@phdthesis{RoggeSolti2014,
  author    = {Rogge-Solti, Andreas},
  title     = {Probabilistic Estimation of Unobserved Process Events},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-70426},
  school      = {Universit{\"a}t Potsdam},
  year      = {2014},
  abstract  = {Organizations try to gain competitive advantages, and to increase customer satisfaction. To ensure the quality and efficiency of their business processes, they perform business process management. An important part of process management that happens on the daily operational level is process controlling. A prerequisite of controlling is process monitoring, i.e., keeping track of the performed activities in running process instances. Only by process monitoring can business analysts detect delays and react to deviations from the expected or guaranteed performance of a process instance. To enable monitoring, process events need to be collected from the process environment. When a business process is orchestrated by a process execution engine, monitoring is available for all orchestrated process activities. Many business processes, however, do not lend themselves to automatic orchestration, e.g., because of required freedom of action. This situation is often encountered in hospitals, where most business processes are manually enacted. Hence, in practice it is often inefficient or infeasible to document and monitor every process activity. Additionally, manual process execution and documentation is prone to errors, e.g., documentation of activities can be forgotten. Thus, organizations face the challenge of process events that occur, but are not observed by the monitoring environment. These unobserved process events can serve as basis for operational process decisions, even without exact knowledge of when they happened or when they will happen. An exemplary decision is whether to invest more resources to manage timely completion of a case, anticipating that the process end event will occur too late. This thesis offers means to reason about unobserved process events in a probabilistic way. We address decisive questions of process managers (e.g., "when will the case be finished?", or "when did we perform the activity that we forgot to document?") in this thesis. As main contribution, we introduce an advanced probabilistic model to business process management that is based on a stochastic variant of Petri nets. We present a holistic approach to use the model effectively along the business process lifecycle. Therefore, we provide techniques to discover such models from historical observations, to predict the termination time of processes, and to ensure quality by missing data management. We propose mechanisms to optimize configuration for monitoring and prediction, i.e., to offer guidance in selecting important activities to monitor. An implementation is provided as a proof of concept. For evaluation, we compare the accuracy of the approach with that of state-of-the-art approaches using real process data of a hospital. Additionally, we show its more general applicability in other domains by applying the approach on process data from logistics and finance.},
  language  = {en}
}
@phdthesis{Heise2014,
  author    = {Heise, Arvid},
  title     = {Data cleansing and integration operators for a parallel data analytics platform},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-77100},
  school      = {Universit{\"a}t Potsdam},
  pages     = {ii, 179},
  year      = {2014},
  abstract  = {The data quality of real-world datasets need to be constantly monitored and maintained to allow organizations and individuals to reliably use their data. Especially, data integration projects suffer from poor initial data quality and as a consequence consume more effort and money. Commercial products and research prototypes for data cleansing and integration help users to improve the quality of individual and combined datasets. They can be divided into either standalone systems or database management system (DBMS) extensions. On the one hand, standalone systems do not interact well with DBMS and require time-consuming data imports and exports. On the other hand, DBMS extensions are often limited by the underlying system and do not cover the full set of data cleansing and integration tasks. We overcome both limitations by implementing a concise set of five data cleansing and integration operators on the parallel data analytics platform Stratosphere. We define the semantics of the operators, present their parallel implementation, and devise optimization techniques for individual operators and combinations thereof. Users specify declarative queries in our query language METEOR with our new operators to improve the data quality of individual datasets or integrate them to larger datasets. By integrating the data cleansing operators into the higher level language layer of Stratosphere, users can easily combine cleansing operators with operators from other domains, such as information extraction, to complex data flows. Through a generic description of the operators, the Stratosphere optimizer reorders operators even from different domains to find better query plans. As a case study, we reimplemented a part of the large Open Government Data integration project GovWILD with our new operators and show that our queries run significantly faster than the original GovWILD queries, which rely on relational operators. Evaluation reveals that our operators exhibit good scalability on up to 100 cores, so that even larger inputs can be efficiently processed by scaling out to more machines. Finally, our scripts are considerably shorter than the original GovWILD scripts, which results in better maintainability of the scripts.},
