@misc{PerlichMeinel2018, author = {Perlich, Anja and Meinel, Christoph}, title = {Cooperative Note-Taking in Psychotherapy Sessions}, series = {2018 IEEE 20th International Conference on e-Health Networking, Applications and Services (Healthcom)}, journal = {2018 IEEE 20th International Conference on e-Health Networking, Applications and Services (Healthcom)}, publisher = {IEEE}, address = {New York}, isbn = {978-1-5386-4294-8}, pages = {6}, year = {2018}, abstract = {In the course of patient treatments, psychotherapists aim to meet the challenges of being both a trusted, knowledgeable conversation partner and a diligent documentalist. We are developing the digital whiteboard system Tele-Board MED (TBM), which allows the therapist to take digital notes during the session together with the patient. This study investigates what therapists are experiencing when they document with TBM in patient sessions for the first time and whether this documentation saves them time when writing official clinical documents. As the core of this study, we conducted four anamnesis session dialogues with behavior psychotherapists and volunteers acting in the role of patients. Following a mixed-method approach, the data collection and analysis involved self-reported emotion samples, user experience curves and questionnaires. We found that even in the very first patient session with TBM, therapists come to feel comfortable, develop a positive feeling and can concentrate on the patient. Regarding administrative documentation tasks, we found with the TBM report generation feature the therapists save 60\% of the time they normally spend on writing case reports to the health insurance.}, language = {en} } @misc{GawronChengMeinel2018, author = {Gawron, Marian and Cheng, Feng and Meinel, Christoph}, title = {Automatic vulnerability classification using machine learning}, series = {Risks and Security of Internet and Systems}, journal = {Risks and Security of Internet and Systems}, publisher = {Springer}, address = {Cham}, isbn = {978-3-319-76687-4}, issn = {0302-9743}, doi = {10.1007/978-3-319-76687-4_1}, pages = {3 -- 17}, year = {2018}, abstract = {The classification of vulnerabilities is a fundamental step to derive formal attributes that allow a deeper analysis. Therefore, it is required that this classification has to be performed timely and accurate. Since the current situation demands a manual interaction in the classification process, the timely processing becomes a serious issue. Thus, we propose an automated alternative to the manual classification, because the amount of identified vulnerabilities per day cannot be processed manually anymore. We implemented two different approaches that are able to automatically classify vulnerabilities based on the vulnerability description. We evaluated our approaches, which use Neural Networks and the Naive Bayes methods respectively, on the base of publicly known vulnerabilities.}, language = {en} } @misc{PufahlWongWeske2018, author = {Pufahl, Luise and Wong, Tsun Yin and Weske, Mathias}, title = {Design of an extensible BPMN process simulator}, series = {Business Process Management Workshops (BPM 2017)}, volume = {308}, journal = {Business Process Management Workshops (BPM 2017)}, publisher = {Springer}, address = {Berlin}, isbn = {978-3-319-74030-0}, issn = {1865-1348}, doi = {10.1007/978-3-319-74030-0_62}, pages = {782 -- 795}, year = {2018}, abstract = {Business process simulation is an important means for quantitative analysis of a business process and to compare different process alternatives. With the Business Process Model and Notation (BPMN) being the state-of-the-art language for the graphical representation of business processes, many existing process simulators support already the simulation of BPMN diagrams. However, they do not provide well-defined interfaces to integrate new concepts in the simulation environment. In this work, we present the design and architecture of a proof-of-concept implementation of an open and extensible BPMN process simulator. It also supports the simulation of multiple BPMN processes at a time and relies on the building blocks of the well-founded discrete event simulation. The extensibility is assured by a plug-in concept. Its feasibility is demonstrated by extensions supporting new BPMN concepts, such as the simulation of business rule activities referencing decision models and batch activities.