@article{Perscheid2021, author = {Perscheid, Cindy}, title = {Comprior}, series = {BMC Bioinformatics}, volume = {22}, journal = {BMC Bioinformatics}, publisher = {Springer Nature}, address = {London}, issn = {1471-2105}, doi = {10.1186/s12859-021-04308-z}, pages = {1 -- 15}, year = {2021}, abstract = {Background Reproducible benchmarking is important for assessing the effectiveness of novel feature selection approaches applied on gene expression data, especially for prior knowledge approaches that incorporate biological information from online knowledge bases. However, no full-fledged benchmarking system exists that is extensible, provides built-in feature selection approaches, and a comprehensive result assessment encompassing classification performance, robustness, and biological relevance. Moreover, the particular needs of prior knowledge feature selection approaches, i.e. uniform access to knowledge bases, are not addressed. As a consequence, prior knowledge approaches are not evaluated amongst each other, leaving open questions regarding their effectiveness. Results We present the Comprior benchmark tool, which facilitates the rapid development and effortless benchmarking of feature selection approaches, with a special focus on prior knowledge approaches. Comprior is extensible by custom approaches, offers built-in standard feature selection approaches, enables uniform access to multiple knowledge bases, and provides a customizable evaluation infrastructure to compare multiple feature selection approaches regarding their classification performance, robustness, runtime, and biological relevance. Conclusion Comprior allows reproducible benchmarking especially of prior knowledge approaches, which facilitates their applicability and for the first time enables a comprehensive assessment of their effectiveness}, language = {en} } @article{RoseGroegerHoelzle2021, author = {Rose, Robert and Groeger, Lars and H{\"o}lzle, Katharina}, title = {The emergence of shared leadership in innovation labs}, series = {Frontiers in Psychology}, volume = {12}, journal = {Frontiers in Psychology}, publisher = {Frontiers Research Foundation}, address = {Lausanne}, issn = {1664-1078}, doi = {10.3389/fpsyg.2021.685167}, pages = {1 -- 13}, year = {2021}, abstract = {Implementing innovation laboratories to leverage intrapreneurship are an increasingly popular organizational practice. A typical feature in these creative environments are semi-autonomous teams in which multiple members collectively exert leadership influence, thereby challenging traditional command-and-control conceptions of leadership. An extensive body of research on the team-centric concept of shared leadership has recognized the potential for pluralized leadership structures in enhancing team effectiveness; however, little empirical work has been conducted in organizational contexts in which creativity is key. This study set out to explore antecedents of shared leadership and its influence on team creativity in an innovation lab. Building on extant shared leadership and innovation research, we propose antecedents customary to creative teamwork, that is, experimental culture, task reflexivity, and voice. Multisource data were collected from 104 team members and 49 evaluations of 29 coaches nested in 21 teams working in a prototypical innovation lab. We identify factors specific to creative teamwork that facilitate the emergence of shared leadership by providing room for experimentation, encouraging team members to speak up in the creative process, and cultivating a reflective application of entrepreneurial thinking. We provide specific exemplary activities for innovation lab teams to increase levels of shared leadership.}, language = {en} } @article{Schlosser2016, author = {Schlosser, Rainer}, title = {Stochastic dynamic pricing and advertising in isoelastic oligopoly models}, series = {European Journal of Operational Research}, volume = {259}, journal = {European Journal of Operational Research}, publisher = {Elsevier}, address = {Amsterdam}, issn = {0377-2217}, doi = {10.1016/j.ejor.2016.11.021}, pages = {1144 -- 1155}, year = {2016}, abstract = {In this paper, we analyze stochastic dynamic pricing and advertising differential games in special oligopoly markets with constant price and advertising elasticity. We consider the sale of perishable as well as durable goods and include adoption effects in the demand. Based on a unique stochastic feedback Nash equilibrium, we derive closed-form solution formulas of the value functions and the optimal feedback policies of all competing firms. Efficient simulation techniques are used to evaluate optimally controlled sales processes over time. This way, the evolution of optimal controls as well as the firms' profit distributions are analyzed. Moreover, we are able to compare feedback solutions of the stochastic model with its deterministic counterpart. We show that the market power of the competing firms is exactly the same as in the deterministic version of the model. Further, we discover two fundamental effects that determine the relation between both models. First, the volatility in demand results in a decline of expected profits compared to the deterministic model. Second, we find that saturation effects in demand have an opposite character. We show that the second effect can be strong enough to either exactly balance or even overcompensate the first one. As a result we are able to identify cases in which feedback solutions of the deterministic model provide useful approximations of solutions of the stochastic model.}, language = {en} } @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} } @book{GerkenUebernickeldePaula2022, author = {Gerken, Stefanie and Uebernickel, Falk and de Paula, Danielly}, title = {Design Thinking: a Global Study on Implementation Practices in Organizations}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-525-5}, doi = {10.25932/publishup-53466}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-534668}, publisher = {Universit{\"a}t Potsdam}, pages = {230}, year = {2022}, abstract = {These days design thinking is no longer a "new approach". Among practitioners, as well as academics, interest in the topic has gathered pace over the last two decades. However, opinions are divided over the longevity of the phenomenon: whether design thinking is merely "old wine in new bottles," a passing trend, or still evolving as it is being spread to an increasing number of organizations and industries. Despite its growing relevance and the diffusion of design thinking, knowledge on the actual status quo in organizations remains scarce. With a new study, the research team of Prof. Uebernickel and Stefanie Gerken investigates temporal developments and changes in design thinking practices in organizations over the past six years comparing the results of the 2015 "Parts without a whole" study with current practices and future developments. Companies of all sizes and from different parts of the world participated in the survey. The findings from qualitative interviews with experts, i.e., people who have years of knowledge with design thinking, were cross-checked with the results from an exploratory analysis of the survey data. This analysis uncovers significant variances and similarities in how design thinking is interpreted and applied in businesses.