  language  = {en}
}
@phdthesis{Lorey2014,
  author    = {Lorey, Johannes},
  title     = {What's in a query : analyzing, predicting, and managing linked data access},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-72312},
  school      = {Universit{\"a}t Potsdam},
  year      = {2014},
  abstract  = {The term Linked Data refers to connected information sources comprising structured data about a wide range of topics and for a multitude of applications. In recent years, the conceptional and technical foundations of Linked Data have been formalized and refined. To this end, well-known technologies have been established, such as the Resource Description Framework (RDF) as a Linked Data model or the SPARQL Protocol and RDF Query Language (SPARQL) for retrieving this information. Whereas most research has been conducted in the area of generating and publishing Linked Data, this thesis presents novel approaches for improved management. In particular, we illustrate new methods for analyzing and processing SPARQL queries. Here, we present two algorithms suitable for identifying structural relationships between these queries. Both algorithms are applied to a large number of real-world requests to evaluate the performance of the approaches and the quality of their results. Based on this, we introduce different strategies enabling optimized access of Linked Data sources. We demonstrate how the presented approach facilitates effective utilization of SPARQL endpoints by prefetching results relevant for multiple subsequent requests. Furthermore, we contribute a set of metrics for determining technical characteristics of such knowledge bases. To this end, we devise practical heuristics and validate them through thorough analysis of real-world data sources. We discuss the findings and evaluate their impact on utilizing the endpoints. Moreover, we detail the adoption of a scalable infrastructure for improving Linked Data discovery and consumption. As we outline in an exemplary use case, this platform is eligible both for processing and provisioning the corresponding information.},
  language  = {en}
}
@phdthesis{Steinert2014,
  author    = {Steinert, Bastian},
  title     = {Built-in recovery support for explorative programming},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-71305},
  school      = {Universit{\"a}t Potsdam},
  year      = {2014},
  abstract  = {This work introduces concepts and corresponding tool support to enable a complementary approach in dealing with recovery. Programmers need to recover a development state, or a part thereof, when previously made changes reveal undesired implications. However, when the need arises suddenly and unexpectedly, recovery often involves expensive and tedious work. To avoid tedious work, literature recommends keeping away from unexpected recovery demands by following a structured and disciplined approach, which consists of the application of various best practices including working only on one thing at a time, performing small steps, as well as making proper use of versioning and testing tools. However, the attempt to avoid unexpected recovery is both time-consuming and error-prone. On the one hand, it requires disproportionate effort to minimize the risk of unexpected situations. On the other hand, applying recommended practices selectively, which saves time, can hardly avoid recovery. In addition, the constant need for foresight and self-control has unfavorable implications. It is exhaustive and impedes creative problem solving. This work proposes to make recovery fast and easy and introduces corresponding support called CoExist. Such dedicated support turns situations of unanticipated recovery from tedious experiences into pleasant ones. It makes recovery fast and easy to accomplish, even if explicit commits are unavailable or tests have been ignored for some time. When mistakes and unexpected insights are no longer associated with tedious corrective actions, programmers are encouraged to change source code as a means to reason about it, as opposed to making changes only after structuring and evaluating them mentally. This work further reports on an implementation of the proposed tool support in the Squeak/Smalltalk development environment. The development of the tools has been accompanied by regular performance and usability tests. In addition, this work investigates whether the proposed tools affect programmers' performance. In a controlled lab study, 22 participants improved the design of two different applications. Using a repeated measurement setup, the study examined the effect of providing CoExist on programming performance. The result of analyzing 88 hours of programming suggests that built-in recovery support as provided with CoExist positively has a positive effect on programming performance in explorative programming tasks.},
  language  = {en}
}
@phdthesis{Tinnefeld2014,
  author    = {Tinnefeld, Christian},
  title     = {Building a columnar database on shared main memory-based storage},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-72063},
  school      = {Universit{\"a}t Potsdam},
  pages     = {175},
  year      = {2014},