}, language = {en} } @misc{BauerMalchowMeinel2018, author = {Bauer, Matthias and Malchow, Martin and Meinel, Christoph}, title = {Improving access to online lecture videos}, series = {Proceedings of 2018 IEEE Global Engineering Education Conference (EDUCON)}, journal = {Proceedings of 2018 IEEE Global Engineering Education Conference (EDUCON)}, publisher = {IEEE}, address = {New York}, isbn = {978-1-5386-2957-4}, issn = {2165-9567}, doi = {10.1109/EDUCON.2018.8363361}, pages = {1161 -- 1168}, year = {2018}, abstract = {In university teaching today, it is common practice to record regular lectures and special events such as conferences and speeches. With these recordings, a large fundus of video teaching material can be created quickly and easily. Typically, lectures have a length of about one and a half hours and usually take place once or twice a week based on the credit hours. Depending on the number of lectures and other events recorded, the number of recordings available is increasing rapidly, which means that an appropriate form of provisioning is essential for the students. This is usually done in the form of lecture video platforms. In this work, we have investigated how lecture video platforms and the contained knowledge can be improved and accessed more easily by an increasing number of students. We came up with a multistep process we have applied to our own lecture video web portal that can be applied to other solutions as well.}, language = {en} } @misc{MalchowBauerMeinel2018, author = {Malchow, Martin and Bauer, Matthias and Meinel, Christoph}, title = {Embedded smart home — remote lab MOOC with optional real hardware experience for over 4000 students}, series = {Proceedings of 2018 IEEE Global Engineering Education Conference (EDUCON)}, journal = {Proceedings of 2018 IEEE Global Engineering Education Conference (EDUCON)}, publisher = {IEEE}, address = {New York}, isbn = {978-1-5386-2957-4}, issn = {2165-9567}, doi = {10.1109/EDUCON.2018.8363353}, pages = {1104 -- 1111}, year = {2018}, abstract = {MOOCs (Massive Open Online Courses) become more and more popular for learners of all ages to study further or to learn new subjects of interest. The purpose of this paper is to introduce a different MOOC course style. Typically, video content is shown teaching the student new information. After watching a video, self-test questions can be answered. Finally, the student answers weekly exams and final exams like the self test questions. Out of the points that have been scored for weekly and final exams a certificate can be issued. Our approach extends the possibility to receive points for the final score with practical programming exercises on real hardware. It allows the student to do embedded programming by communicating over GPIO pins to control LEDs and measure sensor values. Additionally, they can visualize values on an embedded display using web technologies, which are an essential part of embedded and smart home devices to communicate with common APIs. Students have the opportunity to solve all tasks within the online remote lab and at home on the same kind of hardware. The evaluation of this MOOCs indicates the interesting design for students to learn an engineering technique with new technology approaches in an appropriate, modern, supporting and motivating way of teaching.}, language = {en} } @misc{MalchowBauerMeinel2018, author = {Malchow, Martin and Bauer, Matthias and Meinel, Christoph}, title = {Enhance Learning in a Video Lecture Archive with Annotations}, series = {Proceedings of OF 2018 IEEE Global Engineering Education Conference (EDUCON)}, journal = {Proceedings of OF 2018 IEEE Global Engineering Education Conference (EDUCON)}, publisher = {IEEE}, address = {New York}, isbn = {978-1-5386-2957-4}, issn = {2165-9567}, pages = {849 -- 856}, year = {2018}, abstract = {When students watch learning videos online, they usually need to watch several hours of video content. In the end, not every minute of a video is relevant for the exam. Additionally, students need to add notes to clarify issues of a lecture. There are several possibilities to enhance the metadata of a video, e.g. a typical way to add user-specific information to an online video is a comment functionality, which allows users to share their thoughts and questions with the public. In contrast to common video material which can be found online, lecture videos are used for exam preparation. Due to this difference, the idea comes up to annotate lecture videos with markers and personal notes for a better understanding of the taught content. Especially, students learning for an exam use their notes to refresh their memories. To ease this learning method with lecture videos, we introduce the annotation feature in our video lecture archive. This functionality supports the students with keeping track of their thoughts by providing an intuitive interface to easily add, modify or remove their ideas. This annotation function is integrated in the video player. Hence, scrolling to a separate annotation area on the website is not necessary. Furthermore, the annotated notes can be exported together with the slide content to a PDF file, which can then be printed easily. Lecture video annotations support and motivate students to learn and watch videos from an E-Learning video archive.