflow, but the complexity can cause ineffectiveness, frustration, and errors. To address this, we believe digital solutions alone are not sufficient. Therefore, we take a human-centred design approach for AI development, and apply systems engineering methods to identify system leverage points. We demonstrate how automation enables monitoring clinical parameters, using existing non-intrusive sensor technology, resulting in more resources toward patient care. Furthermore, we provide a framework on digitization of clinical data for integration with data management.},
  language  = {en}
}
@article{AdnanSrsicVenticichetal.2020,
  author    = {Adnan, Hassan Sami and Srsic, Amanda and Venticich, Pete Milos and Townend, David M.R.},
  title     = {Using AI for mental health analysis and prediction in school surveys},
  series = {European journal of public health},
  volume    = {30},
  journal   = {European journal of public health},
  publisher = {Oxford Univ. Press},
  address   = {Oxford [u.a.]},
  issn      = {1101-1262},
  doi       = {10.1093/eurpub/ckaa165.336},
  pages     = {V125 -- V125},
  year      = {2020},
  abstract  = {Background: Childhood and adolescence are critical stages of life for mental health and well-being. Schools are a key setting for mental health promotion and illness prevention. One in five children and adolescents have a mental disorder, about half of mental disorders beginning before the age of 14. Beneficial and explainable artificial intelligence can replace current paper- based and online approaches to school mental health surveys. This can enhance data acquisition, interoperability, data driven analysis, trust and compliance. This paper presents a model for using chatbots for non-obtrusive data collection and supervised machine learning models for data analysis; and discusses ethical considerations pertaining to the use of these models. Methods: For data acquisition, the proposed model uses chatbots which interact with students. The conversation log acts as the source of raw data for the machine learning. Pre-processing of the data is automated by filtering for keywords and phrases. Existing survey results, obtained through current paper-based data collection methods, are evaluated by domain experts (health professionals). These can be used to create a test dataset to validate the machine learning models. Supervised learning can then be deployed to classify specific behaviour and mental health patterns. Results: We present a model that can be used to improve upon current paper-based data collection and manual data analysis methods. An open-source GitHub repository contains necessary tools and components of this model. Privacy is respected through rigorous observance of confidentiality and data protection requirements. Critical reflection on these ethics and law aspects is included in the project. Conclusions: This model strengthens mental health surveillance in schools. The same tools and components could be applied to other public health data. Future extensions of this model could also incorporate unsupervised learning to find clusters and patterns of unknown effects.},
  language  = {en}
}
@book{AlbrechtNaumann2012,
  author    = {Albrecht, Alexander and Naumann, Felix},
  title     = {Understanding cryptic schemata in large extract-transform-load systems},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-201-8},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-61257},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {19},
  year      = {2012},
  abstract  = {Extract-Transform-Load (ETL) tools are used for the creation, maintenance, and evolution of data warehouses, data marts, and operational data stores. ETL workflows populate those systems with data from various data sources by specifying and executing a DAG of transformations. Over time, hundreds of individual workflows evolve as new sources and new requirements are integrated into the system. The maintenance and evolution of large-scale ETL systems requires much time and manual effort. A key problem is to understand the meaning of unfamiliar attribute labels in source and target databases and ETL transformations. Hard-to-understand attribute labels lead to frustration and time spent to develop and understand ETL workflows. We present a schema decryption technique to support ETL developers in understanding cryptic schemata of sources, targets, and ETL transformations. For a given ETL system, our recommender-like approach leverages the large number of mapped attribute labels in existing ETL workflows to produce good and meaningful decryptions. In this way we are able to decrypt attribute labels consisting of a number of unfamiliar few-letter abbreviations, such as UNP_PEN_INT, which we can decrypt to UNPAID_PENALTY_INTEREST. We evaluate our schema decryption approach on three real-world repositories of ETL workflows and show that our approach is able to suggest high-quality decryptions for cryptic attribute labels in a given schema.},
  language  = {en}
}
@misc{AlibabaieGhasemzadehMeinel2017,
  author    = {Alibabaie, Najmeh and Ghasemzadeh, Mohammad and Meinel, Christoph},
  title     = {A variant of genetic algorithm for non-homogeneous population},
  series = {International Conference Applied Mathematics, Computational Science and Systems Engineering 2016},
  volume    = {9},
  journal   = {International Conference Applied Mathematics, Computational Science and Systems Engineering 2016},
  publisher = {EDP Sciences},
  address   = {Les Ulis},
  issn      = {2271-2097},
  doi       = {10.1051/itmconf/20170902001},
  pages     = {8},
  year      = {2017},
  abstract  = {Selection of initial points, the number of clusters and finding proper clusters centers are still the main challenge in clustering processes. In this paper, we suggest genetic algorithm based method which searches several solution spaces simultaneously. The solution spaces are population groups consisting of elements with similar structure. Elements in a group have the same size, while elements in different groups are of different sizes. The proposed algorithm processes the population in groups of chromosomes with one gene, two genes to k genes. These genes hold corresponding information about the cluster centers. In the proposed method, the crossover and mutation operators can accept parents with different sizes; this can lead to versatility in population and information transfer among sub-populations. We implemented the proposed method and evaluated its performance against some random datasets and the Ruspini dataset as well. The experimental results show that the proposed method could effectively determine the appropriate number of clusters and recognize their centers. Overall this research implies that using heterogeneous population in the genetic algorithm can lead to better results.},
  language  = {en}
}
@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{AlSa'dehMeinel2012,
  author    = {AlSa'deh, Ahmad and Meinel, Christoph},
  title     = {Secure neighbor discovery Review, challenges, perspectives, and recommendations},
  series = {IEEE security \& privacy : building confidence in a networked world},
  volume    = {10},
  journal   = {IEEE security \& privacy : building confidence in a networked world},
  number    = {4},
  publisher = {Inst. of Electr. and Electronics Engineers},
  address   = {Los Alamitos},
  issn      = {1540-7993},
  pages     = {26 -- 34},
  year      = {2012},
  abstract  = {Secure Neighbor Discovery is designed as a countermeasure to Neighbor Discovery Protocol threats. The authors discuss Secure Neighbor Discovery implementation and deployment challenges and review proposals to optimize it.},
  language  = {en}
}
@article{AndreeIhdeWeskeetal.2022,
  author    = {Andree, Kerstin and Ihde, Sven and Weske, Mathias and Pufahl, Luise},
  title     = {An exception handling framework for case management},
  series = {Software and Systems Modeling},
  volume    = {21},
  journal   = {Software and Systems Modeling},
  number    = {3},
  publisher = {Springer},
  address   = {Heidelberg},
  issn      = {1619-1366},
  doi       = {10.1007/s10270-022-00993-3},
  pages     = {939 -- 962},
  year      = {2022},
  abstract  = {In order to achieve their business goals, organizations heavily rely on the operational excellence of their business processes. In traditional scenarios, business processes are usually well-structured, clearly specifying when and how certain tasks have to be executed. Flexible and knowledge-intensive processes are gathering momentum, where a knowledge worker drives the execution of a process case and determines the exact process path at runtime. In the case of an exception, the knowledge worker decides on an appropriate handling. While there is initial work on exception handling in well-structured business processes, exceptions in case management have not been sufficiently researched. This paper proposes an exception handling framework for stage-oriented case management languages, namely Guard Stage Milestone Model, Case Management Model and Notation, and Fragment-based Case Management. The effectiveness of the framework is evaluated with two real-world use cases showing that it covers all relevant exceptions and proposed handling strategies.},
  language  = {en}
}
@book{AppeltauerHirschfeld2012,
  author    = {Appeltauer, Malte and Hirschfeld, Robert},
  title     = {The JCop language specification : Version 1.0, April 2012},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-193-6},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-60208},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {iv, 48},
  year      = {2012},
  abstract  = {Program behavior that relies on contextual information, such as physical location or network accessibility, is common in today's applications, yet its representation is not sufficiently supported by programming languages. With context-oriented programming (COP), such context-dependent behavioral variations can be explicitly modularized and dynamically activated. In general, COP could be used to manage any context-specific behavior. However, its contemporary realizations limit the control of dynamic adaptation. This, in turn, limits the interaction of COP's adaptation mechanisms with widely used architectures, such as event-based, mobile, and distributed programming. The JCop programming language extends Java with language constructs for context-oriented programming and additionally provides a domain-specific aspect language for declarative control over runtime adaptations. As a result, these redesigned implementations are more concise and better modularized than their counterparts using plain COP. JCop's main features have been described in our previous publications. However, a complete language specification has not been presented so far. This report presents the entire JCop language including the syntax and semantics of its new language constructs.},