  abstract  = {In the field of disk-based parallel database management systems exists a great variety of solutions based on a shared-storage or a shared-nothing architecture. In contrast, main memory-based parallel database management systems are dominated solely by the shared-nothing approach as it preserves the in-memory performance advantage by processing data locally on each server. We argue that this unilateral development is going to cease due to the combination of the following three trends: a) Nowadays network technology features remote direct memory access (RDMA) and narrows the performance gap between accessing main memory inside a server and of a remote server to and even below a single order of magnitude. b) Modern storage systems scale gracefully, are elastic, and provide high-availability. c) A modern storage system such as Stanford's RAMCloud even keeps all data resident in main memory. Exploiting these characteristics in the context of a main-memory parallel database management system is desirable. The advent of RDMA-enabled network technology makes the creation of a parallel main memory DBMS based on a shared-storage approach feasible. This thesis describes building a columnar database on shared main memory-based storage. The thesis discusses the resulting architecture (Part I), the implications on query processing (Part II), and presents an evaluation of the resulting solution in terms of performance, high-availability, and elasticity (Part III). In our architecture, we use Stanford's RAMCloud as shared-storage, and the self-designed and developed in-memory AnalyticsDB as relational query processor on top. AnalyticsDB encapsulates data access and operator execution via an interface which allows seamless switching between local and remote main memory, while RAMCloud provides not only storage capacity, but also processing power. Combining both aspects allows pushing-down the execution of database operators into the storage system. We describe how the columnar data processed by AnalyticsDB is mapped to RAMCloud's key-value data model and how the performance advantages of columnar data storage can be preserved. The combination of fast network technology and the possibility to execute database operators in the storage system opens the discussion for site selection. We construct a system model that allows the estimation of operator execution costs in terms of network transfer, data processed in memory, and wall time. This can be used for database operators that work on one relation at a time - such as a scan or materialize operation - to discuss the site selection problem (data pull vs. operator push). Since a database query translates to the execution of several database operators, it is possible that the optimal site selection varies per operator. For the execution of a database operator that works on two (or more) relations at a time, such as a join, the system model is enriched by additional factors such as the chosen algorithm (e.g. Grace- vs. Distributed Block Nested Loop Join vs. Cyclo-Join), the data partitioning of the respective relations, and their overlapping as well as the allowed resource allocation. We present an evaluation on a cluster with 60 nodes where all nodes are connected via RDMA-enabled network equipment. We show that query processing performance is about 2.4x slower if everything is done via the data pull operator execution strategy (i.e. RAMCloud is being used only for data access) and about 27\% slower if operator execution is also supported inside RAMCloud (in comparison to operating only on main memory inside a server without any network communication at all). The fast-crash recovery feature of RAMCloud can be leveraged to provide high-availability, e.g. a server crash during query execution only delays the query response for about one second. Our solution is elastic in a way that it can adapt to changing workloads a) within seconds, b) without interruption of the ongoing query processing, and c) without manual intervention.},
  language  = {en}
}
@phdthesis{Hebig2014,
  author    = {Hebig, Regina},
  title     = {Evolution of model-driven engineering settings in practice},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-70761},
  school      = {Universit{\"a}t Potsdam},
  year      = {2014},
  abstract  = {Nowadays, software systems are getting more and more complex. To tackle this challenge most diverse techniques, such as design patterns, service oriented architectures (SOA), software development processes, and model-driven engineering (MDE), are used to improve productivity, while time to market and quality of the products stay stable. Multiple of these techniques are used in parallel to profit from their benefits. While the use of sophisticated software development processes is standard, today, MDE is just adopted in practice. However, research has shown that the application of MDE is not always successful. It is not fully understood when advantages of MDE can be used and to what degree MDE can also be disadvantageous for productivity. Further, when combining different techniques that aim to affect the same factor (e.g. productivity) the question arises whether these techniques really complement each other or, in contrast, compensate their effects. Due to that, there is the concrete question how MDE and other techniques, such as software development process, are interrelated. Both aspects (advantages and disadvantages for productivity as well as the interrelation to other techniques) need to be understood to identify risks relating to the productivity impact of MDE. Before studying MDE's impact on productivity, it is necessary to investigate the range of validity that can be reached for the results. This includes two questions. First, there is the question whether MDE's impact on productivity is similar for all approaches of adopting MDE in practice. Second, there is the question whether MDE's impact on productivity for an approach of using MDE in practice remains stable over time. The answers for both questions are crucial for handling risks of MDE, but also for the design of future studies on MDE success. This thesis addresses these questions with the goal to support adoption of MDE in future. To enable a