}, language = {en} } @misc{NeubauerWankoSchaubetal.2018, author = {Neubauer, Kai and Wanko, Philipp and Schaub, Torsten H. and Haubelt, Christian}, title = {Exact multi-objective design space exploration using ASPmT}, series = {Proceedings of the 2018 Design, Automation \& Test in Europe Conference \& Exhibition (DATE)}, journal = {Proceedings of the 2018 Design, Automation \& Test in Europe Conference \& Exhibition (DATE)}, publisher = {IEEE}, address = {New York}, isbn = {978-3-9819-2630-9}, issn = {1530-1591}, doi = {10.23919/DATE.2018.8342014}, pages = {257 -- 260}, year = {2018}, abstract = {An efficient Design Space Exploration (DSE) is imperative for the design of modern, highly complex embedded systems in order to steer the development towards optimal design points. The early evaluation of design decisions at system-level abstraction layer helps to find promising regions for subsequent development steps in lower abstraction levels by diminishing the complexity of the search problem. In recent works, symbolic techniques, especially Answer Set Programming (ASP) modulo Theories (ASPmT), have been shown to find feasible solutions of highly complex system-level synthesis problems with non-linear constraints very efficiently. In this paper, we present a novel approach to a holistic system-level DSE based on ASPmT. To this end, we include additional background theories that concurrently guarantee compliance with hard constraints and perform the simultaneous optimization of several design objectives. We implement and compare our approach with a state-of-the-art preference handling framework for ASP. Experimental results indicate that our proposed method produces better solutions with respect to both diversity and convergence to the true Pareto front.}, language = {en} } @misc{BazhenovaZerbatoWeske2018, author = {Bazhenova, Ekaterina and Zerbato, Francesca and Weske, Mathias}, title = {Data-Centric Extraction of DMN Decision Models from BPMN Process Models}, series = {Business Process Management Workshops}, volume = {308}, journal = {Business Process Management Workshops}, publisher = {Springer}, address = {Berlin}, isbn = {978-3-319-74030-0}, issn = {1865-1348}, doi = {10.1007/978-3-319-74030-0_43}, pages = {542 -- 555}, year = {2018}, abstract = {Operational decisions in business processes can be modeled by using the Decision Model and Notation (DMN). The complementary use of DMN for decision modeling and of the Business Process Model and Notation (BPMN) for process design realizes the separation of concerns principle. For supporting separation of concerns during the design phase, it is crucial to understand which aspects of decision-making enclosed in a process model should be captured by a dedicated decision model. Whereas existing work focuses on the extraction of decision models from process control flow, the connection of process-related data and decision models is still unexplored. In this paper, we investigate how process-related data used for making decisions can be represented in process models and we distinguish a set of BPMN patterns capturing such information. Then, we provide a formal mapping of the identified BPMN patterns to corresponding DMN models and apply our approach to a real-world healthcare process.}, language = {en} } @misc{BoissierKurzynski2018, author = {Boissier, Martin and Kurzynski, Daniel}, title = {Workload-Driven Horizontal Partitioning and Pruning for Large HTAP Systems}, series = {2018 IEEE 34th International Conference on Data Engineering Workshops (ICDEW)}, journal = {2018 IEEE 34th International Conference on Data Engineering Workshops (ICDEW)}, publisher = {IEEE}, address = {New York}, isbn = {978-1-5386-6306-6}, doi = {10.1109/ICDEW.2018.00026}, pages = {116 -- 121}, year = {2018}, abstract = {Modern server systems with large NUMA architectures necessitate (i) data being distributed over the available computing nodes and (ii) NUMA-aware query processing to enable effective parallel processing in database systems. As these architectures incur significant latency and throughout penalties for accessing non-local data, queries should be executed as close as possible to the data. To further increase both performance and efficiency, data that is not relevant for the query result should be skipped as early as possible. One way to achieve this goal is horizontal partitioning to improve static partition pruning. As part of our ongoing work on workload-driven partitioning, we have implemented a recent approach called aggressive data skipping and extended it to handle both analytical as well as transactional access patterns. In this paper, we evaluate this approach with the workload and data of a production enterprise system of a Global 2000 company. The results show that over 80\% of all tuples can be skipped in average while the resulting partitioning schemata are surprisingly stable over time.