  language  = {en}
}
@phdthesis{Awad2010,
  author    = {Awad, Ahmed Mahmoud Hany Aly},
  title     = {A compliance management framework for business process models},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-49222},
  school      = {Universit{\"a}t Potsdam},
  year      = {2010},
  abstract  = {Companies develop process models to explicitly describe their business operations. In the same time, business operations, business processes, must adhere to various types of compliance requirements. Regulations, e.g., Sarbanes Oxley Act of 2002, internal policies, best practices are just a few sources of compliance requirements. In some cases, non-adherence to compliance requirements makes the organization subject to legal punishment. In other cases, non-adherence to compliance leads to loss of competitive advantage and thus loss of market share. Unlike the classical domain-independent behavioral correctness of business processes, compliance requirements are domain-specific. Moreover, compliance requirements change over time. New requirements might appear due to change in laws and adoption of new policies. Compliance requirements are offered or enforced by different entities that have different objectives behind these requirements. Finally, compliance requirements might affect different aspects of business processes, e.g., control flow and data flow. As a result, it is infeasible to hard-code compliance checks in tools. Rather, a repeatable process of modeling compliance rules and checking them against business processes automatically is needed. This thesis provides a formal approach to support process design-time compliance checking. Using visual patterns, it is possible to model compliance requirements concerning control flow, data flow and conditional flow rules. Each pattern is mapped into a temporal logic formula. The thesis addresses the problem of consistency checking among various compliance requirements, as they might stem from divergent sources. Also, the thesis contributes to automatically check compliance requirements against process models using model checking. We show that extra domain knowledge, other than expressed in compliance rules, is needed to reach correct decisions. In case of violations, we are able to provide a useful feedback to the user. The feedback is in the form of parts of the process model whose execution causes the violation. In some cases, our approach is capable of providing automated remedy of the violation.},
  language  = {en}
}
@article{AwadWeidlichWeske2011,
  author    = {Awad, Ahmed Mahmoud Hany Aly and Weidlich, Matthias and Weske, Mathias},
  title     = {Visually specifying compliance rules and explaining their violations for business processes},
  series = {Journal of visual languages and computing},
  volume    = {22},
  journal   = {Journal of visual languages and computing},
  number    = {1},
  publisher = {Elsevier},
  address   = {London},
  issn      = {1045-926X},
  doi       = {10.1016/j.jvlc.2010.11.002},
  pages     = {30 -- 55},
  year      = {2011},
  abstract  = {A business process is a set of steps designed to be executed in a certain order to achieve a business value. Such processes are often driven by and documented using process models. Nowadays, process models are also applied to drive process execution. Thus, correctness of business process models is a must. Much of the work has been devoted to check general, domain-independent correctness criteria, such as soundness. However, business processes must also adhere to and show compliance with various regulations and constraints, the so-called compliance requirements. These are domain-dependent requirements. In many situations, verifying compliance on a model level is of great value, since violations can be resolved in an early stage prior to execution. However, this calls for using formal verification techniques, e.g., model checking, that are too complex for business experts to apply. In this paper, we utilize a visual language. BPMN-Q to express compliance requirements visually in a way similar to that used by business experts to build process models. Still, using a pattern based approach, each BPMN-Qgraph has a formal temporal logic expression in computational tree logic (CTL). Moreover, the user is able to express constraints, i.e., compliance rules, regarding control flow and data flow aspects. In order to provide valuable feedback to a user in case of violations, we depend on temporal logic querying approaches as well as BPMN-Q to visually highlight paths in a process model whose execution causes violations.},
  language  = {en}
}
@article{AzodiChengMeinel2015,
  author    = {Azodi, Amir and Cheng, Feng and Meinel, Christoph},
  title     = {Event Driven Network Topology Discovery and Inventory Listing Using REAMS},
  series = {Wireless personal communications : an international journal},
  volume    = {94},
  journal   = {Wireless personal communications : an international journal},
  publisher = {Springer},
  address   = {New York},
  issn      = {0929-6212},
  doi       = {10.1007/s11277-015-3061-3},
  pages     = {415 -- 430},
  year      = {2015},
  abstract  = {Network Topology Discovery and Inventory Listing are two of the primary features of modern network monitoring systems (NMS). Current NMSs rely heavily on active scanning techniques for discovering and mapping network information. Although this approach works, it introduces some major drawbacks such as the performance impact it can exact, specially in larger network environments. As a consequence, scans are often run less frequently which can result in stale information being presented and used by the network monitoring system. Alternatively, some NMSs rely on their agents being deployed on the hosts they monitor. In this article, we present a new approach to Network Topology Discovery and Network Inventory Listing using only passive monitoring and scanning techniques. The proposed techniques rely solely on the event logs produced by the hosts and network devices present within a network. Finally, we discuss some of the advantages and disadvantages of our approach.},
  language  = {en}
}
@phdthesis{Baier2015,
  author    = {Baier, Thomas},
  title     = {Matching events and activities},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-84548},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xxii, 213},
  year      = {2015},
  abstract  = {Nowadays, business processes are increasingly supported by IT services that produce massive amounts of event data during process execution. Aiming at a better process understanding and improvement, this event data can be used to analyze processes using process mining techniques. Process models can be automatically discovered and the execution can be checked for conformance to specified behavior. Moreover, existing process models can be enhanced and annotated with valuable information, for example for performance analysis. While the maturity of process mining algorithms is increasing and more tools are entering the market, process mining projects still face the problem of different levels of abstraction when comparing events with modeled business activities. Mapping the recorded events to activities of a given process model is essential for conformance checking, annotation and understanding of process discovery results. Current approaches try to abstract from events in an automated way that does not capture the required domain knowledge to fit business activities. Such techniques can be a good way to quickly reduce complexity in process discovery. Yet, they fail to enable techniques like conformance checking or model annotation, and potentially create misleading process discovery results by not using the known business terminology. In this thesis, we develop approaches that abstract an event log to the same level that is needed by the business. Typically, this abstraction level is defined by a given process model. Thus, the goal of this thesis is to match events from an event log to activities in a given process model. To accomplish this goal, behavioral and linguistic aspects of process models and event logs as well as domain knowledge captured in existing process documentation are taken into account to build semiautomatic matching approaches. The approaches establish a pre--processing for every available process mining technique that produces or annotates a process model, thereby reducing the manual effort for process analysts. While each of the presented approaches can be used in isolation, we also introduce a general framework for the integration of different matching approaches. The approaches have been evaluated in case studies with industry and using a large industry process model collection and simulated event logs. The evaluation demonstrates the effectiveness and efficiency of the approaches and their robustness towards nonconforming execution logs.},
  language  = {en}
}
@article{BanoMichaelRumpeetal.2022,
  author    = {Bano, Dorina and Michael, Judith and Rumpe, Bernhard and Varga, Simon and Weske, Mathias},
  title     = {Process-aware digital twin cockpit synthesis from event logs},
  series = {Journal of computer languages},
  volume    = {70},
  journal   = {Journal of computer languages},
  publisher = {Elsevier},
  address   = {Amsterdam [u.a.]},
  issn      = {2590-1184},
  doi       = {10.1016/j.cola.2022.101121},
  pages     = {19},
  year      = {2022},