}, 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 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} } @article{ReinTaeumelHirschfeld2017, author = {Rein, Patrick and Taeumel, Marcel and Hirschfeld, Robert}, title = {Making the domain tangible}, series = {Design Thinking Research}, journal = {Design Thinking Research}, publisher = {Springer}, address = {New York}, isbn = {978-3-319-60967-6}, doi = {10.1007/978-3-319-60967-6_9}, pages = {171 -- 194}, year = {2017}, abstract = {Programmers collaborate continuously with domain experts to explore the problem space and to shape a solution that fits the users' needs. In doing so, all parties develop a shared vocabulary, which is above all a list of named concepts and their relationships to each other. Nowadays, many programmers favor object-oriented programming because it allows them to directly represent real-world concepts and interactions from the vocabulary as code. However, when existing domain data is not yet represented as objects, it becomes a challenge to initially bring existing domain data into object-oriented systems and to keep the source code readable. While source code might be comprehensible to programmers, domain experts can struggle, given their non-programming background. We present a new approach to provide a mapping of existing data sources into the object-oriented programming environment. We support keeping the code of the domain model compact and readable while adding implicit means to access external information as internal domain objects. This should encourage programmers to explore different ways to build the software system quickly. Eventually, our approach fosters communication with the domain experts, especially at the beginning of a project. When the details in the problem space are not yet clear, the source code provides a valuable, tangible communication artifact.}, language = {en} } @article{ThienenClanceyCorazzaetal.2018, author = {Thienen, Julia von and Clancey, William J. and Corazza, Giovanni Emanuele and Meinel, Christoph}, title = {Theoretical foundations of design thinking creative thinking theories}, series = {Design Thinking Research: Making Distinctions: Collaboration versus Cooperation}, journal = {Design Thinking Research: Making Distinctions: Collaboration versus Cooperation}, publisher = {Springer}, address = {New York}, isbn = {978-3-319-60967-6}, doi = {10.1007/978-3-319-60967-6_2}, pages = {13 -- 40}, year = {2018}, abstract = {Design thinking is acknowledged as a thriving innovation practice plus something more, something in the line of a deep understanding of innovation processes. At the same time, quite how and why design thinking works-in scientific terms-appeared an open question at first. Over recent years, empirical research has achieved great progress in illuminating the principles that make design thinking successful. Lately, the community began to explore an additional approach. Rather than setting up novel studies, investigations into the history of design thinking hold the promise of adding systematically to our comprehension of basic principles. This chapter makes a start in revisiting design thinking history with the aim of explicating scientific understandings that inform design thinking practices today. It offers a summary of creative thinking theories that were brought to Stanford Engineering in the 1950s by John E. Arnold.}, 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} } @book{MeinelJohnWollowski2022, author = {Meinel, Christoph and John, Catrina and Wollowski, Tobias}, title = {Die HPI Schul-Cloud - Von der Vision zur digitale Infrastruktur f{\"u}r deutsche Schulen}, number = {144}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-526-2}, issn = {1613-5652}, doi = {10.25932/publishup-53586}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-535860}, publisher = {Universit{\"a}t Potsdam}, pages = {v, 77}, year = {2022}, abstract = {Digitale Medien sind aus unserem Alltag kaum noch wegzudenken. Einer der zentralsten Bereiche f{\"u}r unsere Gesellschaft, die schulische Bildung, darf hier nicht hintanstehen. Wann immer der Einsatz digital unterst{\"u}tzter Tools p{\"a}dagogisch sinnvoll ist, muss dieser in einem sicheren Rahmen erm{\"o}glicht werden k{\"o}nnen. Die HPI Schul-Cloud ist dieser Vision gefolgt, die vom Nationalen IT-Gipfel 2016 angestoßen wurde und dem Bericht vorangestellt ist - gefolgt. Sie hat sich in den vergangenen f{\"u}nf Jahren vom Pilotprojekt zur unverzichtbaren IT-Infrastruktur f{\"u}r zahlreiche Schulen entwickelt. W{\"a}hrend der Corona-Pandemie hat sie f{\"u}r viele Tausend Schulen wichtige Unterst{\"u}tzung bei der Umsetzung ihres Bildungsauftrags geboten. Das Ziel, eine zukunftssichere und datenschutzkonforme Infrastruktur zur digitalen Unterst{\"u}tzung des Unterrichts zur Verf{\"u}gung zu stellen, hat sie damit mehr als erreicht. Aktuell greifen rund 1,4 Millionen Lehrkr{\"a}fte und Sch{\"u}lerinnen und Sch{\"u}ler bundesweit und an den deutschen Auslandsschulen auf die HPI Schul-Cloud zu.}, language = {de} } @misc{RazzaqKaminskiRomeroetal.2018, author = {Razzaq, Misbah and Kaminski, Roland and Romero, Javier and Schaub, Torsten 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} } @misc{ElsaidShawishMeinel2018, author = {Elsaid, Mohamed Esam and Shawish, Ahmed and Meinel, Christoph}, title = {Enhanced cost analysis of multiple virtual machines live migration in VMware environments}, series = {2018 IEEE 8th International Symposium on Cloud and Service Computing (SC2)}, journal = {2018 IEEE 8th International Symposium on Cloud and Service Computing (SC2)}, publisher = {IEEE}, address = {New York}, isbn = {978-1-7281-0236-8}, doi = {10.1109/SC2.2018.00010}, pages = {16 -- 23}, year = {2018}, abstract = {Live migration is an important feature in modern software-defined datacenters and cloud computing environments. Dynamic resource management, load balance, power saving and fault tolerance are all dependent on the live migration feature. Despite the importance of live migration, the cost of live migration cannot be ignored and may result in service availability degradation. Live migration cost includes the migration time, downtime, CPU overhead, network and power consumption. There are many research articles that discuss the problem of live migration cost with different scopes like analyzing the cost and relate it to the parameters that control it, proposing new migration algorithms that minimize the cost and also predicting the migration cost. For the best of our knowledge, most of the papers that discuss the migration cost problem focus on open source hypervisors. For the research articles focus on VMware environments, none of the published articles proposed migration time, network overhead and power consumption modeling for single and multiple VMs live migration. In this paper, we propose empirical models for the live migration time, network overhead and power consumption for single and multiple VMs migration. The proposed models are obtained using a VMware based testbed.