}, language = {en} } @misc{RazzaqKaminskiRomeroetal.2018, author = {Razzaq, Misbah and Kaminski, Roland and Romero, Javier and Schaub, Torsten H. and Bourdon, Jeremie and Guziolowski, Carito}, title = {Computing diverse boolean networks from phosphoproteomic time series data}, series = {Computational Methods in Systems Biology}, volume = {11095}, journal = {Computational Methods in Systems Biology}, publisher = {Springer}, address = {Berlin}, isbn = {978-3-319-99429-1}, issn = {0302-9743}, doi = {10.1007/978-3-319-99429-1_4}, pages = {59 -- 74}, year = {2018}, abstract = {Logical modeling has been widely used to understand and expand the knowledge about protein interactions among different pathways. Realizing this, the caspo-ts system has been proposed recently to learn logical models from time series data. It uses Answer Set Programming to enumerate Boolean Networks (BNs) given prior knowledge networks and phosphoproteomic time series data. In the resulting sequence of solutions, similar BNs are typically clustered together. This can be problematic for large scale problems where we cannot explore the whole solution space in reasonable time. Our approach extends the caspo-ts system to cope with the important use case of finding diverse solutions of a problem with a large number of solutions. We first present the algorithm for finding diverse solutions and then we demonstrate the results of the proposed approach on two different benchmark scenarios in systems biology: (1) an artificial dataset to model TCR signaling and (2) the HPN-DREAM challenge dataset to model breast cancer cell lines.}, language = {en} } @misc{IonBaudisch2018, author = {Ion, Alexandra and Baudisch, Patrick Markus}, title = {Metamaterial Devices}, publisher = {Association for Computing Machinery}, address = {New York}, isbn = {978-1-4503-5819-4}, doi = {10.1145/3214822.3214827}, pages = {2}, year = {2018}, abstract = {In our hands-on demonstration, we show several objects, the functionality of which is defined by the objects' internal micro-structure. Such metamaterial machines can (1) be mechanisms based on their microstructures, (2) employ simple mechanical computation, or (3) change their outside to interact with their environment. They are 3D printed from one piece and we support their creating by providing interactive software tools.}, language = {en} } @misc{TorkuraSukmanaMeinigetal.2018, author = {Torkura, Kennedy A. and Sukmana, Muhammad Ihsan Haikal and Meinig, Michael and Kayem, Anne V. D. M. and Cheng, Feng and Meinel, Christoph and Graupner, Hendrik}, title = {Securing cloud storage brokerage systems through threat models}, series = {Proceedings IEEE 32nd International Conference on Advanced Information Networking and Applications (AINA)}, journal = {Proceedings IEEE 32nd International Conference on Advanced Information Networking and Applications (AINA)}, publisher = {IEEE}, address = {New York}, isbn = {978-1-5386-2195-0}, issn = {1550-445X}, doi = {10.1109/AINA.2018.00114}, pages = {759 -- 768}, year = {2018}, abstract = {Cloud storage brokerage is an abstraction aimed at providing value-added services. However, Cloud Service Brokers are challenged by several security issues including enlarged attack surfaces due to integration of disparate components and API interoperability issues. Therefore, appropriate security risk assessment methods are required to identify and evaluate these security issues, and examine the efficiency of countermeasures. A possible approach for satisfying these requirements is employment of threat modeling concepts, which have been successfully applied in traditional paradigms. In this work, we employ threat models including attack trees, attack graphs and Data Flow Diagrams against a Cloud Service Broker (CloudRAID) and analyze these security threats and risks. Furthermore, we propose an innovative technique for combining Common Vulnerability Scoring System (CVSS) and Common Configuration Scoring System (CCSS) base scores in probabilistic attack graphs to cater for configuration-based vulnerabilities which are typically leveraged for attacking cloud storage systems. This approach is necessary since existing schemes do not provide sufficient security metrics, which are imperatives for comprehensive risk assessments. We demonstrate the efficiency of our proposal by devising CCSS base scores for two common attacks against cloud storage: Cloud Storage Enumeration Attack and Cloud Storage Exploitation Attack. These metrics are then used in Attack Graph Metric-based risk assessment. Our experimental evaluation shows that our approach caters for the aforementioned gaps and provides efficient security hardening options. Therefore, our proposals can be employed to improve cloud security.