@article{KerrLorenzSchoenetal.2021, author = {Kerr, John and Lorenz, Anja and Sch{\"o}n, Sandra and Ebner, Martin and Wittke, Andreas}, title = {Open Tools and Methods to Support the Development of MOOCs}, series = {EMOOCs 2021}, volume = {2021}, journal = {EMOOCs 2021}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-512-5}, doi = {10.25932/publishup-51721}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-517219}, pages = {187 -- 200}, year = {2021}, abstract = {There are a plethora of ways to guide and support people to learn about MOOC (massive open online course) development, from their first interest, sourcing supportive resources, methods and tools to better aid their understanding of the concepts and pedagogical approaches of MOOC design, to becoming a MOOC developer. This contribution highlights tools and methods that are openly available and re-usable under Creative Commons licenses. Our collection builds upon the experiences from three MOOC development and hosting teams with joint experiences of several hundred MOOCs (University of Applied Sciences in L{\"u}beck, Graz University of Technology, University of Glasgow) in three European countries, which are Germany, Austria and the UK. The contribution recommends and shares experiences with short articles and poster for first information sharing a Monster MOOC assignment for beginners, a MOOC canvas for first sketches, the MOOC design kit for details of instructional design and a MOOC for MOOC makers and a MOOC map as introduction into a certain MOOC platform.}, language = {en} } @article{JonsonCarlonGaddemHernandezReyesetal.2021, author = {Jonson Carlon, May Kristine and Gaddem, Mohamed Rami and Hern{\´a}ndez Reyes, C{\´e}sar Augusto and Nagahama, Toru and Cross, Jeffrey S.}, title = {Investigating Mechanical Engineering Learners' Satisfaction with a Revised Monozukuri MOOC}, series = {EMOOCs 2021}, volume = {2021}, journal = {EMOOCs 2021}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-512-5}, doi = {10.25932/publishup-51726}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-517266}, pages = {237 -- 247}, year = {2021}, abstract = {Aside from providing instructional materials to the public, developing massive open online courses (MOOCs) can benefit institutions in different ways. Some examples include providing training opportunities for their students aspiring to work in the online learning space, strengthening its brand recognition through courses appealing to enthusiasts, and enabling online linkages with other universities. One such example is the monozukuri MOOC offered by the Tokyo Institute of Technology on edX, which initially presented the Japanese philosophy of making things in the context of a mechanical engineering course. In this paper, we describe the importance of involving a course development team with a diverse background. The monozukuri MOOC and its revision enabled us to showcase an otherwise distinctively Japanese topic (philosophy) as an intersection of various topics of interest to learners with an equally diverse background. The revision resulted in discussing monozukuri in a mechanical engineering lesson and how monozukuri is actively being practiced in the Japanese workplace and academic setting while juxtaposing it to the relatively Western concept of experiential learning. Aside from presenting the course with a broader perspective, the revision had been an exercise for its team members on working in a multicultural environment within a Japanese institution, thus developing their project management and communication skills.}, language = {en} } @article{TopaliChountaOrtegaArranzetal.2021, author = {Topali, Paraskevi and Chounta, Irene-Angelica and Ortega-Arranz, Alejandro and Villagr{\´a}-Sobrino, Sara L. and Mart{\´i}nez-Mon{\´e}s, Alejandra}, title = {CoFeeMOOC-v.2}, series = {EMOOCs 2021}, volume = {2021}, journal = {EMOOCs 2021}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-512-5}, doi = {10.25932/publishup-51724}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-517241}, pages = {209 -- 217}, year = {2021}, abstract = {Providing adequate support to MOOC participants is often a challenging task due to massiveness of the learners' population and the asynchronous communication among peers and MOOC practitioners. This workshop aims at discussing common learners' problems reported in the literature and reflect on designing adequate feedback interventions with the use of learning data. Our aim is three-fold: a) to pinpoint MOOC aspects that impact the planning of feedback, b) to explore the use of learning data in designing feedback strategies, and c) to propose design guidelines for developing and delivering scaffolding interventions for personalized feedback in MOOCs. To do so, we will carry out hands-on activities that aim to involve participants in interpreting learning data and using them to design adaptive feedback. This workshop appeals to researchers, practitioners and MOOC stakeholders who aim to providing contextualized scaffolding. We envision that this workshop will provide insights for bridging the gap between pedagogical theory and practice when it comes to feedback interventions in MOOCs.}, language = {en} } @article{GershonRuiperezValienteAlexandron2021, author = {Gershon, Sa'ar Karp and Ruip{\´e}rez-Valiente, Jos{\´e} A. and Alexandron, Giora}, title = {MOOC Monetization Changes and Completion Rates}, series = {EMOOCs 2021}, volume = {2021}, journal = {EMOOCs 2021}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-512-5}, doi = {10.25932/publishup-51718}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-517189}, pages = {169 -- 179}, year = {2021}, abstract = {Massive Open Online Courses (MOOCs) offer online courses at low cost for anyone with an internet access. At its early days, the MOOC movement raised the flag of democratizing education, but soon enough, this utopian idea collided with the need to find sustainable business models. Moving from open access to a new financially sustainable certification and monetization policy in December 2015 we aim at this change-point and observe the completion rates before and after this monetary change. In this study we investigate the impact of the change on learners from countries of different development status. Our findings suggest that this change has lowered the completion rates among learners from developing countries, increasing gaps that already existed between global learners from countries of low and high development status. This suggests that more inclusive monetization policies may help MOOCs benefits to spread more equally among global learners.}, language = {en} } @article{PoceReValente2021, author = {Poce, Antonella and Re, Maria Rosaria and Valente, Mara}, title = {Evaluating OERs in Museum Education Context}, series = {EMOOCs 2021}, volume = {2021}, journal = {EMOOCs 2021}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-512-5}, doi = {10.25932/publishup-51717}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-517178}, pages = {159 -- 168}, year = {2021}, abstract = {This paper aims to present the results of a higher education experience promoted by the research centres INTELLECT (University of Modena and Reggio Emilia) and CDM (University of Roma Tre), as part of difference master's degrees programme of the academic years 2018/2019, 2019/2020, and 2020/2021. Through different online activities, 37 students attended and evaluated a MOOC on museum education content, such promoting their professionals and transverse skills, such as critical thinking, and developing their knowledge relative to OERs, within culture and heritage education contexts. Moreover, results from the online evaluation activities support the implementation of the MOOC in a collaborative way: during the academic years, evaluation data have been used by researcher to make changes to the course modules, thus realizing a more effective online path from and educational point of view.}, language = {en} } @article{BeirneNicGiollaMhichilBrownetal.2021, author = {Beirne, Elaine and Nic Giolla Mhich{\´i}l, Mair{\´e}ad and Brown, Mark and Mac Lochlainn, Conch{\´u}r}, title = {Confidence Counts}, series = {EMOOCs 2021}, volume = {2021}, journal = {EMOOCs 2021}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-512-5}, doi = {10.25932/publishup-51722}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-517220}, pages = {201 -- 208}, year = {2021}, abstract = {The increasing reliance on online learning in higher education has been further expedited by the on-going Covid-19 pandemic. Students need to be supported as they adapt to this new learning environment. Research has established that learners with positive online learning self-efficacy beliefs are more likely to persevere and achieve their higher education goals when learning online. In this paper, we explore how MOOC design can contribute to the four sources of self-efficacy beliefs posited by Bandura [4]. Specifically, we will explore, drawing on learner reflections, whether design elements of the MOOC, The Digital Edge: Essentials for the Online Learner, provided participants with the necessary mastery experiences, vicarious experiences, verbal persuasion, and affective regulation opportunities, to evaluate and develop their online learning self-efficacy beliefs. Findings from a content analysis of discussion forum posts show that learners referenced three of the four information sources when reflecting on their experience of the MOOC. This paper illustrates the potential of MOOCs as a pedagogical tool for enhancing online learning self-efficacy among students.}, language = {en} } @article{DespujolTurroBusquets2021, author = {Despujol, Ignacio and Turr{\´o}, Carlos and Busquets, Jaime}, title = {Universitat Polit{\`e}cnica de Val{\`e}ncia's Experience with EDX MOOC Initiatives During the Covid Lockdown}, series = {EMOOCs 2021}, volume = {2021}, journal = {EMOOCs 2021}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-512-5}, doi = {10.25932/publishup-51719}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-517196}, pages = {181 -- 185}, year = {2021}, abstract = {In March 2020, when massive lockdowns started to be enforced around the world to contain the spread of the COVID-19 pandemic, edX launched two initiatives to help students around the world providing free certificates for its courses, RAP, for member institutions and OCE, for any accredited academic institution. In this paper we analyze how Universitat Polt{\`e}cnica de Val{\`e}ncia contributed with its courses to both initiatives, providing almost 14,000 free certificate codes in total, and how UPV used the RAP initiative as a customer, describing the mechanism used to distribute more than 22,000 codes for free certificates to more than 7,000 UPV community members, what led to the achievement of more than 5,000 free certificates. We also comment the results of a post initiative survey answered by 1,612 UPV members about 3,241 edX courses, in which they communicated a satisfaction of 4,69 over 5 with the initiative.