}, language = {en} } @misc{KoetzingKrejca2018, author = {K{\"o}tzing, Timo and Krejca, Martin Stefan}, title = {First-Hitting times under additive drift}, series = {Parallel Problem Solving from Nature - PPSN XV, PT II}, volume = {11102}, journal = {Parallel Problem Solving from Nature - PPSN XV, PT II}, publisher = {Springer}, address = {Cham}, isbn = {978-3-319-99259-4}, issn = {0302-9743}, doi = {10.1007/978-3-319-99259-4_8}, pages = {92 -- 104}, year = {2018}, abstract = {For the last ten years, almost every theoretical result concerning the expected run time of a randomized search heuristic used drift theory, making it the arguably most important tool in this domain. Its success is due to its ease of use and its powerful result: drift theory allows the user to derive bounds on the expected first-hitting time of a random process by bounding expected local changes of the process - the drift. This is usually far easier than bounding the expected first-hitting time directly. Due to the widespread use of drift theory, it is of utmost importance to have the best drift theorems possible. We improve the fundamental additive, multiplicative, and variable drift theorems by stating them in a form as general as possible and providing examples of why the restrictions we keep are still necessary. Our additive drift theorem for upper bounds only requires the process to be nonnegative, that is, we remove unnecessary restrictions like a finite, discrete, or bounded search space. As corollaries, the same is true for our upper bounds in the case of variable and multiplicative drift.}, language = {en} } @misc{KoetzingKrejca2018, author = {K{\"o}tzing, Timo and Krejca, Martin Stefan}, title = {First-Hitting times for finite state spaces}, series = {Parallel Problem Solving from Nature - PPSN XV, PT II}, volume = {11102}, journal = {Parallel Problem Solving from Nature - PPSN XV, PT II}, publisher = {Springer}, address = {Cham}, isbn = {978-3-319-99259-4}, issn = {0302-9743}, doi = {10.1007/978-3-319-99259-4_7}, pages = {79 -- 91}, year = {2018}, abstract = {One of the most important aspects of a randomized algorithm is bounding its expected run time on various problems. Formally speaking, this means bounding the expected first-hitting time of a random process. The two arguably most popular tools to do so are the fitness level method and drift theory. The fitness level method considers arbitrary transition probabilities but only allows the process to move toward the goal. On the other hand, drift theory allows the process to move into any direction as long as it move closer to the goal in expectation; however, this tendency has to be monotone and, thus, the transition probabilities cannot be arbitrary. We provide a result that combines the benefit of these two approaches: our result gives a lower and an upper bound for the expected first-hitting time of a random process over {0,..., n} that is allowed to move forward and backward by 1 and can use arbitrary transition probabilities. In case that the transition probabilities are known, our bounds coincide and yield the exact value of the expected first-hitting time. Further, we also state the stationary distribution as well as the mixing time of a special case of our scenario.}, language = {en} } @misc{KoetzingLagodzinskiLengleretal.2018, author = {K{\"o}tzing, Timo and Lagodzinski, Julius Albert Gregor and Lengler, Johannes and Melnichenko, Anna}, title = {Destructiveness of Lexicographic Parsimony Pressure and Alleviation by a Concatenation Crossover in Genetic Programming}, series = {Parallel Problem Solving from Nature - PPSN XV}, volume = {11102}, journal = {Parallel Problem Solving from Nature - PPSN XV}, publisher = {Springer}, address = {Cham}, isbn = {978-3-319-99259-4}, issn = {0302-9743}, doi = {10.1007/978-3-319-99259-4_4}, pages = {42 -- 54}, year = {2018}, abstract = {For theoretical analyses there are two specifics distinguishing GP from many other areas of evolutionary computation. First, the variable size representations, in particular yielding a possible bloat (i.e. the growth of individuals with redundant parts). Second, the role and realization of crossover, which is particularly central in GP due to the tree-based representation. Whereas some theoretical work on GP has studied the effects of bloat, crossover had a surprisingly little share in this work. We analyze a simple crossover operator in combination with local search, where a preference for small solutions minimizes bloat (lexicographic parsimony pressure); the resulting algorithm is denoted Concatenation Crossover GP. For this purpose three variants of the wellstudied Majority test function with large plateaus are considered. We show that the Concatenation Crossover GP can efficiently optimize these test functions, while local search cannot be efficient for all three variants independent of employing bloat control.}, language = {en} } @misc{PerscheidFaberKrausetal.2018, author = {Perscheid, Cindy and Faber, Lukas and Kraus, Milena and Arndt, Paul and Janke, Michael and Rehfeldt, Sebastian and Schubotz, Antje and Slosarek, Tamara and Uflacker, Matthias}, title = {A tissue-aware gene selection approach for analyzing multi-tissue gene expression data}, series = {2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)}, journal = {2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)}, publisher = {IEEE}, address = {New York}, isbn = {978-1-5386-5488-0}, issn = {2156-1125}, doi = {10.1109/BIBM.2018.8621189}, pages = {2159 -- 2166}, year = {2018}, abstract = {High-throughput RNA sequencing (RNAseq) produces large data sets containing expression levels of thousands of genes. The analysis of RNAseq data leads to a better understanding of gene functions and interactions, which eventually helps to study diseases like cancer and develop effective treatments. Large-scale RNAseq expression studies on cancer comprise samples from multiple cancer types and aim to identify their distinct molecular characteristics. Analyzing samples from different cancer types implies analyzing samples from different tissue origin. Such multi-tissue RNAseq data sets require a meaningful analysis that accounts for the inherent tissue-related bias: The identified characteristics must not originate from the differences in tissue types, but from the actual differences in cancer types. However, current analysis procedures do not incorporate that aspect. As a result, we propose to integrate a tissue-awareness into the analysis of multi-tissue RNAseq data. We introduce an extension for gene selection that provides a tissue-wise context for every gene and can be flexibly combined with any existing gene selection approach. We suggest to expand conventional evaluation by additional metrics that are sensitive to the tissue-related bias. Evaluations show that especially low complexity gene selection approaches profit from introducing tissue-awareness.