}, language = {en} } @misc{DiazMendezSchoelzel2018, author = {Diaz, Sergio and Mendez, Diego and Sch{\"o}lzel, Mario}, title = {Dynamic Gallager-Humblet-Spira Algorithm for Wireless Sensor Networks}, series = {2018 IEEE Colombian Conference on Communications and Computing (COLCOM)}, journal = {2018 IEEE Colombian Conference on Communications and Computing (COLCOM)}, publisher = {IEEE}, address = {New York}, isbn = {978-1-5386-6820-7}, pages = {6}, year = {2018}, abstract = {The problem of constructing and maintaining a tree topology in a distributed manner is a challenging task in WSNs. This is because the nodes have limited computational and memory resources and the network changes over time. We propose the Dynamic Gallager-Humblet-Spira (D-GHS) algorithm that builds and maintains a minimum spanning tree. To do so, we divide D-GHS into four phases, namely neighbor discovery, tree construction, data collection, and tree maintenance. In the neighbor discovery phase, the nodes collect information about their neighbors and the link quality. In the tree construction, D-GHS finds the minimum spanning tree by executing the Gallager-Humblet-Spira algorithm. In the data collection phase, the sink roots the minimum spanning tree at itself, and each node sends data packets. In the tree maintenance phase, the nodes repair the tree when communication failures occur. The emulation results show that D-GHS reduces the number of control messages and the energy consumption, at the cost of a slight increase in memory size and convergence time.}, language = {en} } @misc{ArandaSchoelzelMendezetal.2018, author = {Aranda, Juan and Sch{\"o}lzel, Mario and Mendez, Diego and Carrillo, Henry}, title = {An energy consumption model for multiModal wireless sensor networks based on wake-up radio receivers}, series = {2018 IEEE Colombian Conference on Communications and Computing (COLCOM)}, journal = {2018 IEEE Colombian Conference on Communications and Computing (COLCOM)}, publisher = {IEEE}, address = {New York}, isbn = {978-1-5386-6820-7}, doi = {10.1109/ColComCon.2018.8466728}, pages = {6}, year = {2018}, abstract = {Energy consumption is a major concern in Wireless Sensor Networks. A significant waste of energy occurs due to the idle listening and overhearing problems, which are typically avoided by turning off the radio, while no transmission is ongoing. The classical approach for allowing the reception of messages in such situations is to use a low-duty-cycle protocol, and to turn on the radio periodically, which reduces the idle listening problem, but requires timers and usually unnecessary wakeups. A better solution is to turn on the radio only on demand by using a Wake-up Radio Receiver (WuRx). In this paper, an energy model is presented to estimate the energy saving in various multi-hop network topologies under several use cases, when a WuRx is used instead of a classical low-duty-cycling protocol. The presented model also allows for estimating the benefit of various WuRx properties like using addressing or not.}, language = {en} } @misc{Matthies2018, author = {Matthies, Christoph}, title = {Scrum2kanban}, series = {Proceedings of the 2nd International Workshop on Software Engineering Education for Millennials}, journal = {Proceedings of the 2nd International Workshop on Software Engineering Education for Millennials}, publisher = {IEEE}, address = {New York}, isbn = {978-1-45035-750-0}, doi = {10.1145/3194779.3194784}, pages = {48 -- 55}, year = {2018}, abstract = {Using university capstone courses to teach agile software development methodologies has become commonplace, as agile methods have gained support in professional software development. This usually means students are introduced to and work with the currently most popular agile methodology: Scrum. However, as the agile methods employed in the industry change and are adapted to different contexts, university courses must follow suit. A prime example of this is the Kanban method, which has recently gathered attention in the industry. In this paper, we describe a capstone course design, which