}, language = {en} } @article{LambersOrejas2021, author = {Lambers, Leen and Orejas, Fernando}, title = {Transformation rules with nested application conditions}, series = {Theoretical computer science}, volume = {884}, journal = {Theoretical computer science}, publisher = {Elsevier}, address = {Amsterdam}, issn = {0304-3975}, doi = {10.1016/j.tcs.2021.07.023}, pages = {44 -- 67}, year = {2021}, abstract = {Recently, initial conflicts were introduced in the framework of M-adhesive categories as an important optimization of critical pairs. In particular, they represent a proper subset such that each conflict is represented in a minimal context by a unique initial one. The theory of critical pairs has been extended in the framework of M-adhesive categories to rules with nested application conditions (ACs), restricting the applicability of a rule and generalizing the well-known negative application conditions. A notion of initial conflicts for rules with ACs does not exist yet. In this paper, on the one hand, we extend the theory of initial conflicts in the framework of M-adhesive categories to transformation rules with ACs. They represent a proper subset again of critical pairs for rules with ACs, and represent each conflict in a minimal context uniquely. They are moreover symbolic because we can show that in general no finite and complete set of conflicts for rules with ACs exists. On the other hand, we show that critical pairs are minimally M-complete, whereas initial conflicts are minimally complete. Finally, we introduce important special cases of rules with ACs for which we can obtain finite, minimally (M-)complete sets of conflicts.}, language = {en} } @article{KreowskyStabernack2021, author = {Kreowsky, Philipp and Stabernack, Christian Benno}, title = {A full-featured FPGA-based pipelined architecture for SIFT extraction}, series = {IEEE access : practical research, open solutions / Institute of Electrical and Electronics Engineers}, volume = {9}, journal = {IEEE access : practical research, open solutions / Institute of Electrical and Electronics Engineers}, publisher = {Inst. of Electr. and Electronics Engineers}, address = {New York, NY}, issn = {2169-3536}, doi = {10.1109/ACCESS.2021.3104387}, pages = {128564 -- 128573}, year = {2021}, abstract = {Image feature detection is a key task in computer vision. Scale Invariant Feature Transform (SIFT) is a prevalent and well known algorithm for robust feature detection. However, it is computationally demanding and software implementations are not applicable for real-time performance. In this paper, a versatile and pipelined hardware implementation is proposed, that is capable of computing keypoints and rotation invariant descriptors on-chip. All computations are performed in single precision floating-point format which makes it possible to implement the original algorithm with little alteration. Various rotation resolutions and filter kernel sizes are supported for images of any resolution up to ultra-high definition. For full high definition images, 84 fps can be processed. Ultra high definition images can be processed at 21 fps.}, language = {en} } @article{KossmannPapenbrockNaumann2021, author = {Koßmann, Jan and Papenbrock, Thorsten and Naumann, Felix}, title = {Data dependencies for query optimization}, series = {The VLDB journal : the international journal on very large data bases / publ. on behalf of the VLDB Endowment}, volume = {31}, journal = {The VLDB journal : the international journal on very large data bases / publ. on behalf of the VLDB Endowment}, number = {1}, publisher = {Springer}, address = {Berlin ; Heidelberg ; New York}, issn = {1066-8888}, doi = {10.1007/s00778-021-00676-3}, pages = {1 -- 22}, year = {2021}, abstract = {Effective query optimization is a core feature of any database management system. While most query optimization techniques make use of simple metadata, such as cardinalities and other basic statistics, other optimization techniques are based on more advanced metadata including data dependencies, such as functional, uniqueness, order, or inclusion dependencies. This survey provides an overview, intuitive descriptions, and classifications of query optimization and execution strategies that are enabled by data dependencies. We consider the most popular types of data dependencies and focus on optimization strategies that target the optimization of relational database queries. The survey supports database vendors to identify optimization opportunities as well as DBMS researchers to find related work and open research questions.}, language = {en} } @article{QuinzanGoebelWagneretal.2021, author = {Quinzan, Francesco and G{\"o}bel, Andreas and Wagner, Markus and Friedrich, Tobias}, title = {Evolutionary algorithms and submodular functions}, series = {Natural computing : an innovative journal bridging biosciences and computer sciences ; an international journal}, volume = {20}, journal = {Natural computing : an innovative journal bridging biosciences and computer sciences ; an international journal}, number = {3}, publisher = {Springer Science + Business Media B.V.}, address = {Dordrecht}, issn = {1572-9796}, doi = {10.1007/s11047-021-09841-7}, pages = {561 -- 575}, year = {2021}, abstract = {A core operator of evolutionary algorithms (EAs) is the mutation. Recently, much attention has been devoted to the study of mutation operators with dynamic and non-uniform mutation rates. Following up on this area of work, we propose a new mutation operator and analyze its performance on the (1 + 1) Evolutionary Algorithm (EA). Our analyses show that this mutation operator competes with pre-existing ones, when used by the (1 + 1) EA on classes of problems for which results on the other mutation operators are available. We show that the (1 + 1) EA using our mutation operator finds a (1/3)-approximation ratio on any non-negative submodular function in polynomial time. We also consider the problem of maximizing a symmetric submodular function under a single matroid constraint and show that the (1 + 1) EA using our operator finds a (1/3)-approximation within polynomial time. This performance matches that of combinatorial local search algorithms specifically designed to solve these problems and outperforms them with constant probability. Finally, we evaluate the performance of the (1 + 1) EA using our operator experimentally by considering two applications: (a) the maximum directed cut problem on real-world graphs of different origins, with up to 6.6 million vertices and 56 million edges and (b) the symmetric mutual information problem using a four month period air pollution data set. In comparison with uniform mutation and a recently proposed dynamic scheme, our operator comes out on top on these instances.}, language = {en} } @article{MagkosKupschBruno2021, author = {Magkos, Sotirios and Kupsch, Andreas and Bruno, Giovanni}, title = {Suppression of cone-beam artefacts with Direct Iterative Reconstruction Computed Tomography Trajectories (DIRECTT)}, series = {Journal of imaging : open access journal}, volume = {7}, journal = {Journal of imaging : open access journal}, number = {8}, publisher = {MDPI}, address = {Basel}, issn = {2313-433X}, doi = {10.3390/jimaging7080147}, pages = {9}, year = {2021}, abstract = {The reconstruction of cone-beam computed tomography data using filtered back-projection algorithms unavoidably results in severe artefacts. We describe how the Direct Iterative Reconstruction of Computed Tomography Trajectories (DIRECTT) algorithm can be combined with a model of the artefacts for the reconstruction of such data. The implementation of DIRECTT results in reconstructed volumes of superior quality compared to the conventional algorithms.}, language = {en} } @article{PerugiaPaetzelPruesmannAlanenpaeaeetal.2021, author = {Perugia, Giulia and Paetzel-Pr{\"u}smann, Maike and Alanenp{\"a}{\"a}, Madelene and Castellano, Ginevra}, title = {I can see it in your eyes}, series = {Frontiers in robotics and AI}, volume = {8}, journal = {Frontiers in robotics and AI}, publisher = {Frontiers Media}, address = {Lausanne}, issn = {2296-9144}, doi = {10.3389/frobt.2021.645956}, pages = {18}, year = {2021}, abstract = {Over the past years, extensive research has been dedicated to developing robust platforms and data-driven dialog models to support long-term human-robot interactions. However, little is known about how people's perception of robots and engagement with them develop over time and how these can be accurately assessed through implicit and continuous measurement techniques. In this paper, we explore this by involving participants in three interaction sessions with multiple days of zero exposure in between. Each session consists of a joint task with a robot as well as two short social chats with it before and after the task. We measure participants' gaze patterns with a wearable eye-tracker and gauge their perception of the robot and engagement with it and the joint task using questionnaires. Results disclose that aversion of gaze in a social chat is an indicator of a robot's uncanniness and that the more people gaze at the robot in a joint task, the worse they perform. In contrast with most HRI literature, our results show that gaze toward an object of shared attention, rather than gaze toward a robotic partner, is the most meaningful predictor of engagement in a joint task. Furthermore, the analyses of gaze patterns in repeated interactions disclose that people's mutual gaze in a social chat develops congruently with their perceptions of the robot over time. These are key findings for the HRI community as they entail that gaze behavior can be used as an implicit measure of people's perception of robots in a social chat and of their engagement and task performance in a joint task.