}, language = {en} } @misc{BinTareafBergerHennigetal.2019, author = {Bin Tareaf, Raad and Berger, Philipp and Hennig, Patrick and Meinel, Christoph}, title = {Personality exploration system for online social networks}, series = {2018 IEEE/WIC/ACM International Conference on Web Intelligence (WI)}, journal = {2018 IEEE/WIC/ACM International Conference on Web Intelligence (WI)}, publisher = {IEEE}, address = {New York}, isbn = {978-1-5386-7325-6}, doi = {10.1109/WI.2018.00-76}, pages = {301 -- 309}, year = {2019}, abstract = {User-generated content on social media platforms is a rich source of latent information about individual variables. Crawling and analyzing this content provides a new approach for enterprises to personalize services and put forward product recommendations. In the past few years, brands made a gradual appearance on social media platforms for advertisement, customers support and public relation purposes and by now it became a necessity throughout all branches. This online identity can be represented as a brand personality that reflects how a brand is perceived by its customers. We exploited recent research in text analysis and personality detection to build an automatic brand personality prediction model on top of the (Five-Factor Model) and (Linguistic Inquiry and Word Count) features extracted from publicly available benchmarks. The proposed model reported significant accuracy in predicting specific personality traits form brands. For evaluating our prediction results on actual brands, we crawled the Facebook API for 100k posts from the most valuable brands' pages in the USA and we visualize exemplars of comparison results and present suggestions for future directions.}, language = {en} } @misc{AndjelkovicBabicLietal.2019, author = {Andjelkovic, Marko and Babic, Milan and Li, Yuanqing and Schrape, Oliver and Krstić, Miloš and Kraemer, Rolf}, title = {Use of decoupling cells for mitigation of SET effects in CMOS combinational gates}, series = {2018 25th IEEE International Conference on Electronics, Circuits and Systems (ICECS)}, journal = {2018 25th IEEE International Conference on Electronics, Circuits and Systems (ICECS)}, publisher = {IEEE}, address = {New York}, isbn = {978-1-5386-9562-3}, doi = {10.1109/ICECS.2018.8617996}, pages = {361 -- 364}, year = {2019}, abstract = {This paper investigates the applicability of CMOS decoupling cells for mitigating the Single Event Transient (SET) effects in standard combinational gates. The concept is based on the insertion of two decoupling cells between the gate's output and the power/ground terminals. To verify the proposed hardening approach, extensive SPICE simulations have been performed with standard combinational cells designed in IHP's 130 nm bulk CMOS technology. Obtained simulation results have shown that the insertion of decoupling cells results in the increase of the gate's critical charge, thus reducing the gate's soft error rate (SER). Moreover, the decoupling cells facilitate the suppression of SET pulses propagating through the gate. It has been shown that the decoupling cells may be a competitive alternative to gate upsizing and gate duplication for hardening the gates with lower critical charge and multiple (3 or 4) inputs, as well as for filtering the short SET pulses induced by low-LET particles.}, language = {en} } @article{AmbassaKayemWolthusenetal.2018, author = {Ambassa, Pacome L. and Kayem, Anne Voluntas dei Massah and Wolthusen, Stephen D. and Meinel, Christoph}, title = {Inferring private user behaviour based on information leakage}, series = {Smart Micro-Grid Systems Security and Privacy}, volume = {71}, journal = {Smart Micro-Grid Systems Security and Privacy}, publisher = {Springer}, address = {Dordrecht}, isbn = {978-3-319-91427-5}, doi = {10.1007/978-3-319-91427-5_7}, pages = {145 -- 159}, year = {2018}, abstract = {In rural/remote areas, resource constrained smart micro-grid (RCSMG) architectures can provide a cost-effective power supply alternative in cases when connectivity to the national power grid is impeded by factors such as load shedding. RCSMG architectures can be designed to handle communications over a distributed lossy network in order to minimise operation costs. However, due to the unreliable nature of lossy networks communication data can be distorted by noise additions that alter the veracity of the data. In this chapter, we consider cases in which an adversary who is internal to the RCSMG, deliberately distorts communicated data to gain an unfair advantage over the RCSMG's users. The adversary's goal is to mask malicious data manipulations as distortions due to additive noise due to communication channel unreliability. Distinguishing malicious data distortions from benign distortions is important in ensuring trustworthiness of the RCSMG. Perturbation data anonymisation algorithms can be used to alter transmitted data to ensure that adversarial manipulation of the data reveals no information that the adversary can take advantage of. However, because existing data perturbation anonymisation algorithms operate by using additive noise to anonymise data, using these algorithms in the RCSMG context is challenging. This is due to the fact that distinguishing benign noise additions from malicious noise additions is a difficult problem. In this chapter, we present a brief survey of cases of privacy violations due to inferences drawn from observed power consumption patterns in RCSMGs centred on inference, and propose a method of mitigating these risks. The lesson here is that while RCSMGs give users more control over power management and distribution, good anonymisation is essential to protecting personal information on RCSMGs.}, language = {en} } @article{MarufuKayemWolthusen2018, author = {Marufu, Anesu M. C. and Kayem, Anne Voluntas dei Massah and Wolthusen, Stephen D.