adds the hands-on learning of the lean principles advocated by Kanban into a capstone project run with Scrum. This both ensures that students are aware of recent process frameworks and ideas as well as gain a more thorough overview of how agile methods can be employed in practice. We describe the details of the course and analyze the participating students' perceptions as well as our observations. We analyze the development artifacts, created by students during the course in respect to the two different development methodologies. We further present a summary of the lessons learned as well as recommendations for future similar courses. The survey conducted at the end of the course revealed an overwhelmingly positive attitude of students towards the integration of Kanban into the course.}, language = {en} } @misc{KrentzMeinelGraupner2018, author = {Krentz, Konrad-Felix and Meinel, Christoph and Graupner, Hendrik}, title = {More Lightweight, yet Stronger 802.15.4 Security Through an Intra-layer Optimization}, series = {Foundations and Practice of Security}, volume = {10723}, journal = {Foundations and Practice of Security}, publisher = {Springer}, address = {Cham}, isbn = {978-3-319-75650-9}, issn = {0302-9743}, doi = {10.1007/978-3-319-75650-9_12}, pages = {173 -- 188}, year = {2018}, abstract = {802.15.4 security protects against the replay, injection, and eavesdropping of 802.15.4 frames. A core concept of 802.15.4 security is the use of frame counters for both nonce generation and anti-replay protection. While being functional, frame counters (i) cause an increased energy consumption as they incur a per-frame overhead of 4 bytes and (ii) only provide sequential freshness. The Last Bits (LB) optimization does reduce the per-frame overhead of frame counters, yet at the cost of an increased RAM consumption and occasional energy-and time-consuming resynchronization actions. Alternatively, the timeslotted channel hopping (TSCH) media access control (MAC) protocol of 802.15.4 avoids the drawbacks of frame counters by replacing them with timeslot indices, but findings of Yang et al. question the security of TSCH in general. In this paper, we assume the use of ContikiMAC, which is a popular asynchronous MAC protocol for 802.15.4 networks. Under this assumption, we propose an Intra-Layer Optimization for 802.15.4 Security (ILOS), which intertwines 802.15.4 security and ContikiMAC. In effect, ILOS reduces the security-related per-frame overhead even more than the LB optimization, as well as achieves strong freshness. Furthermore, unlike the LB optimization, ILOS neither incurs an increased RAM consumption nor requires resynchronization actions. Beyond that, ILOS integrates with and advances other security supplements to ContikiMAC. We implemented ILOS using OpenMotes and the Contiki operating system.}, language = {en} } @misc{LosterNaumannEhmuelleretal.2018, author = {Loster, Michael and Naumann, Felix and Ehmueller, Jan and Feldmann, Benjamin}, title = {CurEx}, series = {Proceedings of the 27th ACM International Conference on Information and Knowledge Management}, journal = {Proceedings of the 27th ACM International Conference on Information and Knowledge Management}, publisher = {Association for Computing Machinery}, address = {New York}, isbn = {978-1-4503-6014-2}, doi = {10.1145/3269206.3269229}, pages = {1883 -- 1886}, year = {2018}, abstract = {The integration of diverse structured and unstructured information sources into a unified, domain-specific knowledge base is an important task in many areas. A well-maintained knowledge base enables data analysis in complex scenarios, such as risk analysis in the financial sector or investigating large data leaks, such as the Paradise or Panama papers. Both the creation of such knowledge bases, as well as their continuous maintenance and curation involves many complex tasks and considerable manual effort. With CurEx, we present a modular system that allows structured and unstructured data sources to be integrated into a domain-specific knowledge base. In particular, we (i) enable the incremental improvement of each individual integration component; (ii) enable the selective generation of multiple knowledge graphs from the information contained in the knowledge base; and (iii) provide two distinct user interfaces tailored to the needs of data engineers and end-users respectively. The former has curation capabilities and controls the integration process, whereas the latter focuses on the exploration of the generated knowledge graph.