}, language = {en} } @article{OosthoekDoerr2021, author = {Oosthoek, Kris and D{\"o}rr, Christian}, title = {Cyber security threats to bitcoin exchanges}, series = {IEEE transactions on network and service management : a publication of the IEEE}, volume = {18}, journal = {IEEE transactions on network and service management : a publication of the IEEE}, number = {2}, publisher = {IEEE}, address = {New York}, issn = {1932-4537}, doi = {10.1109/TNSM.2020.3046145}, pages = {1616 -- 1628}, year = {2021}, abstract = {Bitcoin is gaining traction as an alternative store of value. Its market capitalization transcends all other cryptocurrencies in the market. But its high monetary value also makes it an attractive target to cyber criminal actors. Hacking campaigns usually target an ecosystem's weakest points. In Bitcoin, the exchange platforms are one of them. Each exchange breach is a threat not only to direct victims, but to the credibility of Bitcoin's entire ecosystem. Based on an extensive analysis of 36 breaches of Bitcoin exchanges, we show the attack patterns used to exploit Bitcoin exchange platforms using an industry standard for reporting intelligence on cyber security breaches. Based on this we are able to provide an overview of the most common attack vectors, showing that all except three hacks were possible due to relatively lax security. We show that while the security regimen of Bitcoin exchanges is subpar compared to other financial service providers, the use of stolen credentials, which does not require any hacking, is decreasing. We also show that the amount of BTC taken during a breach is decreasing, as well as the exchanges that terminate after being breached. Furthermore we show that overall security posture has improved, but still has major flaws. To discover adversarial methods post-breach, we have analyzed two cases of BTC laundering. Through this analysis we provide insight into how exchange platforms with lax cyber security even further increase the intermediary risk introduced by them into the Bitcoin ecosystem.}, language = {en} } @article{KuehlMuenzer2021, author = {K{\"u}hl, Tim and M{\"u}nzer, Stefan}, title = {Learning about a serious disease}, series = {Journal of computer assisted learning : JCAL}, volume = {37}, journal = {Journal of computer assisted learning : JCAL}, number = {5}, publisher = {Wiley-Blackwell}, address = {Oxford [u.a.]}, issn = {0266-4909}, doi = {10.1111/jcal.12571}, pages = {1312 -- 1323}, year = {2021}, abstract = {According to the personalization principle, addressing learners by means of a personalized compared to a nonpersonalized message can foster learning. Interestingly, though, a recent study found that the personalization principle can invert for aversive contents. The present study investigated whether the negative effect of a personalized message for an aversive content can be compensated when learners are in a happy mood. It was hypothesized that the negative effect of a personalized compared to a nonpersonalized message would only be observable for participants in a sad mood, while for participants in a happy mood a personalized message should be beneficial. A 2 x 2 between-subject design with mood (happy vs. sad) and personalization (personalized vs. nonpersonalized message) was used (N = 125 University students). Mood was experimentally varied prior to learning. Learning outcomes were measured by a retention and a transfer test. Results were essentially in line with the assumption: For participants in the sad mood condition, a negative effect of a personalized message was observable for retention and transfer. For participants in the happy mood condition, a positive effect of personalized message was observable for retention, but no effect for transfer. Note that the manipulation check measure for the mood induction procedure did not detect differences between conditions; this may be due to a shortcoming of the used measure (as indicated by an additional evaluation study). The study emphasizes the importance to consider the inherent emotional content of a topic, such as its aversive nature, since the emotional content of a topic can be a boundary condition for design principles in multimedia learning. The study also highlights the complex interplay of externally induced and inherently arising emotions.}, language = {en} } @article{SchneiderLambersOrejas2021, author = {Schneider, Sven and Lambers, Leen and Orejas, Fernando}, title = {A logic-based incremental approach to graph repair featuring delta preservation}, series = {International journal on software tools for technology transfer : STTT}, volume = {23}, journal = {International journal on software tools for technology transfer : STTT}, number = {3}, publisher = {Springer}, address = {Berlin ; Heidelberg}, issn = {1433-2779}, doi = {10.1007/s10009-020-00584-x}, pages = {369 -- 410}, year = {2021}, abstract = {We introduce a logic-based incremental approach to graph repair, generating a sound and complete (upon termination) overview of least-changing graph repairs from which a user may select a graph repair based on non-formalized further requirements. This incremental approach features delta preservation as it allows to restrict the generation of graph repairs to delta-preserving graph repairs, which do not revert the additions and deletions of the most recent consistency-violating graph update. We specify consistency of graphs using the logic of nested graph conditions, which is equivalent to first-order logic on graphs. Technically, the incremental approach encodes if and how the graph under repair satisfies a graph condition using the novel data structure of satisfaction trees, which are adapted incrementally according to the graph updates applied. In addition to the incremental approach, we also present two state-based graph repair algorithms, which restore consistency of a graph independent of the most recent graph update and which generate additional graph repairs using a global perspective on the graph under repair. We evaluate the developed algorithms using our prototypical implementation in the tool AutoGraph and illustrate our incremental approach using a case study from the graph database domain.}, language = {en} } @article{GoebelLagodzinskiSeidel2021, author = {G{\"o}bel, Andreas and Lagodzinski, Gregor J. A. and Seidel, Karen}, title = {Counting homomorphisms to trees modulo a prime}, series = {ACM transactions on computation theory : TOCT / Association for Computing Machinery}, volume = {13}, journal = {ACM transactions on computation theory : TOCT / Association for Computing Machinery}, number = {3}, publisher = {Association for Computing Machinery}, address = {New York}, issn = {1942-3454}, doi = {10.1145/3460958}, pages = {1 -- 33}, year = {2021}, abstract = {Many important graph-theoretic notions can be encoded as counting graph homomorphism problems, such as partition functions in statistical physics, in particular independent sets and colourings. In this article, we study the complexity of \#(p) HOMSTOH, the problem of counting graph homomorphisms from an input graph to a graph H modulo a prime number p. Dyer and Greenhill proved a dichotomy stating that the tractability of non-modular counting graph homomorphisms depends on the structure of the target graph. Many intractable cases in non-modular counting become tractable in modular counting due to the common phenomenon of cancellation. In subsequent studies on counting modulo 2, however, the influence of the structure of H on the tractability was shown to persist, which yields similar dichotomies.
Our main result states that for every tree H and every prime p the problem \#pHOMSTOH is either polynomial time computable or \#P-p-complete. This relates to the conjecture of Faben and Jerrum stating that this dichotomy holds for every graph H when counting modulo 2. In contrast to previous results on modular counting, the tractable cases of \#pHOMSTOH are essentially the same for all values of the modulo when H is a tree. To prove this result, we study the structural properties of a homomorphism. As an important interim result, our study yields a dichotomy for the problem of counting weighted independent sets in a bipartite graph modulo some prime p. These results are the first suggesting that such dichotomies hold not only for the modulo 2 case but also for the modular counting functions of all primes p.}, language = {en} } @article{DoerrKrejca2021, author = {Doerr, Benjamin and Krejca, Martin Stefan}, title = {A simplified run time analysis of the univariate marginal distribution algorithm on LeadingOnes}, series = {Theoretical computer science}, volume = {851}, journal = {Theoretical computer science}, publisher = {Elsevier}, address = {Amsterdam}, issn = {0304-3975}, doi = {10.1016/j.tcs.2020.11.028}, pages = {121 -- 128}, year = {2021}, abstract = {With elementary means, we prove a stronger run time guarantee for the univariate marginal distribution algorithm (UMDA) optimizing the LEADINGONES benchmark function in the desirable regime with low genetic drift. If the population size is at least quasilinear, then, with high probability, the UMDA samples the optimum in a number of iterations that is linear in the problem size divided by the logarithm of the UMDA's selection rate. This improves over the previous guarantee, obtained by Dang and Lehre (2015) via the deep level-based population method, both in terms of the run time and by demonstrating further run time gains from small selection rates. Under similar assumptions, we prove a lower bound that matches our upper bound up to constant factors.}, language = {en} } @article{HaarmannHolfterPufahletal.2021, author = {Haarmann, Stephan and Holfter, Adrian and Pufahl, Luise and Weske, Mathias}, title = {Formal framework for checking compliance of data-driven case management}, series = {Journal on data semantics : JoDS}, volume = {10}, journal = {Journal on data semantics : JoDS}, number = {1-2}, publisher = {Springer}, address = {Heidelberg}, issn = {1861-2032}, doi = {10.1007/s13740-021-00120-3}, pages = {143 -- 163}, year = {2021}, abstract = {Business processes are often specified in descriptive or normative models. Both types of models should adhere to internal and external regulations, such as company guidelines or laws. Employing compliance checking techniques, it is possible to verify process models against rules. While traditionally compliance checking focuses on well-structured processes, we address case management scenarios. In case management, knowledge workers drive multi-variant and adaptive processes. Our contribution is based on the fragment-based case management approach, which splits a process into a set of fragments. The fragments are synchronized through shared data but can, otherwise, be dynamically instantiated and executed. We formalize case models using Petri nets. We demonstrate the formalization for design-time and run-time compliance checking and present a proof-of-concept implementation. The application of the implemented compliance checking approach to a use case exemplifies its effectiveness while designing a case model. The empirical evaluation on a set of case models for measuring the performance of the approach shows that rules can often be checked in less than a second.