}, title = {The design and classification of cheating attacks on power marketing schemes in resource constrained smart micro-grids}, series = {Smart Micro-Grid Systems Security and Privacy}, volume = {71}, journal = {Smart Micro-Grid Systems Security and Privacy}, publisher = {Springer}, address = {Dordrecht}, isbn = {978-3-319-91427-5}, doi = {10.1007/978-3-319-91427-5_6}, pages = {103 -- 144}, year = {2018}, abstract = {In this chapter, we provide a framework to specify how cheating attacks can be conducted successfully on power marketing schemes in resource constrained smart micro-grids. This is an important problem because such cheating attacks can destabilise and in the worst case result in a breakdown of the micro-grid. We consider three aspects, in relation to modelling cheating attacks on power auctioning schemes. First, we aim to specify exactly how in spite of the resource constrained character of the micro-grid, cheating can be conducted successfully. Second, we consider how mitigations can be modelled to prevent cheating, and third, we discuss methods of maintaining grid stability and reliability even in the presence of cheating attacks. We use an Automated-Cheating-Attack (ACA) conception to build a taxonomy of cheating attacks based on the idea of adversarial acquisition of surplus energy. Adversarial acquisitions of surplus energy allow malicious users to pay less for access to more power than the quota allowed for the price paid. The impact on honest users, is the lack of an adequate supply of energy to meet power demand requests. We conclude with a discussion of the performance overhead of provoking, detecting, and mitigating such attacks efficiently.}, language = {en} } @article{KayemMeinelWolthusen2018, author = {Kayem, Anne Voluntas dei Massah and Meinel, Christoph and Wolthusen, Stephen D.}, title = {A resilient smart micro-grid architecture for resource constrained environments}, series = {Smart Micro-Grid Systems Security and Privacy}, volume = {71}, journal = {Smart Micro-Grid Systems Security and Privacy}, publisher = {Springer}, address = {Dordrecht}, isbn = {978-3-319-91427-5}, doi = {10.1007/978-3-319-91427-5_5}, pages = {71 -- 101}, year = {2018}, abstract = {Resource constrained smart micro-grid architectures describe a class of smart micro-grid architectures that handle communications operations over a lossy network and depend on a distributed collection of power generation and storage units. Disadvantaged communities with no or intermittent access to national power networks can benefit from such a micro-grid model by using low cost communication devices to coordinate the power generation, consumption, and storage. Furthermore, this solution is both cost-effective and environmentally-friendly. One model for such micro-grids, is for users to agree to coordinate a power sharing scheme in which individual generator owners sell excess unused power to users wanting access to power. Since the micro-grid relies on distributed renewable energy generation sources which are variable and only partly predictable, coordinating micro-grid operations with distributed algorithms is necessity for grid stability. Grid stability is crucial in retaining user trust in the dependability of the micro-grid, and user participation in the power sharing scheme, because user withdrawals can cause the grid to breakdown which is undesirable. In this chapter, we present a distributed architecture for fair power distribution and billing on microgrids. The architecture is designed to operate efficiently over a lossy communication network, which is an advantage for disadvantaged communities. We build on the architecture to discuss grid coordination notably how tasks such as metering, power resource allocation, forecasting, and scheduling can be handled. All four tasks are managed by a feedback control loop that monitors the performance and behaviour of the micro-grid, and based on historical data makes decisions to ensure the smooth operation of the grid. Finally, since lossy networks are undependable, differentiating system failures from adversarial manipulations is an important consideration for grid stability. We therefore provide a characterisation of potential adversarial models and discuss possible mitigation measures.}, language = {en} } @misc{KayemMeinelWolthusen2018, author = {Kayem, Anne Voluntas dei Massah and Meinel, Christoph and Wolthusen, Stephen D.}, title = {Smart micro-grid systems security and privacy preface}, series = {Smart micro-grid systems security and privacy}, volume = {71}, journal = {Smart micro-grid systems security and privacy}, publisher = {Springer}, address = {Dordrecht}, isbn = {978-3-319-91427-5}, doi = {10.1007/978-3-319-91427-5_1}, pages = {VII -- VIII}, year = {2018}, abstract = {Studies indicate that reliable access to power is an important enabler for economic growth. To this end, modern energy management systems have seen a shift from reliance on time-consuming manual procedures , to highly automated management , with current energy provisioning systems being run as cyber-physical systems . Operating energy grids as a cyber-physical system offers the advantage of increased reliability and dependability , but also raises issues of security and privacy. In this chapter, we provide an overview of the contents of this book showing the interrelation between the topics of the chapters in terms of smart energy provisioning. We begin by discussing the concept of smart-grids in general, proceeding to narrow our focus to smart micro-grids in particular. Lossy networks also provide an interesting framework for enabling the implementation of smart micro-grids in remote/rural areas, where deploying standard smart grids is economically and structurally infeasible. To this end, we consider an architectural design for a smart micro-grid suited to low-processing capable devices. We model malicious behaviour, and propose mitigation measures based properties to distinguish normal from malicious behaviour .}, language = {en} } @article{KayemWolthusenMeinel2018, author = {Kayem, Anne Voluntas dei Massah and Wolthusen, Stephen D. and Meinel, Christoph}, title = {Power Systems}, series = {Smart Micro-Grid Systems Security and Privacy}, volume = {71}, journal = {Smart Micro-Grid Systems Security and Privacy}, publisher = {Springer}, address = {Dordrecht}, isbn = {978-3-319-91427-5}, doi = {10.1007/978-3-319-91427-5_1}, pages = {1 -- 8}, year = {2018}, abstract = {Studies indicate that reliable access to power is an important enabler for economic growth. To this end, modern energy management systems have seen a shift from reliance on time-consuming manual procedures, to highly automated management, with current energy provisioning systems being run as cyber-physical systems. Operating energy grids as a cyber-physical system offers the advantage of increased reliability and dependability, but also raises issues of security and privacy. In this chapter, we provide an overview of the contents of this book showing the interrelation between the topics of the chapters in terms of smart energy provisioning. We begin by discussing the concept of smart-grids in general, proceeding to narrow our focus to smart micro-grids in particular. Lossy networks also provide an interesting framework for enabling the implementation of smart micro-grids in remote/rural areas, where deploying standard smart grids is economically and structurally infeasible. To this end, we consider an architectural design for a smart micro-grid suited to low-processing capable devices. We model malicious behaviour, and propose mitigation measures based properties to distinguish normal from malicious behaviour.