  abstract  = {The engineering of digital twins and their user interaction parts with explicated processes, namely processaware digital twin cockpits (PADTCs), is challenging due to the complexity of the systems and the need for information from different disciplines within the engineering process. Therefore, it is interesting to investigate how to facilitate their engineering by using already existing data, namely event logs, and reducing the number of manual steps for their engineering. Current research lacks systematic, automated approaches to derive process-aware digital twin cockpits even though some helpful techniques already exist in the areas of process mining and software engineering. Within this paper, we present a low-code development approach that reduces the amount of hand-written code needed and uses process mining techniques to derive PADTCs. We describe what models could be derived from event log data, which generative steps are needed for the engineering of PADTCs, and how process mining could be incorporated into the resulting application. This process is evaluated using the MIMIC III dataset for the creation of a PADTC prototype for an automated hospital transportation system. This approach can be used for early prototyping of PADTCs as it needs no hand-written code in the first place, but it still allows for the iterative evolvement of the application. This empowers domain experts to create their PADTC prototypes.},
  language  = {en}
}
@article{BarkowskyGiese2020,
  author    = {Barkowsky, Matthias and Giese, Holger},
  title     = {Hybrid search plan generation for generalized graph pattern matching},
  series = {Journal of logical and algebraic methods in programming},
  volume    = {114},
  journal   = {Journal of logical and algebraic methods in programming},
  publisher = {Elsevier},
  address   = {New York},
  issn      = {2352-2208},
  doi       = {10.1016/j.jlamp.2020.100563},
  pages     = {29},
  year      = {2020},
  abstract  = {In recent years, the increased interest in application areas such as social networks has resulted in a rising popularity of graph-based approaches for storing and processing large amounts of interconnected data. To extract useful information from the growing network structures, efficient querying techniques are required. In this paper, we propose an approach for graph pattern matching that allows a uniform handling of arbitrary constraints over the query vertices. Our technique builds on a previously introduced matching algorithm, which takes concrete host graph information into account to dynamically adapt the employed search plan during query execution. The dynamic algorithm is combined with an existing static approach for search plan generation, resulting in a hybrid technique which we further extend by a more sophisticated handling of filtering effects caused by constraint checks. We evaluate the presented concepts empirically based on an implementation for our graph pattern matching tool, the Story Diagram Interpreter, with queries and data provided by the LDBC Social Network Benchmark. Our results suggest that the hybrid technique may improve search efficiency in several cases, and rarely reduces efficiency.},
  language  = {en}
}
@misc{BartzYangBethgeetal.2019,
  author    = {Bartz, Christian and Yang, Haojin and Bethge, Joseph and Meinel, Christoph},
  title     = {LoANs},
  series = {Computer Vision - ACCV 2018 Workshops},
  volume    = {11367},
  journal   = {Computer Vision - ACCV 2018 Workshops},
  publisher = {Springer},
  address   = {Cham},
  isbn      = {978-3-030-21074-8},
  issn      = {0302-9743},
  doi       = {10.1007/978-3-030-21074-8_29},
  pages     = {341 -- 356},
  year      = {2019},
  abstract  = {Recently, deep neural networks have achieved remarkable performance on the task of object detection and recognition. The reason for this success is mainly grounded in the availability of large scale, fully annotated datasets, but the creation of such a dataset is a complicated and costly task. In this paper, we propose a novel method for weakly supervised object detection that simplifies the process of gathering data for training an object detector. We train an ensemble of two models that work together in a student-teacher fashion. Our student (localizer) is a model that learns to localize an object, the teacher (assessor) assesses the quality of the localization and provides feedback to the student. The student uses this feedback to learn how to localize objects and is thus entirely supervised by the teacher, as we are using no labels for training the localizer. In our experiments, we show that our model is very robust to noise and reaches competitive performance compared to a state-of-the-art fully supervised approach. We also show the simplicity of creating a new dataset, based on a few videos (e.g. downloaded from YouTube) and artificially generated data.},
  language  = {en}
}
@phdthesis{Bauckmann2013,
  author    = {Bauckmann, Jana},
  title     = {Dependency discovery for data integration},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-66645},
  school      = {Universit{\"a}t Potsdam},
  year      = {2013},
  abstract  = {Data integration aims to combine data of different sources and to provide users with a unified view on these data. This task is as challenging as valuable. In this thesis we propose algorithms for dependency discovery to provide necessary information for data integration. We focus on inclusion dependencies (INDs) in general and a special form named conditional inclusion dependencies (CINDs): (i) INDs enable the discovery of structure in a given schema. (ii) INDs and CINDs support the discovery of cross-references or links between schemas. An IND "A in B" simply states that all values of attribute A are included in the set of values of attribute B. We propose an algorithm that discovers all inclusion dependencies in a relational data source. The challenge of this task is the complexity of testing all attribute pairs and further of comparing all of each attribute pair's values. The complexity of existing approaches depends on the number of attribute pairs, while ours depends only on the number of attributes. Thus, our algorithm enables to profile entirely unknown data sources with large schemas by discovering all INDs. Further, we provide an approach to extract foreign keys from the identified INDs. We extend our IND discovery algorithm to also find three special types of INDs: (i) Composite INDs, such as "AB in CD", (ii) approximate INDs that allow a certain amount of values of A to be not included in B, and (iii) prefix and suffix INDs that represent special cross-references between schemas. Conditional inclusion dependencies are inclusion dependencies with a limited scope defined by conditions over several attributes. Only the matching part of the instance must adhere the dependency. We generalize the definition of CINDs distinguishing covering and completeness conditions and define quality measures for conditions. We propose efficient algorithms that identify covering and completeness conditions conforming to given quality thresholds. The challenge for this task is twofold: (i) Which (and how many) attributes should be used for the conditions? (ii) Which attribute values should be chosen for the conditions? Previous approaches rely on pre-selected condition attributes or can only discover conditions applying to quality thresholds of 100\%. Our approaches were motivated by two application domains: data integration in the life sciences and link discovery for linked open data. We show the efficiency and the benefits of our approaches for use cases in these domains.},
  language  = {en}
}
@book{BauckmannAbedjanLeseretal.2012,
  author    = {Bauckmann, Jana and Abedjan, Ziawasch and Leser, Ulf and M{\"u}ller, Heiko and Naumann, Felix},
  title     = {Covering or complete? : Discovering conditional inclusion dependencies},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-212-4},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-62089},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {34},
  year      = {2012},
  abstract  = {Data dependencies, or integrity constraints, are used to improve the quality of a database schema, to optimize queries, and to ensure consistency in a database. In the last years conditional dependencies have been introduced to analyze and improve data quality. In short, a conditional dependency is a dependency with a limited scope defined by conditions over one or more attributes. Only the matching part of the instance must adhere to the dependency. In this paper we focus on conditional inclusion dependencies (CINDs). We generalize the definition of CINDs, distinguishing covering and completeness conditions. We present a new use case for such CINDs showing their value for solving complex data quality tasks. Further, we define quality measures for conditions inspired by precision and recall. We propose efficient algorithms that identify covering and completeness conditions conforming to given quality thresholds. Our algorithms choose not only the condition values but also the condition attributes automatically. Finally, we show that our approach efficiently provides meaningful and helpful results for our use case.},
  language  = {en}
}
@book{BauckmannLeserNaumann2010,
  author    = {Bauckmann, Jana and Leser, Ulf and Naumann, Felix},
  title     = {Efficient and exact computation of inclusion dependencies for data integration},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-048-9},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-41396},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {36},
  year      = {2010},
  abstract  = {Data obtained from foreign data sources often come with only superficial structural information, such as relation names and attribute names. Other types of metadata that are important for effective integration and meaningful querying of such data sets are missing. In particular, relationships among attributes, such as foreign keys, are crucial metadata for understanding the structure of an unknown database. The discovery of such relationships is difficult, because in principle for each pair of attributes in the database each pair of data values must be compared. A precondition for a foreign key is an inclusion dependency (IND) between the key and the foreign key attributes. We present with Spider an algorithm that efficiently finds all INDs in a given relational database. It leverages the sorting facilities of DBMS but performs the actual comparisons outside of the database to save computation. Spider analyzes very large databases up to an order of magnitude faster than previous approaches. We also evaluate in detail the effectiveness of several heuristics to reduce the number of necessary comparisons. Furthermore, we generalize Spider to find composite INDs covering multiple attributes, and partial INDs, which are true INDs for all but a certain number of values. This last type is particularly relevant when integrating dirty data as is often the case in the life sciences domain - our driving motivation.},