differentiated discussion about MDE, the term MDE setting'' is introduced. MDE setting refers to the applied technical setting, i.e. the employed manual and automated activities, artifacts, languages, and tools. An MDE setting's possible impact on productivity is studied with a focus on changeability and the interrelation to software development processes. This is done by introducing a taxonomy of changeability concerns that might be affected by an MDE setting. Further, three MDE traits are identified and it is studied for which manifestations of these MDE traits software development processes are impacted. To enable the assessment and evaluation of an MDE setting's impacts, the Software Manufacture Model language is introduced. This is a process modeling language that allows to reason about how relations between (modeling) artifacts (e.g. models or code files) change during application of manual or automated development activities. On that basis, risk analysis techniques are provided. These techniques allow identifying changeability risks and assessing the manifestations of the MDE traits (and with it an MDE setting's impact on software development processes). To address the range of validity, MDE settings from practice and their evolution histories were capture in context of this thesis. First, this data is used to show that MDE settings cover the whole spectrum concerning their impact on changeability or interrelation to software development processes. Neither it is seldom that MDE settings are neutral for processes nor is it seldom that MDE settings have impact on processes. Similarly, the impact on changeability differs relevantly. Second, a taxonomy of evolution of MDE settings is introduced. In that context it is discussed to what extent different types of changes on an MDE setting can influence this MDE setting's impact on changeability and the interrelation to processes. The category of structural evolution, which can change these characteristics of an MDE setting, is identified. The captured MDE settings from practice are used to show that structural evolution exists and is common. In addition, some examples of structural evolution steps are collected that actually led to a change in the characteristics of the respective MDE settings. Two implications are: First, the assessed diversity of MDE settings evaluates the need for the analysis techniques that shall be presented in this thesis. Second, evolution is one explanation for the diversity of MDE settings in practice. To summarize, this thesis studies the nature and evolution of MDE settings in practice. As a result support for the adoption of MDE settings is provided in form of techniques for the identification of risks relating to productivity impacts.},
  language  = {en}
}
@phdthesis{Truemper2014,
  author    = {Tr{\"u}mper, Jonas},
  title     = {Visualization techniques for the analysis of software behavior and related structures},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-72145},
  school      = {Universit{\"a}t Potsdam},
  year      = {2014},
  abstract  = {Software maintenance encompasses any changes made to a software system after its initial deployment and is thereby one of the key phases in the typical software-engineering lifecycle. In software maintenance, we primarily need to understand structural and behavioral aspects, which are difficult to obtain, e.g., by code reading. Software analysis is therefore a vital tool for maintaining these systems: It provides - the preferably automated - means to extract and evaluate information from their artifacts such as software structure, runtime behavior, and related processes. However, such analysis typically results in massive raw data, so that even experienced engineers face difficulties directly examining, assessing, and understanding these data. Among other things, they require tools with which to explore the data if no clear question can be formulated beforehand. For this, software analysis and visualization provide its users with powerful interactive means. These enable the automation of tasks and, particularly, the acquisition of valuable and actionable insights into the raw data. For instance, one means for exploring runtime behavior is trace visualization. This thesis aims at extending and improving the tool set for visual software analysis by concentrating on several open challenges in the fields of dynamic and static analysis of software systems. This work develops a series of concepts and tools for the exploratory visualization of the respective data to support users in finding and retrieving information on the system artifacts concerned. This is a difficult task, due to the lack of appropriate visualization metaphors; in particular, the visualization of complex runtime behavior poses various questions and challenges of both a technical and conceptual nature. This work focuses on a set of visualization techniques for visually representing control-flow related aspects of software traces from shared-memory software systems: A trace-visualization concept based on icicle plots aids in understanding both single-threaded as well as multi-threaded runtime behavior on the function level. The concept's extensibility further allows the visualization and analysis of specific aspects of multi-threading such as synchronization, the correlation of such traces with data from static software analysis, and a comparison between traces. Moreover, complementary techniques for simultaneously analyzing system structures and the evolution of related attributes are proposed. These aim at facilitating long-term planning of software architecture and supporting management decisions in software projects by extensions to the circular-bundle-view technique: An extension to 3-dimensional space allows for the use of additional variables simultaneously; interaction techniques allow for the modification of structures in a visual manner. The concepts and techniques presented here are generic and, as such, can be applied beyond software analysis for the visualization of similarly structured data. The techniques' practicability is demonstrated by several qualitative studies using subject data from industry-scale software systems. The studies provide initial evidence that the techniques' application yields useful insights into the subject data and its interrelationships in several scenarios.},