}, language = {en} } @misc{BrandGiese2019, author = {Brand, Thomas and Giese, Holger Burkhard}, title = {Towards Generic Adaptive Monitoring}, series = {2018 IEEE 12th International Conference on Self-Adaptive and Self-Organizing Systems (SASO)}, journal = {2018 IEEE 12th International Conference on Self-Adaptive and Self-Organizing Systems (SASO)}, publisher = {IEEE}, address = {New York}, isbn = {978-1-5386-5172-8}, issn = {1949-3673}, doi = {10.1109/SASO.2018.00027}, pages = {156 -- 161}, year = {2019}, abstract = {Monitoring is a key prerequisite for self-adaptive software and many other forms of operating software. Monitoring relevant lower level phenomena like the occurrences of exceptions and diagnosis data requires to carefully examine which detailed information is really necessary and feasible to monitor. Adaptive monitoring permits observing a greater variety of details with less overhead, if most of the time the MAPE-K loop can operate using only a small subset of all those details. However, engineering such an adaptive monitoring is a major engineering effort on its own that further complicates the development of self-adaptive software. The proposed approach overcomes the outlined problems by providing generic adaptive monitoring via runtime models. It reduces the effort to introduce and apply adaptive monitoring by avoiding additional development effort for controlling the monitoring adaptation. Although the generic approach is independent from the monitoring purpose, it still allows for substantial savings regarding the monitoring resource consumption as demonstrated by an example.}, language = {en} } @misc{BlaesiusEubeFeldtkelleretal.2018, author = {Blaesius, Thomas and Eube, Jan and Feldtkeller, Thomas and Friedrich, Tobias and Krejca, Martin Stefan and Lagodzinski, Julius Albert Gregor and Rothenberger, Ralf and Severin, Julius and Sommer, Fabian and Trautmann, Justin}, title = {Memory-restricted Routing With Tiled Map Data}, series = {2018 IEEE International Conference on Systems, Man, and Cybernetics (SMC)}, journal = {2018 IEEE International Conference on Systems, Man, and Cybernetics (SMC)}, publisher = {IEEE}, address = {New York}, isbn = {978-1-5386-6650-0}, issn = {1062-922X}, doi = {10.1109/SMC.2018.00567}, pages = {3347 -- 3354}, year = {2018}, abstract = {Modern routing algorithms reduce query time by depending heavily on preprocessed data. The recently developed Navigation Data Standard (NDS) enforces a separation between algorithms and map data, rendering preprocessing inapplicable. Furthermore, map data is partitioned into tiles with respect to their geographic coordinates. With the limited memory found in portable devices, the number of tiles loaded becomes the major factor for run time. We study routing under these restrictions and present new algorithms as well as empirical evaluations. Our results show that, on average, the most efficient algorithm presented uses more than 20 times fewer tile loads than a normal A*.}, language = {en} } @misc{PodlesnyKayemvonSchorlemeretal.2018, author = {Podlesny, Nikolai Jannik and Kayem, Anne V. D. M. and von Schorlemer, Stephan and Uflacker, Matthias}, title = {Minimising Information Loss on Anonymised High Dimensional Data with Greedy In-Memory Processing}, series = {Database and Expert Systems Applications, DEXA 2018, PT I}, volume = {11029}, journal = {Database and Expert Systems Applications, DEXA 2018, PT I}, publisher = {Springer}, address = {Cham}, isbn = {978-3-319-98809-2}, issn = {0302-9743}, doi = {10.1007/978-3-319-98809-2_6}, pages = {85 -- 100}, year = {2018}, abstract = {Minimising information loss on anonymised high dimensional data is important for data utility. Syntactic data anonymisation algorithms address this issue by generating datasets that are neither use-case specific nor dependent on runtime specifications. This results in anonymised datasets that can be re-used in different scenarios which is performance efficient. However, syntactic data anonymisation algorithms incur high information loss on high dimensional data, making the data unusable for analytics. In this paper, we propose an optimised exact quasi-identifier identification scheme, based on the notion of k-anonymity, to generate anonymised high dimensional datasets efficiently, and with low information loss. The optimised exact quasi-identifier identification scheme works by identifying and eliminating maximal partial unique column combination (mpUCC) attributes that endanger anonymity. By using in-memory processing to handle the attribute selection procedure, we significantly reduce the processing time required. We evaluated the effectiveness of our proposed approach with an enriched dataset drawn from multiple real-world data sources, and augmented with synthetic values generated in close alignment with the real-world data distributions. Our results indicate that in-memory processing drops attribute selection time for the mpUCC candidates from 400s to 100s, while significantly reducing information loss. In addition, we achieve a time complexity speed-up of O(3(n/3)) approximate to O(1.4422(n)).}, language = {en} } @misc{GalkeGerstenkornScherp2018, author = {Galke, Lukas and Gerstenkorn, Gunnar and Scherp, Ansgar}, title = {A case atudy of closed-domain response suggestion with limited training data}, series = {Database and Expert Systems Applications : DEXA 2018 Iinternational workshops}, volume = {903}, journal = {Database and Expert Systems Applications : DEXA 2018 Iinternational workshops}, publisher = {Springer}, address = {Berlin}, isbn = {978-3-319-99133-7}, issn = {1865-0929}, doi = {10.1007/978-3-319-99133-7_18}, pages = {218 -- 229}, year = {2018}, abstract = {We analyze the problem of response suggestion in a closed domain along a real-world scenario of a digital library. We present a text-processing pipeline to generate question-answer pairs from chat transcripts. On this limited amount of training data, we compare retrieval-based, conditioned-generation, and dedicated representation learning approaches for response suggestion. Our results show that retrieval-based methods that strive to find similar, known contexts are preferable over parametric approaches from the conditioned-generation family, when the training data is limited. We, however, identify a specific representation learning approach that is competitive to the retrieval-based approaches despite the training data limitation.