}, language = {en} } @article{MaldonadoMahauadValdiviezoCarvalloetal.2021, author = {Maldonado-Mahauad, Jorge and Valdiviezo, Javier and Carvallo, Juan Pablo and Samaniego-Erazo, Nicolay}, title = {The MOOC-CEDIA Observatory}, series = {EMOOCs 2021}, volume = {2021}, journal = {EMOOCs 2021}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-512-5}, doi = {10.25932/publishup-51715}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-517153}, pages = {143 -- 158}, year = {2021}, abstract = {In the last few years, an important amount of Massive Open Online Courses (MOOCS) has been made available to the worldwide community, mainly by European and North American universities (i.e. United States). Since its emergence, the adoption of these educational resources has been widely studied by several research groups and universities with the aim of understanding their evolution and impact in educational models, through the time. In the case of Latin America, data from the MOOC-UC Observatory (updated until 2018) shows that, the adoption of these courses by universities in the region has been slow and heterogeneous. In the specific case of Ecuador, although some data is available, there is lack of information regarding the construction, publication and/or adoption of such courses by universities in the country. Moreover, there are not updated studies designed to identify and analyze the barriers and factors affecting the adoption of MOOCs in the country. The aim of this work is to present the MOOC-CEDIA Observatory, a web platform that offers interactive visualizations on the adoption of MOOCs in Ecuador. The main results of the study show that: (1) until 2020 there have been 99 MOOCs in Ecuador, (2) the domains of MOOCs are mostly related to applied sciences, social sciences and natural sciences, with the humanities being the least covered, (3) Open edX and Moodle are the most widely used platforms to deploy such courses. It is expected that the conclusions drawn from this analysis, will allow the design of recommendations aimed to promote the creation and use of quality MOOCs in Ecuador and help institutions to chart the route for their adoption, both for internal use by their community but also by society in general.}, language = {en} } @article{PawassarTiberius2021, author = {Pawassar, Christian Matthias and Tiberius, Victor}, title = {Virtual reality in health care}, series = {JMIR Serious Games}, volume = {9}, journal = {JMIR Serious Games}, edition = {4}, publisher = {JMIR Publications}, address = {Toronto, Kanada}, issn = {2291-9279}, doi = {10.2196/32721}, pages = {1 -- 19}, year = {2021}, abstract = {Background: Research into the application of virtual reality technology in the health care sector has rapidly increased, resulting in a large body of research that is difficult to keep up with. Objective: We will provide an overview of the annual publication numbers in this field and the most productive and influential countries, journals, and authors, as well as the most used, most co-occurring, and most recent keywords. Methods: Based on a data set of 356 publications and 20,363 citations derived from Web of Science, we conducted a bibliometric analysis using BibExcel, HistCite, and VOSviewer. Results: The strongest growth in publications occurred in 2020, accounting for 29.49\% of all publications so far. The most productive countries are the United States, the United Kingdom, and Spain; the most influential countries are the United States, Canada, and the United Kingdom. The most productive journals are the Journal of Medical Internet Research (JMIR), JMIR Serious Games, and the Games for Health Journal; the most influential journals are Patient Education and Counselling, Medical Education, and Quality of Life Research. The most productive authors are Riva, del Piccolo, and Schwebel; the most influential authors are Finset, del Piccolo, and Eide. The most frequently occurring keywords other than "virtual" and "reality" are "training," "trial," and "patients." The most relevant research themes are communication, education, and novel treatments; the most recent research trends are fitness and exergames. Conclusions: The analysis shows that the field has left its infant state and its specialization is advancing, with a clear focus on patient usability.}, language = {en} } @article{HuangRichterKleickmannetal.2021, author = {Huang, Yizhen and Richter, Eric and Kleickmann, Thilo and Wiepke, Axel and Richter, Dirk}, title = {Classroom complexity affects student teachers' behavior in a VR classroom}, series = {Computers \& education : an international journal}, volume = {163}, journal = {Computers \& education : an international journal}, publisher = {Elsevier}, address = {Oxford}, issn = {0360-1315}, doi = {10.1016/j.compedu.2020.104100}, pages = {15}, year = {2021}, abstract = {Student teachers often struggle to keep track of everything that is happening in the classroom, and particularly to notice and respond when students cause disruptions. The complexity of the classroom environment is a potential contributing factor that has not been empirically tested. In this experimental study, we utilized a virtual reality (VR) classroom to examine whether classroom complexity affects the likelihood of student teachers noticing disruptions and how they react after noticing. Classroom complexity was operationalized as the number of disruptions and the existence of overlapping disruptions (multidimensionality) as well as the existence of parallel teaching tasks (simultaneity). Results showed that student teachers (n = 50) were less likely to notice the scripted disruptions, and also less likely to respond to the disruptions in a comprehensive and effortful manner when facing greater complexity. These results may have implications for both teacher training and the design of VR for training or research purpose. This study contributes to the field from two aspects: 1) it revealed how features of the classroom environment can affect student teachers' noticing of and reaction to disruptions; and 2) it extends the functionality of the VR environment-from a teacher training tool to a testbed of fundamental classroom processes that are difficult to manipulate in real-life.}, language = {en} } @article{ShekharReimannMayeretal.2021, author = {Shekhar, Sumit and Reimann, Max and Mayer, Maximilian and Semmo, Amir and Pasewaldt, Sebastian and D{\"o}llner, J{\"u}rgen and Trapp, Matthias}, title = {Interactive photo editing on smartphones via intrinsic decomposition}, series = {Computer graphics forum : journal of the European Association for Computer Graphics}, volume = {40}, journal = {Computer graphics forum : journal of the European Association for Computer Graphics}, publisher = {Blackwell}, address = {Oxford}, issn = {0167-7055}, doi = {10.1111/cgf.142650}, pages = {497 -- 510}, year = {2021}, abstract = {Intrinsic decomposition refers to the problem of estimating scene characteristics, such as albedo and shading, when one view or multiple views of a scene are provided. The inverse problem setting, where multiple unknowns are solved given a single known pixel-value, is highly under-constrained. When provided with correlating image and depth data, intrinsic scene decomposition can be facilitated using depth-based priors, which nowadays is easy to acquire with high-end smartphones by utilizing their depth sensors. In this work, we present a system for intrinsic decomposition of RGB-D images on smartphones and the algorithmic as well as design choices therein. Unlike state-of-the-art methods that assume only diffuse reflectance, we consider both diffuse and specular pixels. For this purpose, we present a novel specularity extraction algorithm based on a multi-scale intensity decomposition and chroma inpainting. At this, the diffuse component is further decomposed into albedo and shading components. We use an inertial proximal algorithm for non-convex optimization (iPiano) to ensure albedo sparsity. Our GPU-based visual processing is implemented on iOS via the Metal API and enables interactive performance on an iPhone 11 Pro. Further, a qualitative evaluation shows that we are able to obtain high-quality outputs. Furthermore, our proposed approach for specularity removal outperforms state-of-the-art approaches for real-world images, while our albedo and shading layer decomposition is faster than the prior work at a comparable output quality. Manifold applications such as recoloring, retexturing, relighting, appearance editing, and stylization are shown, each using the intrinsic layers obtained with our method and/or the corresponding depth data.}, language = {en} } @article{ŞahinEgloffsteinBotheetal.2021, author = {Şahin, Muhittin and Egloffstein, Marc and Bothe, Max and Rohloff, Tobias and Schenk, Nathanael and Schwerer, Florian and Ifenthaler, Dirk}, title = {Behavioral Patterns in Enterprise MOOCs at openSAP}, series = {EMOOCs 2021}, volume = {2021}, journal = {EMOOCs 2021}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-512-5}, doi = {10.25932/publishup-51735}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-517350}, pages = {281 -- 288}, year = {2021}, language = {en} } @article{Boissier2021, author = {Boissier, Martin}, title = {Robust and budget-constrained encoding configurations for in-memory database systems}, series = {Proceedings of the VLDB Endowment}, volume = {15}, journal = {Proceedings of the VLDB Endowment}, number = {4}, publisher = {Association for Computing Machinery (ACM)}, address = {[New York]}, issn = {2150-8097}, doi = {10.14778/3503585.3503588}, pages = {780 -- 793}, year = {2021}, abstract = {Data encoding has been applied to database systems for decades as it mitigates bandwidth bottlenecks and reduces storage requirements. But even in the presence of these advantages, most in-memory database systems use data encoding only conservatively as the negative impact on runtime performance can be severe. Real-world systems with large parts being infrequently accessed and cost efficiency constraints in cloud environments require solutions that automatically and efficiently select encoding techniques, including heavy-weight compression. In this paper, we introduce workload-driven approaches to automaticaly determine memory budget-constrained encoding configurations using greedy heuristics and linear programming. We show for TPC-H, TPC-DS, and the Join Order Benchmark that optimized encoding configurations can reduce the main memory footprint significantly without a loss in runtime performance over state-of-the-art dictionary encoding. To yield robust selections, we extend the linear programming-based approach to incorporate query runtime constraints and mitigate unexpected performance regressions.