  language  = {en}
}
@article{BaudischSilberKommanaetal.2019,
  author    = {Baudisch, Patrick Markus and Silber, Arthur and Kommana, Yannis and Gruner, Milan and Wall, Ludwig and Reuss, Kevin and Heilman, Lukas and Kovacs, Robert and Rechlitz, Daniel and Roumen, Thijs},
  title     = {Kyub},
  series = {Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems},
  journal   = {Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems},
  publisher = {Association for Computing Machinery},
  address   = {New York},
  isbn      = {978-1-4503-5970-2},
  doi       = {10.1145/3290605.3300796},
  pages     = {1 -- 12},
  year      = {2019},
  abstract  = {We present an interactive editing system for laser cutting called kyub. Kyub allows users to create models efficiently in 3D, which it then unfolds into the 2D plates laser cutters expect. Unlike earlier systems, such as FlatFitFab, kyub affords construction based on closed box structures, which allows users to turn very thin material, such as 4mm plywood, into objects capable of withstanding large forces, such as chairs users can actually sit on. To afford such sturdy construction, every kyub project begins with a simple finger-joint "boxel"-a structure we found to be capable of withstanding over 500kg of load. Users then extend their model by attaching additional boxels. Boxels merge automatically, resulting in larger, yet equally strong structures. While the concept of stacking boxels allows kyub to offer the strong affordance and ease of use of a voxel-based editor, boxels are not confined to a grid and readily combine with kuyb's various geometry deformation tools. In our technical evaluation, objects built with kyub withstood hundreds of kilograms of loads. In our user study, non-engineers rated the learnability of kyub 6.1/7.},
  language  = {en}
}
@incollection{BauerMalchowMeinel2019,
  author    = {Bauer, Matthias and Malchow, Martin and Meinel, Christoph},
  title     = {Full Lecture Recording Watching Behavior, or Why Students Watch 90-Min Lectures in 5 Min},
  series = {IMCL 2018: Mobile Technologies and Applications for the Internet of Things},
  volume    = {909},
  booktitle = {IMCL 2018: Mobile Technologies and Applications for the Internet of Things},
  publisher = {Springer},
  address   = {Cham},
  isbn      = {978-3-030-11434-3},
  issn      = {2194-5357},
  doi       = {10.1007/978-3-030-11434-3_38},
  pages     = {347 -- 358},
  year      = {2019},
  abstract  = {Many universities record the lectures being held in their facilities to preserve knowledge and to make it available to their students and, at least for some universities and classes, to the broad public. The way with the least effort is to record the whole lecture, which in our case usually is 90 min long. This saves the labor and time of cutting and rearranging lectures scenes to provide short learning videos as known from Massive Open Online Courses (MOOCs), etc. Many lecturers fear that recording their lectures and providing them via an online platform might lead to less participation in the actual lecture. Also, many teachers fear that the lecture recordings are not used with the same focus and dedication as lectures in a lecture hall. In this work, we show that in our experience, full lectures have an average watching duration of just a few minutes and explain the reasons for that and why, in most cases, teachers do not have to worry about that.},
  language  = {en}
}
@article{BaumanBolzHirschfeldetal.2015,
  author    = {Bauman, Spenser and Bolz, Carl Friedrich and Hirschfeld, Robert and Kirilichev, Vasily and Pape, Tobias and Siek, Jeremy G. and Tobin-Hochstadt, Sam},
  title     = {Pycket: A Tracing JIT for a Functional Language},
  series = {ACM SIGPLAN notices},
  volume    = {50},
  journal   = {ACM SIGPLAN notices},
  number    = {9},
  publisher = {Association for Computing Machinery},
  address   = {New York},
  issn      = {0362-1340},
  doi       = {10.1145/2784731.2784740},
  pages     = {22 -- 34},
  year      = {2015},
  abstract  = {We present Pycket, a high-performance tracing JIT compiler for Racket. Pycket supports a wide variety of the sophisticated features in Racket such as contracts, continuations, classes, structures, dynamic binding, and more. On average, over a standard suite of benchmarks, Pycket outperforms existing compilers, both Racket's JIT and other highly-optimizing Scheme compilers. Further, Pycket provides much better performance for Racket proxies than existing systems, dramatically reducing the overhead of contracts and gradual typing. We validate this claim with performance evaluation on multiple existing benchmark suites. The Pycket implementation is of independent interest as an application of the RPython meta-tracing framework (originally created for PyPy), which automatically generates tracing JIT compilers from interpreters. Prior work on meta-tracing focuses on bytecode interpreters, whereas Pycket is a high-level interpreter based on the CEK abstract machine and operates directly on abstract syntax trees. Pycket supports proper tail calls and first-class continuations. In the setting of a functional language, where recursion and higher-order functions are more prevalent than explicit loops, the most significant performance challenge for a tracing JIT is identifying which control flows constitute a loop-we discuss two strategies for identifying loops and measure their impact.},
  language  = {en}
}
@phdthesis{Becker2013,
  author    = {Becker, Basil},
  title     = {Architectural modelling and verification of open service-oriented systems of systems},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-70158},
  school      = {Universit{\"a}t Potsdam},
  year      = {2013},
  abstract  = {Systems of Systems (SoS) have received a lot of attention recently. In this thesis we will focus on SoS that are built atop the techniques of Service-Oriented Architectures and thus combine the benefits and challenges of both paradigms. For this thesis we will understand SoS as ensembles of single autonomous systems that are integrated to a larger system, the SoS. The interesting fact about these systems is that the previously isolated systems are still maintained, improved and developed on their own. Structural dynamics is an issue in SoS, as at every point in time systems can join and leave the ensemble. This and the fact that the cooperation among the constituent systems is not necessarily observable means that we will consider these systems as open systems. Of course, the system has a clear boundary at each point in time, but this can only be identified by halting the complete SoS. However, halting a system of that size is practically impossible. Often SoS are combinations of software systems and physical systems. Hence a failure in the software system can have a serious physical impact what makes an SoS of this kind easily a safety-critical system. The contribution of this thesis is a modelling approach that extends OMG's SoaML and basically relies on collaborations and roles as an abstraction layer above the components. This will allow us to describe SoS at an architectural level. We will also give a formal semantics for our modelling approach which employs hybrid graph-transformation systems. The modelling approach is accompanied by a modular verification scheme that will be able to cope with the complexity constraints implied by the SoS' structural dynamics and size. Building such autonomous systems as SoS without evolution at the architectural level --- i. e. adding and removing of components and services --- is inadequate. Therefore our approach directly supports the modelling and verification of evolution.},
  language  = {en}
}
@book{BeckerGiese2012,
  author    = {Becker, Basil and Giese, Holger},
  title     = {Cyber-physical systems with dynamic structure : towards modeling and verification of inductive invariants},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-217-9},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-62437},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {iv, 27},
  year      = {2012},
  abstract  = {Cyber-physical systems achieve sophisticated system behavior exploring the tight interconnection of physical coupling present in classical engineering systems and information technology based coupling. A particular challenging case are systems where these cyber-physical systems are formed ad hoc according to the specific local topology, the available networking capabilities, and the goals and constraints of the subsystems captured by the information processing part. In this paper we present a formalism that permits to model the sketched class of cyber-physical systems. The ad hoc formation of tightly coupled subsystems of arbitrary size are specified using a UML-based graph transformation system approach. Differential equations are employed to define the resulting tightly coupled behavior. Together, both form hybrid graph transformation systems where the graph transformation rules define the discrete steps where the topology or modes may change, while the differential equations capture the continuous behavior in between such discrete changes. In addition, we demonstrate that automated analysis techniques known for timed graph transformation systems for inductive invariants can be extended to also cover the hybrid case for an expressive case of hybrid models where the formed tightly coupled subsystems are restricted to smaller local networks.},
  language  = {en}
}
@book{BeckerGieseNeumann2009,
  author    = {Becker, Basil and Giese, Holger and Neumann, Stefan},
  title     = {Correct dynamic service-oriented architectures : modeling and compositional verification with dynamic collaborations},