}, language = {en} } @misc{GrossTiwariHammer2018, author = {Gross, Sascha and Tiwari, Abhishek and Hammer, Christian}, title = {PlAnalyzer}, series = {Computer Security(ESORICS 2018), PT II}, volume = {11099}, journal = {Computer Security(ESORICS 2018), PT II}, publisher = {Springer}, address = {Cham}, isbn = {978-3-319-98989-1}, issn = {0302-9743}, doi = {10.1007/978-3-319-98989-1_3}, pages = {41 -- 59}, year = {2018}, abstract = {In this work we propose PIAnalyzer, a novel approach to analyze PendingIntent related vulnerabilities. We empirically evaluate PIAnalyzer on a set of 1000 randomly selected applications from the Google Play Store and find 1358 insecure usages of Pendinglntents, including 70 severe vulnerabilities. We manually inspected ten reported vulnerabilities out of which nine correctly reported vulnerabilities, indicating a high precision. The evaluation shows that PIAnalyzer is efficient with an average execution time of 13 seconds per application.}, language = {en} } @misc{FrickeDoellnerAsche2018, author = {Fricke, Andreas and D{\"o}llner, J{\"u}rgen Roland Friedrich and Asche, Hartmut}, title = {Servicification - Trend or Paradigm Shift in Geospatial Data Processing?}, series = {Computational Science and Its Applications - ICCSA 2018, PT III}, volume = {10962}, journal = {Computational Science and Its Applications - ICCSA 2018, PT III}, publisher = {Springer}, address = {Cham}, isbn = {978-3-319-95168-3}, issn = {0302-9743}, doi = {10.1007/978-3-319-95168-3_23}, pages = {339 -- 350}, year = {2018}, abstract = {Currently we are witnessing profound changes in the geospatial domain. Driven by recent ICT developments, such as web services, serviceoriented computing or open-source software, an explosion of geodata and geospatial applications or rapidly growing communities of non-specialist users, the crucial issue is the provision and integration of geospatial intelligence in these rapidly changing, heterogeneous developments. This paper introduces the concept of Servicification into geospatial data processing. Its core idea is the provision of expertise through a flexible number of web-based software service modules. Selection and linkage of these services to user profiles, application tasks, data resources, or additional software allow for the compilation of flexible, time-sensitive geospatial data handling processes. Encapsulated in a string of discrete services, the approach presented here aims to provide non-specialist users with geospatial expertise required for the effective, professional solution of a defined application problem. Providing users with geospatial intelligence in the form of web-based, modular services, is a completely different approach to geospatial data processing. This novel concept puts geospatial intelligence, made available through services encapsulating rule bases and algorithms, in the centre and at the disposal of the users, regardless of their expertise.}, language = {en} } @misc{HaarmannBatoulisNikajetal.2018, author = {Haarmann, Stephan and Batoulis, Kimon and Nikaj, Adriatik and Weske, Mathias}, title = {DMN Decision Execution on the Ethereum Blockchain}, series = {Advanced Information Systems Engineering, CAISE 2018}, volume = {10816}, journal = {Advanced Information Systems Engineering, CAISE 2018}, publisher = {Springer}, address = {Cham}, isbn = {978-3-319-91563-0}, issn = {0302-9743}, doi = {10.1007/978-3-319-91563-0_20}, pages = {327 -- 341}, year = {2018}, abstract = {Recently blockchain technology has been introduced to execute interacting business processes in a secure and transparent way. While the foundations for process enactment on blockchain have been researched, the execution of decisions on blockchain has not been addressed yet. In this paper we argue that decisions are an essential aspect of interacting business processes, and, therefore, also need to be executed on blockchain. The immutable representation of decision logic can be used by the interacting processes, so that decision taking will be more secure, more transparent, and better auditable. The approach is based on a mapping of the DMN language S-FEEL to Solidity code to be run on the Ethereum blockchain. The work is evaluated by a proof-of-concept prototype and an empirical cost evaluation.}, language = {en} } @misc{LimbergerGroplerBuschmannetal.2018, author = {Limberger, Daniel and Gropler, Anne and Buschmann, Stefan and D{\"o}llner, J{\"u}rgen Roland Friedrich and Wasty, Benjamin}, title = {OpenLL}, series = {22nd International Conference Information Visualisation (IV)}, journal = {22nd International Conference Information Visualisation (IV)}, publisher = {IEEE}, address = {New York}, isbn = {978-1-5386-7202-0}, doi = {10.1109/iV.2018.00039}, pages = {175 -- 181}, year = {2018}, abstract = {Today's rendering APIs lack robust functionality and capabilities for dynamic, real-time text rendering and labeling, which represent key requirements for 3D application design in many fields. As a consequence, most rendering systems are barely or not at all equipped with respective capabilities. This paper drafts the unified text rendering and labeling API OpenLL intended to complement common rendering APIs, frameworks, and transmission formats. For it, various uses of static and dynamic placement of labels are showcased and a text interaction technique is presented. Furthermore, API design constraints with respect to state-of-the-art text rendering techniques are discussed. This contribution is intended to initiate a community-driven specification of a free and open label library.}, language = {en} } @misc{SianiparSukmanaMeinel2019, author = {Sianipar, Johannes Harungguan and Sukmana, Muhammad Ihsan Haikal and Meinel, Christoph}, title = {Moving sensitive data against live memory dumping, spectre and meltdown attacks}, series = {26th International Conference on Systems Engineering (ICSEng)}, journal = {26th International Conference on Systems Engineering (ICSEng)}, publisher = {IEEE}, address = {New York}, isbn = {978-1-5386-7834-3}, pages = {8}, year = {2019}, abstract = {The emergence of cloud computing allows users to easily host their Virtual Machines with no up-front investment and the guarantee of always available anytime anywhere. But with the Virtual Machine (VM) is hosted outside of user's premise, the user loses the physical control of the VM as it could be running on untrusted host machines in the cloud. Malicious host administrator could launch live memory dumping, Spectre, or Meltdown attacks in order to extract sensitive information from the VM's memory, e.g. passwords or cryptographic keys of applications running in the VM. In this paper, inspired by the moving target defense (MTD) scheme, we propose a novel approach to increase the security of application's sensitive data in the VM by continuously moving the sensitive data among several memory allocations (blocks) in Random Access Memory (RAM). A movement function is added into the application source code in order for the function to be running concurrently with the application's main function. Our approach could reduce the possibility of VM's sensitive data in the memory to be leaked into memory dump file by 2 5\% and secure the sensitive data from Spectre and Meltdown attacks. Our approach's overhead depends on the number and the size of the sensitive data.