}, language = {en} } @article{VitaglianoJiangNaumann2021, author = {Vitagliano, Gerardo and Jiang, Lan and Naumann, Felix}, title = {Detecting layout templates in complex multiregion files}, series = {Proceedings of the VLDB Endowment}, volume = {15}, journal = {Proceedings of the VLDB Endowment}, number = {3}, publisher = {Association for Computing Machinery}, address = {New York}, issn = {2150-8097}, doi = {10.14778/3494124.3494145}, pages = {646 -- 658}, year = {2021}, abstract = {Spreadsheets are among the most commonly used file formats for data management, distribution, and analysis. Their widespread employment makes it easy to gather large collections of data, but their flexible canvas-based structure makes automated analysis difficult without heavy preparation. One of the common problems that practitioners face is the presence of multiple, independent regions in a single spreadsheet, possibly separated by repeated empty cells. We define such files as "multiregion" files. In collections of various spreadsheets, we can observe that some share the same layout. We present the Mondrian approach to automatically identify layout templates across multiple files and systematically extract the corresponding regions. Our approach is composed of three phases: first, each file is rendered as an image and inspected for elements that could form regions; then, using a clustering algorithm, the identified elements are grouped to form regions; finally, every file layout is represented as a graph and compared with others to find layout templates. We compare our method to state-of-the-art table recognition algorithms on two corpora of real-world enterprise spreadsheets. Our approach shows the best performances in detecting reliable region boundaries within each file and can correctly identify recurring layouts across files.}, language = {en} } @article{RuedianVladova2021, author = {R{\"u}dian, Sylvio Leo and Vladova, Gergana}, title = {Kostenfreie Onlinekurse nachhaltig mit personalisiertem Marketing finanzieren}, series = {HMD Praxis der Wirtschaftsinformatik}, volume = {58}, journal = {HMD Praxis der Wirtschaftsinformatik}, number = {3}, publisher = {Springer Vieweg}, address = {Wiesbaden}, issn = {1436-3011}, doi = {10.1365/s40702-021-00720-4}, pages = {507 -- 520}, year = {2021}, abstract = {Selbstbestimmtes Lernen mit Onlinekursen findet zunehmend mehr Akzeptanz in unserer Gesellschaft. Lernende k{\"o}nnen mithilfe von Onlinekursen selbst festlegen, was sie wann lernen und Kurse k{\"o}nnen durch vielf{\"a}ltige Adaptionen an den Lernfortschritt der Nutzer angepasst und individualisiert werden. Auf der einen Seite ist eine große Zielgruppe f{\"u}r diese Lernangebote vorhanden. Auf der anderen Seite sind die Erstellung von Onlinekursen, ihre Bereitstellung, Wartung und Betreuung kostenintensiv, wodurch hochwertige Angebote h{\"a}ufig kostenpflichtig angeboten werden m{\"u}ssen, um als Anbieter zumindest kostenneutral agieren zu k{\"o}nnen. In diesem Beitrag er{\"o}rtern und diskutieren wir ein offenes, nachhaltiges datengetriebenes zweiseitiges Gesch{\"a}ftsmodell zur Verwertung gepr{\"u}fter Onlinekurse und deren kostenfreie Bereitstellung f{\"u}r jeden Lernenden. Kern des Gesch{\"a}ftsmodells ist die Nutzung der dabei entstehenden Verhaltensdaten, die daraus m{\"o}gliche Ableitung von Pers{\"o}nlichkeitsmerkmalen und Interessen und deren Nutzung im kommerziellen Kontext. Dies ist eine bei der Websuche bereits weitl{\"a}ufig akzeptierte Methode, welche nun auf den Lernkontext {\"u}bertragen wird. Welche M{\"o}glichkeiten, Herausforderungen, aber auch Barrieren {\"u}berwunden werden m{\"u}ssen, damit das Gesch{\"a}ftsmodell nachhaltig und ethisch vertretbar funktioniert, werden zwei unabh{\"a}ngige, jedoch synergetisch verbundene Gesch{\"a}ftsmodelle vorgestellt und diskutiert. Zus{\"a}tzlich wurde die Akzeptanz und Erwartung der Zielgruppe f{\"u}r das vorgestellte Gesch{\"a}ftsmodell untersucht, um notwendige Kernressourcen f{\"u}r die Praxis abzuleiten. Die Ergebnisse der Untersuchung zeigen, dass das Gesch{\"a}ftsmodell von den Nutzer*innen grundlegend akzeptiert wird. 10 \% der Befragten w{\"u}rden es bevorzugen, mit virtuellen Assistenten - anstelle mit Tutor*innen zu lernen. Zudem ist der Großteil der Nutzer*innen sich nicht dar{\"u}ber bewusst, dass Pers{\"o}nlichkeitsmerkmale anhand des Nutzerverhaltens abgeleitet werden k{\"o}nnen.}, language = {de} } @article{vonSteinauSteinrueckBruhn2021, author = {von Steinau-Steinr{\"u}ck, Robert and Bruhn, Emma}, title = {Der Impfmuffel im Arbeitsrecht}, series = {NJW spezial}, volume = {18}, journal = {NJW spezial}, number = {16}, publisher = {C.H. Beck}, address = {M{\"u}nchen}, issn = {1613-4621}, pages = {498 -- 499}, year = {2021}, abstract = {Trotz erfolgreicher Impfkampagne droht nach dem Sommer eine vierte Infektionswelle der Corona-Pandemie. Ob es dazu kommen wird, h{\"a}ngt maßgeblich davon ab, wie viele Menschen sich f{\"u}r eine Corona-Schutzimpfung entscheiden. Am Impfstoff mangelt es nicht mehr, daf{\"u}r an der Impfbereitschaft. Viele Arbeitgeber fragen sich daher, was sie unternehmen k{\"o}nnen, um die Impfquote in ihren Betrieben zu erh{\"o}hen.}, language = {de} } @article{vonSteinauSteinrueckJoeris2021, author = {von Steinau-Steinr{\"u}ck, Robert and J{\"o}ris, Nils}, title = {Brexit-Arbeitsrecht und die Folgen}, series = {NJW spezial}, volume = {18}, journal = {NJW spezial}, number = {8}, publisher = {C.H. Beck}, address = {M{\"u}nchen}, issn = {1613-4621}, pages = {242 -- 243}, year = {2021}, abstract = {Die Corona-Pandemie hat den Brexit ein wenig in den Hintergrund gedr{\"a}ngt. Dabei hat er gerade im Arbeitsrecht ganz erhebliche Auswirkungen. {\"U}ber sie geben wir einen {\"U}berblick.}, language = {de} } @article{vonSteinauSteinrueck2021, author = {von Steinau-Steinr{\"u}ck, Robert}, title = {Was ist bei "Workation" und "Bleisure" rechtlich zu beachten?}, series = {NJW spezial}, volume = {18}, journal = {NJW spezial}, number = {20}, publisher = {C.H. Beck}, address = {M{\"u}nchen}, issn = {1613-4621}, pages = {626 -- 627}, year = {2021}, abstract = {Die Digitalisierung unseres Lebens l{\"o}st die Grenzen zwischen Privat- und Berufsleben immer weiter auf. Bekanntes Beispiel ist das Homeoffice. Arbeitgeber begegnen aber auch zahlreichen weiteren Trends in diesem Zusammenhang. Dazu geh{\"o}ren „workation", also die Verbindung zwischen Arbeit („work") und Urlaub („vacation") ebenso wie „bleisure", dh die Verbindung von Dienstreisen („business") und Urlaub („leisure"). Der Beitrag geht den rechtlichen Rahmenbedingungen hierf{\"u}r nach.}, language = {de} } @article{BethgeSerthStaubitzetal.2021, author = {Bethge, Joseph and Serth, Sebastian and Staubitz, Thomas and Wuttke, Tobias and Nordemann, Oliver and Das, Partha-Pratim and Meinel, Christoph}, title = {TransPipe}, series = {EMOOCs 2021}, volume = {2021}, journal = {EMOOCs 2021}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, doi = {10.25932/publishup-51694}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-516943}, pages = {79 -- 94}, year = {2021}, abstract = {Online learning environments, such as Massive Open Online Courses (MOOCs), often rely on videos as a major component to convey knowledge. However, these videos exclude potential participants who do not understand the lecturer's language, regardless of whether that is due to language unfamiliarity or aural handicaps. Subtitles and/or interactive transcripts solve this issue, ease navigation based on the content, and enable indexing and retrieval by search engines. Although there are several automated speech-to-text converters and translation tools, their quality varies and the process of integrating them can be quite tedious. Thus, in practice, many videos on MOOC platforms only receive subtitles after the course is already finished (if at all) due to a lack of resources. This work describes an approach to tackle this issue by providing a dedicated tool, which is closing this gap between MOOC platforms and transcription and translation tools and offering a simple workflow that can easily be handled by users with a less technical background. The proposed method is designed and evaluated by qualitative interviews with three major MOOC providers.}, language = {en} } @article{GruenerMuehleMeinel2021, author = {Gr{\"u}ner, Andreas and M{\"u}hle, Alexander and Meinel, Christoph}, title = {ATIB}, series = {IEEE access : practical research, open solutions / Institute of Electrical and Electronics Engineers}, volume = {9}, journal = {IEEE access : practical research, open solutions / Institute of Electrical and Electronics Engineers}, publisher = {Institute of Electrical and Electronics Engineers}, address = {New York, NY}, issn = {2169-3536}, doi = {10.1109/ACCESS.2021.3116095}, pages = {138553 -- 138570}, year = {2021}, abstract = {Identity management is a principle component of securing online services. In the advancement of traditional identity management patterns, the identity provider remained a Trusted Third Party (TTP). The service provider and the user need to trust a particular identity provider for correct attributes amongst other demands. This paradigm changed with the invention of blockchain-based Self-Sovereign Identity (SSI) solutions that primarily focus on the users. SSI reduces the functional scope of the identity provider to an attribute provider while enabling attribute aggregation. Besides that, the development of new protocols, disregarding established protocols and a significantly fragmented landscape of SSI solutions pose considerable challenges for an adoption by service providers. We propose an Attribute Trust-enhancing Identity Broker (ATIB) to leverage the potential of SSI for trust-enhancing attribute aggregation. Furthermore, ATIB abstracts from a dedicated SSI solution and offers standard protocols. Therefore, it facilitates the adoption by service providers. Despite the brokered integration approach, we show that ATIB provides a high security posture. Additionally, ATIB does not compromise the ten foundational SSI principles for the users.