}, language = {en} } @misc{RepkeKrestelEddingetal.2018, author = {Repke, Tim and Krestel, Ralf and Edding, Jakob and Hartmann, Moritz and Hering, Jonas and Kipping, Dennis and Schmidt, Hendrik and Scordialo, Nico and Zenner, Alexander}, title = {Beacon in the Dark}, series = {Proceedings of the 27th ACM International Conference on Information and Knowledge Management}, journal = {Proceedings of the 27th ACM International Conference on Information and Knowledge Management}, publisher = {Association for Computing Machinery}, address = {New York}, isbn = {978-1-4503-6014-2}, doi = {10.1145/3269206.3269231}, pages = {1871 -- 1874}, year = {2018}, abstract = {The large amount of heterogeneous data in these email corpora renders experts' investigations by hand infeasible. Auditors or journalists, e.g., who are looking for irregular or inappropriate content or suspicious patterns, are in desperate need for computer-aided exploration tools to support their investigations. We present our Beacon system for the exploration of such corpora at different levels of detail. A distributed processing pipeline combines text mining methods and social network analysis to augment the already semi-structured nature of emails. The user interface ties into the resulting cleaned and enriched dataset. For the interface design we identify three objectives expert users have: gain an initial overview of the data to identify leads to investigate, understand the context of the information at hand, and have meaningful filters to iteratively focus onto a subset of emails. To this end we make use of interactive visualisations based on rearranged and aggregated extracted information to reveal salient patterns.}, language = {en} } @misc{ShaabaniMeinel2018, author = {Shaabani, Nuhad and Meinel, Christoph}, title = {Improving the efficiency of inclusion dependency detection}, series = {Proceedings of the 27th ACM International Conference on Information and Knowledge Management}, journal = {Proceedings of the 27th ACM International Conference on Information and Knowledge Management}, publisher = {Association for Computing Machinery}, address = {New York}, isbn = {978-1-4503-6014-2}, doi = {10.1145/3269206.3271724}, pages = {207 -- 216}, year = {2018}, abstract = {The detection of all inclusion dependencies (INDs) in an unknown dataset is at the core of any data profiling effort. Apart from the discovery of foreign key relationships, INDs can help perform data integration, integrity checking, schema (re-)design, and query optimization. With the advent of Big Data, the demand increases for efficient INDs discovery algorithms that can scale with the input data size. To this end, we propose S-INDD++ as a scalable system for detecting unary INDs in large datasets. S-INDD++ applies a new stepwise partitioning technique that helps discard a large number of attributes in early phases of the detection by processing the first partitions of smaller sizes. S-INDD++ also extends the concept of the attribute clustering to decide which attributes to be discarded based on the clustering result of each partition. Moreover, in contrast to the state-of-the-art, S-INDD++ does not require the partition to fit into the main memory-which is a highly appreciable property in the face of the ever growing datasets. We conducted an exhaustive evaluation of S-INDD++ by applying it to large datasets with thousands attributes and more than 266 million tuples. The results show the high superiority of S-INDD++ over the state-of-the-art. S-INDD++ reduced up to 50 \% of the runtime in comparison with BINDER, and up to 98 \% in comparison with S-INDD.}, language = {en} } @misc{SahlmannSchefflerSchnor2018, author = {Sahlmann, Kristina and Scheffler, Thomas and Schnor, Bettina}, title = {Ontology-driven Device Descriptions for IoT Network Management}, series = {2018 Global Internet of Things Summit (GIoTS)}, journal = {2018 Global Internet of Things Summit (GIoTS)}, publisher = {IEEE}, address = {New York}, isbn = {978-1-5386-6451-3}, doi = {10.1109/GIOTS.2018.8534569}, pages = {295 -- 300}, year = {2018}, abstract = {One particular challenge in the Internet of Things is the management of many heterogeneous things. The things are typically constrained devices with limited memory, power, network and processing capacity. Configuring every device manually is a tedious task. We propose an interoperable way to configure an IoT network automatically using existing standards. The proposed NETCONF-MQTT bridge intermediates between the constrained devices (speaking MQTT) and the network management standard NETCONF. The NETCONF-MQTT bridge generates dynamically YANG data models from the semantic description of the device capabilities based on the oneM2M ontology. We evaluate the approach for two use cases, i.e. describing an actuator and a sensor scenario.}, language = {en} }