  language  = {en}
}
@phdthesis{Takouna2014,
  author    = {Takouna, Ibrahim},
  title     = {Energy-efficient and performance-aware virtual machine management for cloud data centers},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-72399},
  school      = {Universit{\"a}t Potsdam},
  year      = {2014},
  abstract  = {Virtualisierte Cloud Datenzentren stellen nach Bedarf Ressourcen zur Verf{\"u}gu-ng, erm{\"o}glichen agile Ressourcenbereitstellung und beherbergen heterogene Applikationen mit verschiedenen Anforderungen an Ressourcen. Solche Datenzentren verbrauchen enorme Mengen an Energie, was die Erh{\"o}hung der Betriebskosten, der W{\"a}rme innerhalb der Zentren und des Kohlendioxidausstoßes verursacht. Der Anstieg des Energieverbrauches kann durch ein ineffektives Ressourcenmanagement, das die ineffiziente Ressourcenausnutzung verursacht, entstehen. Die vorliegende Dissertation stellt detaillierte Modelle und neue Verfahren f{\"u}r virtualisiertes Ressourcenmanagement in Cloud Datenzentren vor. Die vorgestellten Verfahren ziehen das Service-Level-Agreement (SLA) und die Heterogenit{\"a}t der Auslastung bez{\"u}glich des Bedarfs an Speicherzugriffen und Kommunikationsmustern von Web- und HPC- (High Performance Computing) Applikationen in Betracht. Um die pr{\"a}sentierten Techniken zu evaluieren, verwenden wir Simulationen und echte Protokollierung der Auslastungen von Web- und HPC- Applikationen. Außerdem vergleichen wir unser Techniken und Verfahren mit anderen aktuellen Verfahren durch die Anwendung von verschiedenen Performance Metriken. Die Hauptbeitr{\"a}ge dieser Dissertation sind Folgendes: Ein Proaktives auf robuster Optimierung basierendes Ressourcenbereitstellungsverfahren. Dieses Verfahren erh{\"o}ht die F{\"a}higkeit der Hostes zur Verf{\"u}g-ungsstellung von mehr VMs. Gleichzeitig aber wird der unn{\"o}tige Energieverbrauch minimiert. Zus{\"a}tzlich mindert diese Technik unerw{\"u}nschte {\"A}nde-rungen im Energiezustand des Servers. Die vorgestellte Technik nutzt einen auf Intervall basierenden Vorhersagealgorithmus zur Implementierung einer robusten Optimierung. Dabei werden unsichere Anforderungen in Betracht gezogen. Ein adaptives und auf Intervall basierendes Verfahren zur Vorhersage des Arbeitsaufkommens mit hohen, in k{\"u}rzer Zeit auftretenden Schwankungen. Die Intervall basierende Vorhersage ist implementiert in der Standard Abweichung Variante und in der Median absoluter Abweichung Variante. Die Intervall-{\"A}nderungen basieren auf einem adaptiven Vertrauensfenster um die Schwankungen des Arbeitsaufkommens zu bew{\"a}ltigen. Eine robuste VM Zusammenlegung f{\"u}r ein effizientes Energie und Performance Management. Dies erm{\"o}glicht die gegenseitige Abh{\"a}ngigkeit zwischen der Energie und der Performance zu minimieren. Unser Verfahren reduziert die Anzahl der VM-Migrationen im Vergleich mit den neu vor kurzem vorgestellten Verfahren. Dies tr{\"a}gt auch zur Reduzierung des durch das Netzwerk verursachten Energieverbrauches. Außerdem reduziert dieses Verfahren SLA-Verletzungen und die Anzahl von {\"A}nderungen an Energiezus-t{\"a}nden. Ein generisches Modell f{\"u}r das Netzwerk eines Datenzentrums um die verz{\"o}-gerte Kommunikation und ihre Auswirkung auf die VM Performance und auf die Netzwerkenergie zu simulieren. Außerdem wird ein generisches Modell f{\"u}r ein Memory-Bus des Servers vorgestellt. Dieses Modell beinhaltet auch Modelle f{\"u}r die Latenzzeit und den Energieverbrauch f{\"u}r verschiedene Memory Frequenzen. Dies erlaubt eine Simulation der Memory Verz{\"o}gerung und ihre Auswirkung auf die VM-Performance und auf den Memory Energieverbrauch. Kommunikation bewusste und Energie effiziente Zusammenlegung f{\"u}r parallele Applikationen um die dynamische Entdeckung von Kommunikationsmustern und das Umplanen von VMs zu erm{\"o}glichen. Das Umplanen von VMs benutzt eine auf den entdeckten Kommunikationsmustern basierende Migration. Eine neue Technik zur Entdeckung von dynamischen Mustern ist implementiert. Sie basiert auf der Signal Verarbeitung des Netzwerks von VMs, anstatt die Informationen des virtuellen Umstellung der Hosts oder der Initiierung der VMs zu nutzen. Das Ergebnis zeigt, dass unsere Methode die durchschnittliche Anwendung des Netzwerks reduziert und aufgrund der Reduzierung der aktiven Umstellungen Energie gespart. Außerdem bietet sie eine bessere VM Performance im Vergleich zu der CPU-basierten Platzierung. Memory bewusste VM Zusammenlegung f{\"u}r unabh{\"a}ngige VMs. Sie nutzt die Vielfalt des VMs Memory Zuganges um die Anwendung vom Memory-Bus der Hosts zu balancieren. Die vorgestellte Technik, Memory-Bus Load Balancing (MLB), verteilt die VMs reaktiv neu im Bezug auf ihre Anwendung vom Memory-Bus. Sie nutzt die VM Migration um die Performance des gesamtem Systems zu verbessern. Außerdem sind die dynamische Spannung, die Frequenz Skalierung des Memory und die MLB Methode kombiniert um ein besseres Energiesparen zu leisten.},
  language  = {en}
}
@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}
}