  organization    = {System Analysis and Modeling Group},
  isbn      = {978-3-940793-91-1},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-30473},
  publisher      = {Universit{\"a}t Potsdam},
  year      = {2009},
  abstract  = {Service-oriented modeling employs collaborations to capture the coordination of multiple roles in form of service contracts. In case of dynamic collaborations the roles may join and leave the collaboration at runtime and therefore complex structural dynamics can result, which makes it very hard to ensure their correct and safe operation. We present in this paper our approach for modeling and verifying such dynamic collaborations. Modeling is supported using a well-defined subset of UML class diagrams, behavioral rules for the structural dynamics, and UML state machines for the role behavior. To be also able to verify the resulting service-oriented systems, we extended our former results for the automated verification of systems with structural dynamics [7, 8] and developed a compositional reasoning scheme, which enables the reuse of verification results. We outline our approach using the example of autonomous vehicles that use such dynamic collaborations via ad-hoc networking to coordinate and optimize their joint behavior.},
  language  = {en}
}
@phdthesis{Berg2013,
  author    = {Berg, Gregor},
  title     = {Virtual prototypes for the model-based elicitation and validation of collaborative scenarios},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-69729},
  school      = {Universit{\"a}t Potsdam},
  year      = {2013},
  abstract  = {Requirements engineers have to elicit, document, and validate how stakeholders act and interact to achieve their common goals in collaborative scenarios. Only after gathering all information concerning who interacts with whom to do what and why, can a software system be designed and realized which supports the stakeholders to do their work. To capture and structure requirements of different (groups of) stakeholders, scenario-based approaches have been widely used and investigated. Still, the elicitation and validation of requirements covering collaborative scenarios remains complicated, since the required information is highly intertwined, fragmented, and distributed over several stakeholders. Hence, it can only be elicited and validated collaboratively. In times of globally distributed companies, scheduling and conducting workshops with groups of stakeholders is usually not feasible due to budget and time constraints. Talking to individual stakeholders, on the other hand, is feasible but leads to fragmented and incomplete stakeholder scenarios. Going back and forth between different individual stakeholders to resolve this fragmentation and explore uncovered alternatives is an error-prone, time-consuming, and expensive task for the requirements engineers. While formal modeling methods can be employed to automatically check and ensure consistency of stakeholder scenarios, such methods introduce additional overhead since their formal notations have to be explained in each interaction between stakeholders and requirements engineers. Tangible prototypes as they are used in other disciplines such as design, on the other hand, allow designers to feasibly validate and iterate concepts and requirements with stakeholders. This thesis proposes a model-based approach for prototyping formal behavioral specifications of stakeholders who are involved in collaborative scenarios. By simulating and animating such specifications in a remote domain-specific visualization, stakeholders can experience and validate the scenarios captured so far, i.e., how other stakeholders act and react. This interactive scenario simulation is referred to as a model-based virtual prototype. Moreover, through observing how stakeholders interact with a virtual prototype of their collaborative scenarios, formal behavioral specifications can be automatically derived which complete the otherwise fragmented scenarios. This, in turn, enables requirements engineers to elicit and validate collaborative scenarios in individual stakeholder sessions - decoupled, since stakeholders can participate remotely and are not forced to be available for a joint session at the same time. This thesis discusses and evaluates the feasibility, understandability, and modifiability of model-based virtual prototypes. Similarly to how physical prototypes are perceived, the presented approach brings behavioral models closer to being tangible for stakeholders and, moreover, combines the advantages of joint stakeholder sessions and decoupled sessions.},
  language  = {en}
}
@phdthesis{Beyhl2017,
  author    = {Beyhl, Thomas},
  title     = {A framework for incremental view graph maintenance},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-405929},
  school      = {Universit{\"a}t Potsdam},
  pages     = {VII, 293},
  year      = {2017},
  abstract  = {Nowadays, graph data models are employed, when relationships between entities have to be stored and are in the scope of queries. For each entity, this graph data model locally stores relationships to adjacent entities. Users employ graph queries to query and modify these entities and relationships. These graph queries employ graph patterns to lookup all subgraphs in the graph data that satisfy certain graph structures. These subgraphs are called graph pattern matches. However, this graph pattern matching is NP-complete for subgraph isomorphism. Thus, graph queries can suffer a long response time, when the number of entities and relationships in the graph data or the graph patterns increases. One possibility to improve the graph query performance is to employ graph views that keep ready graph pattern matches for complex graph queries for later retrieval. However, these graph views must be maintained by means of an incremental graph pattern matching to keep them consistent with the graph data from which they are derived, when the graph data changes. This maintenance adds subgraphs that satisfy a graph pattern to the graph views and removes subgraphs that do not satisfy a graph pattern anymore from the graph views. Current approaches for incremental graph pattern matching employ Rete networks. Rete networks are discrimination networks that enumerate and maintain all graph pattern matches of certain graph queries by employing a network of condition tests, which implement partial graph patterns that together constitute the overall graph query. Each condition test stores all subgraphs that satisfy the partial graph pattern. Thus, Rete networks suffer high memory consumptions, because they store a large number of partial graph pattern matches. But, especially these partial graph pattern matches enable Rete networks to update the stored graph pattern matches efficiently, because the network maintenance exploits the already stored partial graph pattern matches to find new graph pattern matches. However, other kinds of discrimination networks exist that can perform better in time and space than Rete networks. Currently, these other kinds of networks are not used for incremental graph pattern matching. This thesis employs generalized discrimination networks for incremental graph pattern matching. These discrimination networks permit a generalized network structure of condition tests to enable users to steer the trade-off between memory consumption and execution time for the incremental graph pattern matching. For that purpose, this thesis contributes a modeling language for the effective definition of generalized discrimination networks. Furthermore, this thesis contributes an efficient and scalable incremental maintenance algorithm, which updates the (partial) graph pattern matches that are stored by each condition test. Moreover, this thesis provides a modeling evaluation, which shows that the proposed modeling language enables the effective modeling of generalized discrimination networks. Furthermore, this thesis provides a performance evaluation, which shows that a) the incremental maintenance algorithm scales, when the graph data becomes large, and b) the generalized discrimination network structures can outperform Rete network structures in time and space at the same time for incremental graph pattern matching.},
  language  = {en}
}
@book{BeyhlBlouinGieseetal.2016,
  author    = {Beyhl, Thomas and Blouin, Dominique and Giese, Holger and Lambers, Leen},
  title     = {On the operationalization of graph queries with generalized discrimination networks},
  number    = {106},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-372-5},
  issn      = {1613-5652},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-96279},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {33},
  year      = {2016},
  abstract  = {Graph queries have lately gained increased interest due to application areas such as social networks, biological networks, or model queries. For the relational database case the relational algebra and generalized discrimination networks have been studied to find appropriate decompositions into subqueries and ordering of these subqueries for query evaluation or incremental updates of query results. For graph database queries however there is no formal underpinning yet that allows us to find such suitable operationalizations. Consequently, we suggest a simple operational concept for the decomposition of arbitrary complex queries into simpler subqueries and the ordering of these subqueries in form of generalized discrimination networks for graph queries inspired by the relational case. The approach employs graph transformation rules for the nodes of the network and thus we can employ the underlying theory. We further show that the proposed generalized discrimination networks have the same expressive power as nested graph conditions.},
  language  = {en}
}
@book{BeyhlGiese2015,
  author    = {Beyhl, Thomas and Giese, Holger},
  title     = {Efficient and scalable graph view maintenance for deductive graph databases based on generalized discrimination networks},
  number    = {99},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-339-8},
  issn      = {1613-5652},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-79535},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {148},
  year      = {2015},