}, language = {en} } @misc{RischKrestel2018, author = {Risch, Julian and Krestel, Ralf}, title = {My Approach = Your Apparatus?}, series = {Libraries}, journal = {Libraries}, publisher = {Association for Computing Machinery}, address = {New York}, isbn = {978-1-4503-5178-2}, issn = {2575-7865}, doi = {10.1145/3197026.3197038}, pages = {283 -- 292}, year = {2018}, abstract = {Comparative text mining extends from genre analysis and political bias detection to the revelation of cultural and geographic differences, through to the search for prior art across patents and scientific papers. These applications use cross-collection topic modeling for the exploration, clustering, and comparison of large sets of documents, such as digital libraries. However, topic modeling on documents from different collections is challenging because of domain-specific vocabulary. We present a cross-collection topic model combined with automatic domain term extraction and phrase segmentation. This model distinguishes collection-specific and collection-independent words based on information entropy and reveals commonalities and differences of multiple text collections. We evaluate our model on patents, scientific papers, newspaper articles, forum posts, and Wikipedia articles. In comparison to state-of-the-art cross-collection topic modeling, our model achieves up to 13\% higher topic coherence, up to 4\% lower perplexity, and up to 31\% higher document classification accuracy. More importantly, our approach is the first topic model that ensures disjunct general and specific word distributions, resulting in clear-cut topic representations.}, language = {en} } @phdthesis{Elsaid2022, author = {Elsaid, Mohamed Esameldin Mohamed}, title = {Virtual machines live migration cost modeling and prediction}, doi = {10.25932/publishup-54001}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-540013}, school = {Universit{\"a}t Potsdam}, pages = {xiv, 107}, year = {2022}, abstract = {Dynamic resource management is an essential requirement for private and public cloud computing environments. With dynamic resource management, the physical resources assignment to the cloud virtual resources depends on the actual need of the applications or the running services, which enhances the cloud physical resources utilization and reduces the offered services cost. In addition, the virtual resources can be moved across different physical resources in the cloud environment without an obvious impact on the running applications or services production. This means that the availability of the running services and applications in the cloud is independent on the hardware resources including the servers, switches and storage failures. This increases the reliability of using cloud services compared to the classical data-centers environments. In this thesis we briefly discuss the dynamic resource management topic and then deeply focus on live migration as the definition of the compute resource dynamic management. Live migration is a commonly used and an essential feature in cloud and virtual data-centers environments. Cloud computing load balance, power saving and fault tolerance features are all dependent on live migration to optimize the virtual and physical resources usage. As we will discuss in this thesis, live migration shows many benefits to cloud and virtual data-centers environments, however the cost of live migration can not be ignored. Live migration cost includes the migration time, downtime, network overhead, power consumption increases and CPU overhead. IT admins run virtual machines live migrations without an idea about the migration cost. So, resources bottlenecks, higher migration cost and migration failures might happen. The first problem that we discuss in this thesis is how to model the cost of the virtual machines live migration. Secondly, we investigate how to make use of machine learning techniques to help the cloud admins getting an estimation of this cost before initiating the migration for one of multiple virtual machines. Also, we discuss the optimal timing for a specific virtual machine before live migration to another server. Finally, we propose practical solutions that can be used by the cloud admins to be integrated with the cloud administration portals to answer the raised research questions above. Our research methodology to achieve the project objectives is to propose empirical models based on using VMware test-beds with different benchmarks tools. Then we make use of the machine learning techniques to propose a prediction approach for virtual machines live migration cost. Timing optimization for live migration is also proposed in this thesis based on using the cost prediction and data-centers network utilization prediction. Live migration with persistent memory clusters is also discussed at the end of the thesis. The cost prediction and timing optimization techniques proposed in this thesis could be practically integrated with VMware vSphere cluster portal such that the IT admins can now use the cost prediction feature and timing optimization option before proceeding with a virtual machine live migration. Testing results show that our proposed approach for VMs live migration cost prediction shows acceptable results with less than 20\% prediction error and can be easily implemented and integrated with VMware vSphere as an example of a commonly used resource management portal for virtual data-centers and private cloud environments. The results show that using our proposed VMs migration timing optimization technique also could save up to 51\% of migration time of the VMs migration time for memory intensive workloads and up to 27\% of the migration time for network intensive workloads. This timing optimization technique can be useful for network admins to save migration time with utilizing higher network rate and higher probability of success. At the end of this thesis, we discuss the persistent memory technology as a new trend in servers memory technology. Persistent memory modes of operation and configurations are discussed in detail to explain how live migration works between servers with different memory configuration set up. Then, we build a VMware cluster with persistent memory inside server and also with DRAM only servers to show the live migration cost difference between the VMs with DRAM only versus the VMs with persistent memory inside.}, language = {en} }