}, language = {en} } @article{Perscheid2021, author = {Perscheid, Cindy}, title = {Integrative biomarker detection on high-dimensional gene expression data sets}, series = {Briefings in bioinformatics}, volume = {22}, journal = {Briefings in bioinformatics}, number = {3}, publisher = {Oxford Univ. Press}, address = {Oxford}, issn = {1467-5463}, doi = {10.1093/bib/bbaa151}, pages = {18}, year = {2021}, abstract = {Gene expression data provide the expression levels of tens of thousands of genes from several hundred samples. These data are analyzed to detect biomarkers that can be of prognostic or diagnostic use. Traditionally, biomarker detection for gene expression data is the task of gene selection. The vast number of genes is reduced to a few relevant ones that achieve the best performance for the respective use case. Traditional approaches select genes based on their statistical significance in the data set. This results in issues of robustness, redundancy and true biological relevance of the selected genes. Integrative analyses typically address these shortcomings by integrating multiple data artifacts from the same objects, e.g. gene expression and methylation data. When only gene expression data are available, integrative analyses instead use curated information on biological processes from public knowledge bases. With knowledge bases providing an ever-increasing amount of curated biological knowledge, such prior knowledge approaches become more powerful. This paper provides a thorough overview on the status quo of biomarker detection on gene expression data with prior biological knowledge. We discuss current shortcomings of traditional approaches, review recent external knowledge bases, provide a classification and qualitative comparison of existing prior knowledge approaches and discuss open challenges for this kind of gene selection.}, language = {en} } @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{LosterKoumarelasNaumann2021, author = {Loster, Michael and Koumarelas, Ioannis and Naumann, Felix}, title = {Knowledge transfer for entity resolution with siamese neural networks}, series = {ACM journal of data and information quality}, volume = {13}, journal = {ACM journal of data and information quality}, number = {1}, publisher = {Association for Computing Machinery}, address = {New York}, issn = {1936-1955}, doi = {10.1145/3410157}, pages = {25}, year = {2021}, abstract = {The integration of multiple data sources is a common problem in a large variety of applications. Traditionally, handcrafted similarity measures are used to discover, merge, and integrate multiple representations of the same entity-duplicates-into a large homogeneous collection of data. Often, these similarity measures do not cope well with the heterogeneity of the underlying dataset. In addition, domain experts are needed to manually design and configure such measures, which is both time-consuming and requires extensive domain expertise.
We propose a deep Siamese neural network, capable of learning a similarity measure that is tailored to the characteristics of a particular dataset. With the properties of deep learning methods, we are able to eliminate the manual feature engineering process and thus considerably reduce the effort required for model construction. In addition, we show that it is possible to transfer knowledge acquired during the deduplication of one dataset to another, and thus significantly reduce the amount of data required to train a similarity measure. We evaluated our method on multiple datasets and compare our approach to state-of-the-art deduplication methods. Our approach outperforms competitors by up to +26 percent F-measure, depending on task and dataset. In addition, we show that knowledge transfer is not only feasible, but in our experiments led to an improvement in F-measure of up to +4.7 percent.}, language = {en} } @article{NavarroOrejasPinoetal.2021, author = {Navarro, Marisa and Orejas, Fernando and Pino, Elvira and Lambers, Leen}, title = {A navigational logic for reasoning about graph properties}, series = {Journal of logical and algebraic methods in programming}, volume = {118}, journal = {Journal of logical and algebraic methods in programming}, publisher = {Elsevier Science}, address = {Amsterdam [u.a.]}, issn = {2352-2208}, doi = {10.1016/j.jlamp.2020.100616}, pages = {33}, year = {2021}, abstract = {Graphs play an important role in many areas of Computer Science. In particular, our work is motivated by model-driven software development and by graph databases. For this reason, it is very important to have the means to express and to reason about the properties that a given graph may satisfy. With this aim, in this paper we present a visual logic that allows us to describe graph properties, including navigational properties, i.e., properties about the paths in a graph. The logic is equipped with a deductive tableau method that we have proved to be sound and complete.}, language = {en} } @article{GautamZhangLandwehretal.2021, author = {Gautam, Khem Raj and Zhang, Guoqiang and Landwehr, Niels and Adolphs, Julian}, title = {Machine learning for improvement of thermal conditions inside a hybrid ventilated animal building}, series = {Computers and electronics in agriculture : COMPAG online ; an international journal}, volume = {187}, journal = {Computers and electronics in agriculture : COMPAG online ; an international journal}, publisher = {Elsevier Science}, address = {Amsterdam [u.a.]}, issn = {0168-1699}, doi = {10.1016/j.compag.2021.106259}, pages = {10}, year = {2021}, abstract = {In buildings with hybrid ventilation, natural ventilation opening positions (windows), mechanical ventilation rates, heating, and cooling are manipulated to maintain desired thermal conditions. The indoor temperature is regulated solely by ventilation (natural and mechanical) when the external conditions are favorable to save external heating and cooling energy. The ventilation parameters are determined by a rule-based control scheme, which is not optimal. This study proposes a methodology to enable real-time optimum control of ventilation parameters. We developed offline prediction models to estimate future thermal conditions from the data collected from building in operation. The developed offline model is then used to find the optimal controllable ventilation parameters in real-time to minimize the setpoint deviation in the building. With the proposed methodology, the experimental building's setpoint deviation improved for 87\% of time, on average, by 0.53 degrees C compared to the current deviations.}, language = {en} } @article{BorchertMockTomczaketal.2021, author = {Borchert, Florian and Mock, Andreas and Tomczak, Aurelie and H{\"u}gel, Jonas and Alkarkoukly, Samer and Knurr, Alexander and Volckmar, Anna-Lena and Stenzinger, Albrecht and Schirmacher, Peter and Debus, J{\"u}rgen and J{\"a}ger, Dirk and Longerich, Thomas and Fr{\"o}hling, Stefan and Eils, Roland and Bougatf, Nina and Sax, Ulrich and Schapranow, Matthieu-Patrick}, title = {Correction to: Knowledge bases and software support for variant interpretation in precision oncology}, series = {Briefings in bioinformatics}, volume = {22}, journal = {Briefings in bioinformatics}, number = {6}, publisher = {Oxford Univ. Press}, address = {Oxford}, issn = {1467-5463}, doi = {10.1093/bib/bbab246}, pages = {1}, year = {2021}, language = {en} } @article{CombiOliboniWeskeetal.2021, author = {Combi, Carlo and Oliboni, Barbara and Weske, Mathias and Zerbato, Francesca}, title = {Seamless conceptual modeling of processes with transactional and analytical data}, series = {Data \& knowledge engineering}, volume = {134}, journal = {Data \& knowledge engineering}, publisher = {Elsevier}, address = {Amsterdam}, issn = {0169-023X}, doi = {10.1016/j.datak.2021.101895}, pages = {14}, year = {2021}, abstract = {In the field of Business Process Management (BPM), modeling business processes and related data is a critical issue since process activities need to manage data stored in databases. The connection between processes and data is usually handled at the implementation level, even if modeling both processes and data at the conceptual level should help designers in improving business process models and identifying requirements for implementation. Especially in data -and decision-intensive contexts, business process activities need to access data stored both in databases and data warehouses. In this paper, we complete our approach for defining a novel conceptual view that bridges process activities and data. The proposed approach allows the designer to model the connection between business processes and database models and define the operations to perform, providing interesting insights on the overall connected perspective and hints for identifying activities that are crucial for decision support.}, language = {en} } @article{KoerppenUllrichBertheau2021, author = {K{\"o}rppen, Tim and Ullrich, Andr{\´e} and Bertheau, Clementine}, title = {Durchblick statt Bauchgef{\"u}hl - Transformation zur Data-Driven Organization}, series = {Wirtschaftsinformatik \& Management}, volume = {13}, journal = {Wirtschaftsinformatik \& Management}, number = {6}, publisher = {Springer Gabler}, address = {Wiesbaden}, issn = {1867-5905}, doi = {10.1365/s35764-021-00370-7}, pages = {452 -- 459}, year = {2021}, abstract = {Um in der digitalisierten Wirtschaft mitzuspielen, m{\"u}ssen Unternehmen, Markt und insbesondere Kunden detailliert verstanden werden. Neben den „Big Playern" aus dem Silicon Valley sieht der deutsche Mittelstand, der zu großen Teilen noch auf gewachsenen IT-Infrastrukturen und Prozessen agiert, oft alt aus. Um in den n{\"a}chsten Jahren nicht g{\"a}nzlich abgeh{\"a}ngt zu werden, ist ein Umbruch notwendig. Sowohl Leistungserstellungsprozesse als auch Leistungsangebot m{\"u}ssen transparent und datenbasiert ausgerichtet werden. Nur so k{\"o}nnen Gesch{\"a}ftsvorf{\"a}lle, das Marktgeschehen sowie Handeln der Akteure integrativ bewertet und fundierte Entscheidungen getroffen werden. In diesem Beitrag wird das Konzept der Data-Driven Organization vorgestellt und aufgezeigt, wie Unternehmen den eigenen Analyticsreifegrad ermitteln und in einem iterativen Transformationsprozess steigern k{\"o}nnen.}, language = {de} } @article{UllrichTeichmannGronau2021, author = {Ullrich, Andr{\´e} and Teichmann, Malte and Gronau, Norbert}, title = {Fast trainable capabilities in software engineering-skill development in learning factories}, series = {Ji suan ji jiao yu = Computer Education / Qing hua da xue}, journal = {Ji suan ji jiao yu = Computer Education / Qing hua da xue}, number = {12}, publisher = {[Verlag nicht ermittelbar]}, address = {Bei jing shi}, issn = {1672-5913}, doi = {10.16512/j.cnki.jsjjy.2020.12.002}, pages = {2 -- 10}, year = {2021}, abstract = {The increasing demand for software engineers cannot completely be fulfilled by university education and conventional training approaches due to limited capacities. Accordingly, an alternative approach is necessary where potential software engineers are being educated in software engineering skills using new methods. We suggest micro tasks combined with theoretical lessons to overcome existing skill deficits and acquire fast trainable capabilities. This paper addresses the gap between demand and supply of software engineers by introducing an actionoriented and scenario-based didactical approach, which enables non-computer scientists to code. Therein, the learning content is provided in small tasks and embedded in learning factory scenarios. Therefore, different requirements for software engineers from the market side and from an academic viewpoint are analyzed and synthesized into an integrated, yet condensed skills catalogue. This enables the development of training and education units that focus on the most important skills demanded on the market. To achieve this objective, individual learning scenarios are developed. Of course, proper basic skills in coding cannot be learned over night but software programming is also no sorcery.