  abstract  = {Graph databases provide a natural way of storing and querying graph data. In contrast to relational databases, queries over graph databases enable to refer directly to the graph structure of such graph data. For example, graph pattern matching can be employed to formulate queries over graph data. However, as for relational databases running complex queries can be very time-consuming and ruin the interactivity with the database. One possible approach to deal with this performance issue is to employ database views that consist of pre-computed answers to common and often stated queries. But to ensure that database views yield consistent query results in comparison with the data from which they are derived, these database views must be updated before queries make use of these database views. Such a maintenance of database views must be performed efficiently, otherwise the effort to create and maintain views may not pay off in comparison to processing the queries directly on the data from which the database views are derived. At the time of writing, graph databases do not support database views and are limited to graph indexes that index nodes and edges of the graph data for fast query evaluation, but do not enable to maintain pre-computed answers of complex queries over graph data. Moreover, the maintenance of database views in graph databases becomes even more challenging when negation and recursion have to be supported as in deductive relational databases. In this technical report, we present an approach for the efficient and scalable incremental graph view maintenance for deductive graph databases. The main concept of our approach is a generalized discrimination network that enables to model nested graph conditions including negative application conditions and recursion, which specify the content of graph views derived from graph data stored by graph databases. The discrimination network enables to automatically derive generic maintenance rules using graph transformations for maintaining graph views in case the graph data from which the graph views are derived change. We evaluate our approach in terms of a case study using multiple data sets derived from open source projects.},
  language  = {en}
}
@article{BiloLenzner2019,
  author    = {Bil{\`o}, Davide and Lenzner, Pascal},
  title     = {On the tree conjecture for the network creation game},
  series = {Theory of computing systems},
  volume    = {64},
  journal   = {Theory of computing systems},
  number    = {3},
  publisher = {Springer},
  address   = {New York},
  issn      = {1432-4350},
  doi       = {10.1007/s00224-019-09945-9},
  pages     = {422 -- 443},
  year      = {2019},
  abstract  = {Selfish Network Creation focuses on modeling real world networks from a game-theoretic point of view. One of the classic models by Fabrikant et al. (2003) is the network creation game, where agents correspond to nodes in a network which buy incident edges for the price of alpha per edge to minimize their total distance to all other nodes. The model is well-studied but still has intriguing open problems. The most famous conjectures state that the price of anarchy is constant for all alpha and that for alpha >= n all equilibrium networks are trees. We introduce a novel technique for analyzing stable networks for high edge-price alpha and employ it to improve on the best known bound for the latter conjecture. In particular we show that for alpha > 4n - 13 all equilibrium networks must be trees, which implies a constant price of anarchy for this range of alpha. Moreover, we also improve the constant upper bound on the price of anarchy for equilibrium trees.},
  language  = {en}
}
@article{BirnickBlaesiusFriedrichetal.2020,
  author    = {Birnick, Johann and Bl{\"a}sius, Thomas and Friedrich, Tobias and Naumann, Felix and Papenbrock, Thorsten and Schirneck, Friedrich Martin},
  title     = {Hitting set enumeration with partial information for unique column combination discovery},
  series = {Proceedings of the VLDB Endowment},
  volume    = {13},
  journal   = {Proceedings of the VLDB Endowment},
  number    = {11},
  publisher = {Association for Computing Machinery},
  address   = {[New York, NY]},
  issn      = {2150-8097},
  doi       = {10.14778/3407790.3407824},
  pages     = {2270 -- 2283},
  year      = {2020},
  abstract  = {Unique column combinations (UCCs) are a fundamental concept in relational databases. They identify entities in the data and support various data management activities. Still, UCCs are usually not explicitly defined and need to be discovered. State-of-the-art data profiling algorithms are able to efficiently discover UCCs in moderately sized datasets, but they tend to fail on large and, in particular, on wide datasets due to run time and memory limitations. <br /> In this paper, we introduce HPIValid, a novel UCC discovery algorithm that implements a faster and more resource-saving search strategy. HPIValid models the metadata discovery as a hitting set enumeration problem in hypergraphs. In this way, it combines efficient discovery techniques from data profiling research with the most recent theoretical insights into enumeration algorithms. Our evaluation shows that HPIValid is not only orders of magnitude faster than related work, it also has a much smaller memory footprint.},
  language  = {en}
}
@misc{BjoerkHoelze2019,
  author    = {Bj{\"o}rk, Jennie and H{\"o}lze, Katharina},
  title     = {Editorial},
  series = {Creativity and innovation management},
  volume    = {28},
  journal   = {Creativity and innovation management},
  number    = {3},
  publisher = {Wiley},
  address   = {Hoboken},
  issn      = {0963-1690},
  doi       = {10.1111/caim.12336},
  pages     = {289 -- 290},
  year      = {2019},
  language  = {en}
}
@article{BjoerkHoelzleBoer2021,
  author    = {Bj{\"o}rk, Jennie and H{\"o}lzle, Katharina and Boer, Harry},
  title     = {'What will we learn from the current crisis?'},
  series = {Creativity and innovation management},
  volume    = {30},
  journal   = {Creativity and innovation management},
  number    = {2},
  publisher = {Wiley-Blackwell},
  address   = {Oxford [u.a.]},
  issn      = {0963-1690},
  doi       = {10.1111/caim.12442},
  pages     = {231 -- 232},
  year      = {2021},
  language  = {en}
}
@article{BlaesiusFriedrichSchirneck2021,
  author    = {Blaesius, Thomas and Friedrich, Tobias and Schirneck, Friedrich Martin},
  title     = {The complexity of dependency detection and discovery in relational databases},
  series = {Theoretical computer science},
  volume    = {900},
  journal   = {Theoretical computer science},
  publisher = {Elsevier},
  address   = {Amsterdam},
  issn      = {0304-3975},
  doi       = {10.1016/j.tcs.2021.11.020},
  pages     = {79 -- 96},
  year      = {2021},
  abstract  = {Multi-column dependencies in relational databases come associated with two different computational tasks. The detection problem is to decide whether a dependency of a certain type and size holds in a given database, the discovery problem asks to enumerate all valid dependencies of that type. We settle the complexity of both of these problems for unique column combinations (UCCs), functional dependencies (FDs), and inclusion dependencies (INDs). We show that the detection of UCCs and FDs is W[2]-complete when parameterized by the solution size. The discovery of inclusion-wise minimal UCCs is proven to be equivalent under parsimonious reductions to the transversal hypergraph problem of enumerating the minimal hitting sets of a hypergraph. The discovery of FDs is equivalent to the simultaneous enumeration of the hitting sets of multiple input hypergraphs. We further identify the detection of INDs as one of the first natural W[3]-complete problems. The discovery of maximal INDs is shown to be equivalent to enumerating the maximal satisfying assignments of antimonotone, 3-normalized Boolean formulas.},
  language  = {en}
}
@article{BlaesiusFreibergerFriedrichetal.2022,
  author    = {Bl{\"a}sius, Thomas and Freiberger, Cedric and Friedrich, Tobias and Katzmann, Maximilian and Montenegro-Retana, Felix and Thieffry, Marianne},
  title     = {Efficient Shortest Paths in Scale-Free Networks with Underlying Hyperbolic Geometry},
  series = {ACM Transactions on Algorithms},
  volume    = {18},
  journal   = {ACM Transactions on Algorithms},
  number    = {2},
  publisher = {Association for Computing Machinery},
  address   = {New York},
  issn      = {1549-6325},
  doi       = {10.1145/3516483},
  pages     = {1 -- 32},
  year      = {2022},
  abstract  = {A standard approach to accelerating shortest path algorithms on networks is the bidirectional search, which explores the graph from the start and the destination, simultaneously. In practice this strategy performs particularly well on scale-free real-world networks. Such networks typically have a heterogeneous degree distribution (e.g., a power-law distribution) and high clustering (i.e., vertices with a common neighbor are likely to be connected themselves). These two properties can be obtained by assuming an underlying hyperbolic geometry. <br /> To explain the observed behavior of the bidirectional search, we analyze its running time on hyperbolic random graphs and prove that it is (O) over tilde (n(2-1/alpha) + n(1/(2 alpha)) + delta(max)) with high probability, where alpha is an element of (1/2, 1) controls the power-law exponent of the degree distribution, and dmax is the maximum degree. This bound is sublinear, improving the obvious worst-case linear bound. Although our analysis depends on the underlying geometry, the algorithm itself is oblivious to it.},
  language  = {en}
}
@article{BogPlattnerZeier2011,
  author    = {Bog, Anja and Plattner, Hasso and Zeier, Alexander},
  title     = {A mixed transaction processing and operational reporting benchmark},
  series = {Information systems frontiers},
  volume    = {13},
  journal   = {Information systems frontiers},
  number    = {3},
  publisher = {Springer},
  address   = {Dordrecht},
  issn      = {1387-3326},
  doi       = {10.1007/s10796-010-9283-8},
  pages     = {321 -- 335},
  year      = {2011},
  abstract  = {The importance of reporting is ever increasing in today's fast-paced market environments and the availability of up-to-date information for reporting has become indispensable. Current reporting systems are separated from the online transaction processing systems (OLTP) with periodic updates pushed in. A pre-defined and aggregated subset of the OLTP data, however, does not provide the flexibility, detail, and timeliness needed for today's operational reporting. As technology advances, this separation has to be re-evaluated and means to study and evaluate new trends in data storage management have to be provided. This article proposes a benchmark for combined OLTP and operational reporting, providing means to evaluate the performance of enterprise data management systems for mixed workloads of OLTP and operational reporting queries. Such systems offer up-to-date information and the flexibility of the entire data set for reporting. We describe how the benchmark provokes the conflicts that are the reason for separating the two workloads on different systems. In this article, we introduce the concepts, logical data schema, transactions and queries of the benchmark, which are entirely based on the original data sets and real workloads of existing, globally operating enterprises.},
  language  = {en}
}
@article{BohnKundisch2020,
  author    = {Bohn, Nicolai and Kundisch, Dennis},
  title     = {What are we talking about when we talk about technology pivots?},
  series = {Information \& management},
  volume    = {57},
  journal   = {Information \& management},
  number    = {6},
  publisher = {Elsevier},
  address   = {Amsterdam},
  issn      = {0378-7206},
  doi       = {10.1016/j.im.2020.103319},
  pages     = {20},
  year      = {2020},
  abstract  = {Technology pivots were designed to help digital startups make adjustments to the technology underpinning their products and services. While academia and the media make liberal use of the term "technology pivot," they rarely align themselves to Ries' foundational conceptualization. Recent research suggests that a more granulated conceptualization of technology pivots is required. To scientifically derive a comprehensive conceptualization, we conduct a Delphi study with a panel of 38 experts drawn from academia and practice to explore their understanding of "technology pivots." Our study thus makes an important contribution to advance the seminal work by Ries on technology pivots.},
  language  = {en}
}
@article{Boissier2021,
  author    = {Boissier, Martin},
  title     = {Robust and budget-constrained encoding configurations for in-memory database systems},
  series = {Proceedings of the VLDB Endowment},
  volume    = {15},
  journal   = {Proceedings of the VLDB Endowment},
  number    = {4},
  publisher = {Association for Computing Machinery (ACM)},
  address   = {[New York]},
  issn      = {2150-8097},
  doi       = {10.14778/3503585.3503588},
  pages     = {780 -- 793},
  year      = {2021},
  abstract  = {Data encoding has been applied to database systems for decades as it mitigates bandwidth bottlenecks and reduces storage requirements. But even in the presence of these advantages, most in-memory database systems use data encoding only conservatively as the negative impact on runtime performance can be severe. Real-world systems with large parts being infrequently accessed and cost efficiency constraints in cloud environments require solutions that automatically and efficiently select encoding techniques, including heavy-weight compression. In this paper, we introduce workload-driven approaches to automaticaly determine memory budget-constrained encoding configurations using greedy heuristics and linear programming. We show for TPC-H, TPC-DS, and the Join Order Benchmark that optimized encoding configurations can reduce the main memory footprint significantly without a loss in runtime performance over state-of-the-art dictionary encoding. To yield robust selections, we extend the linear programming-based approach to incorporate query runtime constraints and mitigate unexpected performance regressions.},
  language  = {en}
}
@article{BonifatiMiorNaumannetal.2022,
  author    = {Bonifati, Angela and Mior, Michael J. and Naumann, Felix and Noack, Nele Sina},
  title     = {How inclusive are we?},
  series = {SIGMOD record / Association for Computing Machinery, Special Interest Group on Management of Data},
  volume    = {50},
  journal   = {SIGMOD record / Association for Computing Machinery, Special Interest Group on Management of Data},
  number    = {4},
  publisher = {Association for Computing Machinery},
  address   = {New York},
  issn      = {0163-5808},
  doi       = {10.1145/3516431.3516438},
  pages     = {30 -- 35},
  year      = {2022},
  abstract  = {ACM SIGMOD, VLDB and other database organizations have committed to fostering an inclusive and diverse community, as do many other scientific organizations. Recently, different measures have been taken to advance these goals, especially for underrepresented groups. One possible measure is double-blind reviewing, which aims to hide gender, ethnicity, and other properties of the authors. <br /> We report the preliminary results of a gender diversity analysis of publications of the database community across several peer-reviewed venues, and also compare women's authorship percentages in both single-blind and double-blind venues along the years. We also obtained a cross comparison of the obtained results in data management with other relevant areas in Computer Science.},
  language  = {en}
}
@article{BorchertMockTomczaketal.2021,
  author    = {Borchert, Florian and Mock, Andreas and Tomczak, Aurelie and H{\"u}gel, Jonas and Alkarkoukly, Samer and Knurr, Alexander and Volckmar, Anna-Lena and Stenzinger, Albrecht and Schirmacher, Peter and Debus, J{\"u}rgen and J{\"a}ger, Dirk and Longerich, Thomas and Fr{\"o}hling, Stefan and Eils, Roland and Bougatf, Nina and Sax, Ulrich and Schapranow, Matthieu-Patrick},
  title     = {Knowledge bases and software support for variant interpretation in precision oncology},
  series = {Briefings in bioinformatics},
  volume    = {22},
  journal   = {Briefings in bioinformatics},
  number    = {6},
  publisher = {Oxford Univ. Press},
  address   = {Oxford},
  issn      = {1467-5463},
  doi       = {10.1093/bib/bbab134},
  pages     = {17},
  year      = {2021},
  abstract  = {Precision oncology is a rapidly evolving interdisciplinary medical specialty. Comprehensive cancer panels are becoming increasingly available at pathology departments worldwide, creating the urgent need for scalable cancer variant annotation and molecularly informed treatment recommendations. A wealth of mainly academia-driven knowledge bases calls for software tools supporting the multi-step diagnostic process. We derive a comprehensive list of knowledge bases relevant for variant interpretation by a review of existing literature followed by a survey among medical experts from university hospitals in Germany. In addition, we review cancer variant interpretation tools, which integrate multiple knowledge bases. We categorize the knowledge bases along the diagnostic process in precision oncology and analyze programmatic access options as well as the integration of knowledge bases into software tools. The most commonly used knowledge bases provide good programmatic access options and have been integrated into a range of software tools. For the wider set of knowledge bases, access options vary across different parts of the diagnostic process. Programmatic access is limited for information regarding clinical classifications of variants and for therapy recommendations. The main issue for databases used for biological classification of pathogenic variants and pathway context information is the lack of standardized interfaces. There is no single cancer variant interpretation tool that integrates all identified knowledge bases. Specialized tools are available and need to be further developed for different steps in the diagnostic process.},
  language  = {en}
}
@article{BorchertMockTomczaketal.2021,
  author    = {Borchert, Florian and Mock, Andreas and Tomczak, Aurelie and H{\"u}gel, Jonas and Alkarkoukly, Samer and Knurr, Alexander and Volckmar, Anna-Lena and Stenzinger, Albrecht and Schirmacher, Peter and Debus, J{\"u}rgen and J{\"a}ger, Dirk and Longerich, Thomas and Fr{\"o}hling, Stefan and Eils, Roland and Bougatf, Nina and Sax, Ulrich and Schapranow, Matthieu-Patrick},
  title     = {Correction to: Knowledge bases and software support for variant interpretation in precision oncology},
  series = {Briefings in bioinformatics},
  volume    = {22},
  journal   = {Briefings in bioinformatics},
  number    = {6},
  publisher = {Oxford Univ. Press},
  address   = {Oxford},
  issn      = {1467-5463},
  doi       = {10.1093/bib/bbab246},
  pages     = {1},
  year      = {2021},
  language  = {en}
}
@book{BreestBoucheGrundetal.2006,
  author    = {Breest, Martin and Bouch{\´e}, Paul and Grund, Martin and Haubrock, S{\"o}ren and H{\"u}ttenrauch, Stefan and Kylau, Uwe and Ploskonos, Anna and Queck, Tobias and Schreiter, Torben},
  title     = {Fundamentals of Service-Oriented Engineering},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-939469-35-3},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-33801},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {Getr. Z{\"a}hlung},
  year      = {2006},
  abstract  = {Since 2002, keywords like service-oriented engineering, service-oriented computing, and service-oriented architecture have been widely used in research, education, and enterprises. These and related terms are often misunderstood or used incorrectly. To correct these misunderstandings, a deeper knowledge of the concepts, the historical backgrounds, and an overview of service-oriented architectures is demanded and given in this paper.},
  language  = {en}
}
@article{BuchwaldWagelaarDanetal.2014,
  author    = {Buchwald, Sebastian and Wagelaar, Dennis and Dan, Li and Hegedues, Abel and Herrmannsdoerfer, Markus and Horn, Tassilo and Kalnina, Elina and Krause, Christian and Lano, Kevin and Lepper, Markus and Rensink, Arend and Rose, Louis and Waetzoldt, Sebastian and Mazanek, Steffen},
  title     = {A survey and comparison of transformation tools based on the transformation tool contest},
  series = {Science of computer programming},
  volume    = {85},
  journal   = {Science of computer programming},
  publisher = {Elsevier},