}, language = {en} } @article{MarxFreundlichKlotzetal.2021, author = {Marx, Susanne and Freundlich, Heidi and Klotz, Michael and Kyl{\"a}nen, Mika and Niedoszytko, Grazyna and Swacha, Jakub and Vollerthum, Anne}, title = {Towards an Online Learning Community on Digitalization in Tourism}, series = {EMOOCs 2021}, journal = {EMOOCs 2021}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-512-5}, doi = {10.25932/publishup-51598}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-515986}, pages = {9}, year = {2021}, abstract = {Information technology and digital solutions as enablers in the tourism sector require continuous development of skills, as digital transformation is characterized by fast change, complexity and uncertainty. This research investigates how a cMOOC concept could support the tourism industry. A consortium of three universities, a tourism association, and a tourist attraction investigates online learning needs and habits of tourism industry stakeholders in the field of digitalization in a cross-border study in the Baltic Sea region. The multi-national survey (n = 244) reveals a high interest in participating in an online learning community, with two-thirds of respondents seeing opportunities to contributing to such community apart from consuming knowledge. The paper demonstrates preferred ways of learning, motivational and hampering aspects as well as types of possible contributions.}, language = {en} } @article{CsehJuhos2021, author = {Cseh, {\´A}gnes and Juhos, Attila}, title = {Pairwise preferences in the stable marriage problem}, series = {ACM Transactions on Economics and Computation / Association for Computing Machinery}, volume = {9}, journal = {ACM Transactions on Economics and Computation / Association for Computing Machinery}, number = {1}, publisher = {Association for Computing Machinery}, address = {New York}, issn = {2167-8375}, doi = {10.1145/3434427}, pages = {28}, year = {2021}, abstract = {We study the classical, two-sided stable marriage problem under pairwise preferences. In the most general setting, agents are allowed to express their preferences as comparisons of any two of their edges, and they also have the right to declare a draw or even withdraw from such a comparison. This freedom is then gradually restricted as we specify six stages of orderedness in the preferences, ending with the classical case of strictly ordered lists. We study all cases occurring when combining the three known notions of stability-weak, strong, and super-stability-under the assumption that each side of the bipartite market obtains one of the six degrees of orderedness. By designing three polynomial algorithms and two NP-completeness proofs, we determine the complexity of all cases not yet known and thus give an exact boundary in terms of preference structure between tractable and intractable cases.}, language = {en} } @article{CsehKavitha2021, author = {Cseh, {\´A}gnes and Kavitha, Telikepalli}, title = {Popular matchings in complete graphs}, series = {Algorithmica : an international journal in computer science}, volume = {83}, journal = {Algorithmica : an international journal in computer science}, number = {5}, publisher = {Springer}, address = {New York}, issn = {0178-4617}, doi = {10.1007/s00453-020-00791-7}, pages = {1493 -- 1523}, year = {2021}, abstract = {Our input is a complete graph G on n vertices where each vertex has a strict ranking of all other vertices in G. The goal is to construct a matching in G that is popular. A matching M is popular if M does not lose a head-to-head election against any matching M ': here each vertex casts a vote for the matching in {M,M '} in which it gets a better assignment. Popular matchings need not exist in the given instance G and the popular matching problem is to decide whether one exists or not. The popular matching problem in G is easy to solve for odd n. Surprisingly, the problem becomes NP-complete for even n, as we show here. This is one of the few graph theoretic problems efficiently solvable when n has one parity and NP-complete when n has the other parity.}, language = {en} } @article{BredeBotta2021, author = {Brede, Nuria and Botta, Nicola}, title = {On the correctness of monadic backward induction}, series = {Journal of functional programming}, volume = {31}, journal = {Journal of functional programming}, publisher = {Cambridge University Press}, address = {Cambridge}, issn = {1469-7653}, doi = {10.1017/S0956796821000228}, pages = {39}, year = {2021}, abstract = {In control theory, to solve a finite-horizon sequential decision problem (SDP) commonly means to find a list of decision rules that result in an optimal expected total reward (or cost) when taking a given number of decision steps. SDPs are routinely solved using Bellman's backward induction. Textbook authors (e.g. Bertsekas or Puterman) typically give more or less formal proofs to show that the backward induction algorithm is correct as solution method for deterministic and stochastic SDPs. Botta, Jansson and Ionescu propose a generic framework for finite horizon, monadic SDPs together with a monadic version of backward induction for solving such SDPs. In monadic SDPs, the monad captures a generic notion of uncertainty, while a generic measure function aggregates rewards. In the present paper, we define a notion of correctness for monadic SDPs and identify three conditions that allow us to prove a correctness result for monadic backward induction that is comparable to textbook correctness proofs for ordinary backward induction. The conditions that we impose are fairly general and can be cast in category-theoretical terms using the notion of Eilenberg-Moore algebra. They hold in familiar settings like those of deterministic or stochastic SDPs, but we also give examples in which they fail. Our results show that backward induction can safely be employed for a broader class of SDPs than usually treated in textbooks. However, they also rule out certain instances that were considered admissible in the context of Botta et al. 's generic framework. Our development is formalised in Idris as an extension of the Botta et al. framework and the sources are available as supplementary material.}, language = {en} } @article{BensonMakaitRabl2021, author = {Benson, Lawrence and Makait, Hendrik and Rabl, Tilmann}, title = {Viper}, series = {Proceedings of the VLDB Endowment}, volume = {14}, journal = {Proceedings of the VLDB Endowment}, number = {9}, publisher = {Association for Computing Machinery}, address = {New York}, issn = {2150-8097}, doi = {10.14778/3461535.3461543}, pages = {1544 -- 1556}, year = {2021}, abstract = {Key-value stores (KVSs) have found wide application in modern software systems. For persistence, their data resides in slow secondary storage, which requires KVSs to employ various techniques to increase their read and write performance from and to the underlying medium. Emerging persistent memory (PMem) technologies offer data persistence at close-to-DRAM speed, making them a promising alternative to classical disk-based storage. However, simply drop-in replacing existing storage with PMem does not yield good results, as block-based access behaves differently in PMem than on disk and ignores PMem's byte addressability, layout, and unique performance characteristics. In this paper, we propose three PMem-specific access patterns and implement them in a hybrid PMem-DRAM KVS called Viper. We employ a DRAM-based hash index and a PMem-aware storage layout to utilize the random-write speed of DRAM and efficient sequential-write performance PMem. Our evaluation shows that Viper significantly outperforms existing KVSs for core KVS operations while providing full data persistence. Moreover, Viper outperforms existing PMem-only, hybrid, and disk-based KVSs by 4-18x for write workloads, while matching or surpassing their get performance.}, language = {en} } @article{XuRazaghiMoghadamNikoloski2021, author = {Xu, Rudan and Razaghi-Moghadam, Zahra and Nikoloski, Zoran}, title = {Maximization of non-idle enzymes improves the coverage of the estimated maximal in vivo enzyme catalytic rates in Escherichia coli}, series = {Bioinformatics}, volume = {37}, journal = {Bioinformatics}, number = {21}, publisher = {Oxford Univ. Press}, address = {Oxford}, issn = {1367-4803}, doi = {10.1093/bioinformatics/btab575}, pages = {3848 -- 3855}, year = {2021}, abstract = {Motivation: Constraint-based modeling approaches allow the estimation of maximal in vivo enzyme catalytic rates that can serve as proxies for enzyme turnover numbers. Yet, genome-scale flux profiling remains a challenge in deploying these approaches to catalogue proxies for enzyme catalytic rates across organisms. Results: Here, we formulate a constraint-based approach, termed NIDLE-flux, to estimate fluxes at a genome-scale level by using the principle of efficient usage of expressed enzymes. Using proteomics data from Escherichia coli, we show that the fluxes estimated by NIDLE-flux and the existing approaches are in excellent qualitative agreement (Pearson correlation > 0.9). We also find that the maximal in vivo catalytic rates estimated by NIDLE-flux exhibits a Pearson correlation of 0.74 with in vitro enzyme turnover numbers. However, NIDLE-flux results in a 1.4-fold increase in the size of the estimated maximal in vivo catalytic rates in comparison to the contenders. Integration of the maximum in vivo catalytic rates with publically available proteomics and metabolomics data provide a better match to fluxes estimated by NIDLE-flux. Therefore, NIDLE-flux facilitates more effective usage of proteomics data to estimate proxies for kcatomes.}, language = {en} } @article{AngeleskaOmranianNikoloski2021, author = {Angeleska, Angela and Omranian, Sara and Nikoloski, Zoran}, title = {Coherent network partitions}, series = {Theoretical computer science : the journal of the EATCS}, volume = {894}, journal = {Theoretical computer science : the journal of the EATCS}, publisher = {Elsevier}, address = {Amsterdam [u.a.]