  address   = {Amsterdam},
  issn      = {0167-6423},
  doi       = {10.1016/j.scico.2013.10.009},
  pages     = {41 -- 99},
  year      = {2014},
  abstract  = {Model transformation is one of the key tasks in model-driven engineering and relies on the efficient matching and modification of graph-based data structures; its sibling graph rewriting has been used to successfully model problems in a variety of domains. Over the last years, a wide range of graph and model transformation tools have been developed all of them with their own particular strengths and typical application domains. In this paper, we give a survey and a comparison of the model and graph transformation tools that participated at the Transformation Tool Contest 2011. The reader gains an overview of the field and its tools, based on the illustrative solutions submitted to a Hello World task, and a comparison alongside a detailed taxonomy. The article is of interest to researchers in the field of model and graph transformation, as well as to software engineers with a transformation task at hand who have to choose a tool fitting to their needs. All solutions referenced in this article provide a SHARE demo. It supported the peer-review process for the contest, and now allows the reader to test the tools online.},
  language  = {en}
}
@inproceedings{BynensVanLanduytTruyenetal.2010,
  author    = {Bynens, Maarten and Van Landuyt, Dimitri and Truyen, Eddy and Joosen, Wouter},
  title     = {Towards reusable aspects: the callback mismatch problem},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-41347},
  year      = {2010},
  abstract  = {Because software development is increasingly expensive and timeconsuming, software reuse gains importance. Aspect-oriented software development modularizes crosscutting concerns which enables their systematic reuse. Literature provides a number of AOP patterns and best practices for developing reusable aspects based on compelling examples for concerns like tracing, transactions and persistence. However, such best practices are lacking for systematically reusing invasive aspects. In this paper, we present the 'callback mismatch problem'. This problem arises in the context of abstraction mismatch, in which the aspect is required to issue a callback to the base application. As a consequence, the composition of invasive aspects is cumbersome to implement, difficult to maintain and impossible to reuse. We motivate this problem in a real-world example, show that it persists in the current state-of-the-art, and outline the need for advanced aspectual composition mechanisms to deal with this.},
  language  = {en}
}
@phdthesis{Boehm2013,
  author    = {B{\"o}hm, Christoph},
  title     = {Enriching the Web of Data with topics and links},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-68624},
  school      = {Universit{\"a}t Potsdam},
  year      = {2013},
  abstract  = {This thesis presents novel ideas and research findings for the Web of Data - a global data space spanning many so-called Linked Open Data sources. Linked Open Data adheres to a set of simple principles to allow easy access and reuse for data published on the Web. Linked Open Data is by now an established concept and many (mostly academic) publishers adopted the principles building a powerful web of structured knowledge available to everybody. However, so far, Linked Open Data does not yet play a significant role among common web technologies that currently facilitate a high-standard Web experience. In this work, we thoroughly discuss the state-of-the-art for Linked Open Data and highlight several shortcomings - some of them we tackle in the main part of this work. First, we propose a novel type of data source meta-information, namely the topics of a dataset. This information could be published with dataset descriptions and support a variety of use cases, such as data source exploration and selection. For the topic retrieval, we present an approach coined Annotated Pattern Percolation (APP), which we evaluate with respect to topics extracted from Wikipedia portals. Second, we contribute to entity linking research by presenting an optimization model for joint entity linking, showing its hardness, and proposing three heuristics implemented in the LINked Data Alignment (LINDA) system. Our first solution can exploit multi-core machines, whereas the second and third approach are designed to run in a distributed shared-nothing environment. We discuss and evaluate the properties of our approaches leading to recommendations which algorithm to use in a specific scenario. The distributed algorithms are among the first of their kind, i.e., approaches for joint entity linking in a distributed fashion. Also, we illustrate that we can tackle the entity linking problem on the very large scale with data comprising more than 100 millions of entity representations from very many sources. Finally, we approach a sub-problem of entity linking, namely the alignment of concepts. We again target a method that looks at the data in its entirety and does not neglect existing relations. Also, this concept alignment method shall execute very fast to serve as a preprocessing for further computations. Our approach, called Holistic Concept Matching (HCM), achieves the required speed through grouping the input by comparing so-called knowledge representations. Within the groups, we perform complex similarity computations, relation conclusions, and detect semantic contradictions. The quality of our result is again evaluated on a large and heterogeneous dataset from the real Web. In summary, this work contributes a set of techniques for enhancing the current state of the Web of Data. All approaches have been tested on large and heterogeneous real-world input.},
  language  = {en}
}
@article{CabalarKaminskiSchaubetal.2018,
  author    = {Cabalar, Pedro and Kaminski, Roland and Schaub, Torsten H. and Schuhmann, Anna},
  title     = {Temporal answer set programming on finite traces},
  series = {Theory and practice of logic programming},
  volume    = {18},
  journal   = {Theory and practice of logic programming},
  number    = {3-4},
  publisher = {Cambridge Univ. Press},
  address   = {New York},
  issn      = {1471-0684},
  doi       = {10.1017/S1471068418000297},
  pages     = {406 -- 420},
  year      = {2018},
  abstract  = {In this paper, we introduce an alternative approach to Temporal Answer Set Programming that relies on a variation of Temporal Equilibrium Logic (TEL) for finite traces. This approach allows us to even out the expressiveness of TEL over infinite traces with the computational capacity of (incremental) Answer Set Programming (ASP). Also, we argue that finite traces are more natural when reasoning about action and change. As a result, our approach is readily implementable via multi-shot ASP systems and benefits from an extension of ASP's full-fledged input language with temporal operators. This includes future as well as past operators whose combination offers a rich temporal modeling language. For computation, we identify the class of temporal logic programs and prove that it constitutes a normal form for our approach. Finally, we outline two implementations, a generic one and an extension of the ASP system clingo. Under consideration for publication in Theory and Practice of Logic Programming (TPLP)},
  language  = {en}
}
@book{CalmezHesseSiegmundetal.2013,
  author    = {Calmez, Conrad and Hesse, Hubert and Siegmund, Benjamin and Stamm, Sebastian and Thomschke, Astrid and Hirschfeld, Robert and Ingalls, Dan and Lincke, Jens},
  title     = {Explorative authoring of Active Web content in a mobile environment},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-232-2},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-64054},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {132},
  year      = {2013},
  abstract  = {Developing rich Web applications can be a complex job - especially when it comes to mobile device support. Web-based environments such as Lively Webwerkstatt can help developers implement such applications by making the development process more direct and interactive. Further the process of developing software is collaborative which creates the need that the development environment offers collaboration facilities. This report describes extensions of the webbased development environment Lively Webwerkstatt such that it can be used in a mobile environment. The extensions are collaboration mechanisms, user interface adaptations but as well event processing and performance measuring on mobile devices.},
  language  = {en}
}
@article{CaruccioDeufemiaNaumannetal.2021,
  author    = {Caruccio, Loredana and Deufemia, Vincenzo and Naumann, Felix and Polese, Giuseppe},
  title     = {Discovering relaxed functional dependencies based on multi-attribute dominance},
  series = {IEEE transactions on knowledge and data engineering},
  volume    = {33},
  journal   = {IEEE transactions on knowledge and data engineering},
  number    = {9},
  publisher = {Institute of Electrical and Electronics Engineers},
  address   = {New York, NY},
  issn      = {1041-4347},
  doi       = {10.1109/TKDE.2020.2967722},
  pages     = {3212 -- 3228},
  year      = {2021},
  abstract  = {With the advent of big data and data lakes, data are often integrated from multiple sources. Such integrated data are often of poor quality, due to inconsistencies, errors, and so forth. One way to check the quality of data is to infer functional dependencies (fds). However, in many modern applications it might be necessary to extract properties and relationships that are not captured through fds, due to the necessity to admit exceptions, or to consider similarity rather than equality of data values. Relaxed fds (rfds) have been introduced to meet these needs, but their discovery from data adds further complexity to an already complex problem, also due to the necessity of specifying similarity and validity thresholds. We propose Domino, a new discovery algorithm for rfds that exploits the concept of dominance in order to derive similarity thresholds of attribute values while inferring rfds. An experimental evaluation on real datasets demonstrates the discovery performance and the effectiveness of the proposed algorithm.},
  language  = {en}
}