}, issn = {0304-3975}, doi = {10.1016/j.tcs.2021.10.002}, pages = {3 -- 11}, year = {2021}, abstract = {We continue to study coherent partitions of graphs whereby the vertex set is partitioned into subsets that induce biclique spanned subgraphs. The problem of identifying the minimum number of edges to obtain biclique spanned connected components (CNP), called the coherence number, is NP-hard even on bipartite graphs. Here, we propose a graph transformation geared towards obtaining an O (log n)-approximation algorithm for the CNP on a bipartite graph with n vertices. The transformation is inspired by a new characterization of biclique spanned subgraphs. In addition, we study coherent partitions on prime graphs, and show that finding coherent partitions reduces to the problem of finding coherent partitions in a prime graph. Therefore, these results provide future directions for approximation algorithms for the coherence number of a given graph.}, language = {en} } @article{Steinroetter2021, author = {Steinr{\"o}tter, Bj{\"o}rn}, title = {Das Konzept einer datenaltruistischen Organisation}, series = {Datenschutz und Datensicherheit}, volume = {45}, journal = {Datenschutz und Datensicherheit}, number = {12}, publisher = {Springer}, address = {Berlin}, issn = {1862-2607}, doi = {10.1007/s11623-021-1539-6}, pages = {794 -- 798}, year = {2021}, abstract = {Dass Technologien wie Machine Learning-Anwendungen oder Big bzw. Smart Data- Verfahren unbedingt Daten in ausreichender Menge und G{\"u}te ben{\"o}tigen, erscheint inzwischen als Binsenweisheit. Vor diesem Hintergrund hat insbesondere der EU-Gesetzgeber f{\"u}r sich zuletzt ein neues Bet{\"a}tigungsfeld entdeckt, indem er versucht, auf unterschiedlichen Wegen Anreize zum Datenteilen zu schaffen, um Innovation zu kreieren. Hierzu z{\"a}hlt auch eine geradezu wohlt{\"o}nend mit ,,Datenaltruismus'' verschlagwortete Konstellation. Der Beitrag stellt die diesbez{\"u}glichen Regulierungserw{\"a}gungen auf supranationaler Ebene dar und nimmt eine erste Analyse vor.}, language = {de} } @article{SchindlerMoldenhawerStangeetal.2021, author = {Schindler, Daniel and Moldenhawer, Ted and Stange, Maike and Lepro, Valentino and Beta, Carsten and Holschneider, Matthias and Huisinga, Wilhelm}, title = {Analysis of protrusion dynamics in amoeboid cell motility by means of regularized contour flows}, series = {PLoS Computational Biology : a new community journal}, volume = {17}, journal = {PLoS Computational Biology : a new community journal}, number = {8}, publisher = {PLoS}, address = {San Fransisco}, issn = {1553-734X}, doi = {10.1371/journal.pcbi.1009268}, pages = {33}, year = {2021}, abstract = {Amoeboid cell motility is essential for a wide range of biological processes including wound healing, embryonic morphogenesis, and cancer metastasis. It relies on complex dynamical patterns of cell shape changes that pose long-standing challenges to mathematical modeling and raise a need for automated and reproducible approaches to extract quantitative morphological features from image sequences. Here, we introduce a theoretical framework and a computational method for obtaining smooth representations of the spatiotemporal contour dynamics from stacks of segmented microscopy images. Based on a Gaussian process regression we propose a one-parameter family of regularized contour flows that allows us to continuously track reference points (virtual markers) between successive cell contours. We use this approach to define a coordinate system on the moving cell boundary and to represent different local geometric quantities in this frame of reference. In particular, we introduce the local marker dispersion as a measure to identify localized membrane expansions and provide a fully automated way to extract the properties of such expansions, including their area and growth time. The methods are available as an open-source software package called AmoePy, a Python-based toolbox for analyzing amoeboid cell motility (based on time-lapse microscopy data), including a graphical user interface and detailed documentation. Due to the mathematical rigor of our framework, we envision it to be of use for the development of novel cell motility models. We mainly use experimental data of the social amoeba Dictyostelium discoideum to illustrate and validate our approach.
Author summary Amoeboid motion is a crawling-like cell migration that plays an important key role in multiple biological processes such as wound healing and cancer metastasis. This type of cell motility results from expanding and simultaneously contracting parts of the cell membrane. From fluorescence images, we obtain a sequence of points, representing the cell membrane, for each time step. By using regression analysis on these sequences, we derive smooth representations, so-called contours, of the membrane. Since the number of measurements is discrete and often limited, the question is raised of how to link consecutive contours with each other. In this work, we present a novel mathematical framework in which these links are described by regularized flows allowing a certain degree of concentration or stretching of neighboring reference points on the same contour. This stretching rate, the so-called local dispersion, is used to identify expansions and contractions of the cell membrane providing a fully automated way of extracting properties of these cell shape changes. We applied our methods to time-lapse microscopy data of the social amoeba Dictyostelium discoideum.}, language = {en} } @article{TavakoliAlirezazadehHedayatipouretal.2021, author = {Tavakoli, Hamad and Alirezazadeh, Pendar and Hedayatipour, Ava and Nasib, A. H. Banijamali and Landwehr, Niels}, title = {Leaf image-based classification of some common bean cultivars using discriminative convolutional neural networks}, series = {Computers and electronics in agriculture : COMPAG online ; an international journal}, volume = {181}, journal = {Computers and electronics in agriculture : COMPAG online ; an international journal}, publisher = {Elsevier}, address = {Amsterdam [u.a.]}, issn = {0168-1699}, doi = {10.1016/j.compag.2020.105935}, pages = {11}, year = {2021}, abstract = {In recent years, many efforts have been made to apply image processing techniques for plant leaf identification. However, categorizing leaf images at the cultivar/variety level, because of the very low inter-class variability, is still a challenging task. In this research, we propose an automatic discriminative method based on convolutional neural networks (CNNs) for classifying 12 different cultivars of common beans that belong to three various species. We show that employing advanced loss functions, such as Additive Angular Margin Loss and Large Margin Cosine Loss, instead of the standard softmax loss function for the classification can yield better discrimination between classes and thereby mitigate the problem of low inter-class variability. The method was evaluated by classifying species (level I), cultivars from the same species (level II), and cultivars from different species (level III), based on images from the leaf foreside and backside. The results indicate that the performance of the classification algorithm on the leaf backside image dataset is superior. The maximum mean classification accuracies of 95.86, 91.37 and 86.87\% were obtained at the levels I, II and III, respectively. The proposed method outperforms the previous relevant works and provides a reliable approach for plant cultivars identification.}, language = {en} } @article{PfitznerSteckhanArnrich2021, author = {Pfitzner, Bjarne and Steckhan, Nico and Arnrich, Bert}, title = {Federated learning in a medical context}, series = {ACM transactions on internet technology : TOIT / Association for Computing}, volume = {21}, journal = {ACM transactions on internet technology : TOIT / Association for Computing}, number = {2}, publisher = {Association for Computing Machinery}, address = {New York}, issn = {1533-5399}, doi = {10.1145/3412357}, pages = {1 -- 31}, year = {2021}, abstract = {Data privacy is a very important issue. Especially in fields like medicine, it is paramount to abide by the existing privacy regulations to preserve patients' anonymity. However, data is required for research and training machine learning models that could help gain insight into complex correlations or personalised treatments that may otherwise stay undiscovered. Those models generally scale with the amount of data available, but the current situation often prohibits building large databases across sites. So it would be beneficial to be able to combine similar or related data from different sites all over the world while still preserving data privacy. Federated learning has been proposed as a solution for this, because it relies on the sharing of machine learning models, instead of the raw data itself. That means private data never leaves the site or device it was collected on. Federated learning is an emerging research area, and many domains have been identified for the application of those methods. This systematic literature review provides an extensive look at the concept of and research into federated learning and its applicability for confidential healthcare datasets.}, language = {en} } @article{BonnetDongNaumannetal.2021, author = {Bonnet, Philippe and Dong, Xin Luna and Naumann, Felix and T{\"o}z{\"u}n, P{\i}nar}, title = {VLDB 2021}, series = {SIGMOD record}, volume = {50}, journal = {SIGMOD record}, number = {4}, publisher = {Association for Computing Machinery}, address = {New York}, issn = {0163-5808}, doi = {10.1145/3516431.3516447}, pages = {50 -- 53}, year = {2021}, abstract = {The 47th International Conference on Very Large Databases (VLDB'21) was held on August 16-20, 2021 as a hybrid conference. It attracted 180 in-person attendees in Copenhagen and 840 remote attendees. In this paper, we describe our key decisions as general chairs and program committee chairs and share the lessons we learned.}, language = {en} } @article{NguyenGeorgieKayhanetal.2021, author = {Nguyen, Dong Hai Phuong and Georgie, Yasmin Kim and Kayhan, Ezgi and Eppe, Manfred and Hafner, Verena Vanessa and Wermter, Stefan}, title = {Sensorimotor representation learning for an "active self" in robots}, series = {K{\"u}nstliche Intelligenz : KI ; Forschung, Entwicklung, Erfahrungen ; Organ des Fachbereichs 1 K{\"u}nstliche Intelligenz der Gesellschaft f{\"u}r Informatik e.V., GI / Fachbereich 1 der Gesellschaft f{\"u}r Informatik e.V}, volume = {35}, journal = {K{\"u}nstliche Intelligenz : KI ; Forschung, Entwicklung, Erfahrungen ; Organ des Fachbereichs 1 K{\"u}nstliche Intelligenz der Gesellschaft f{\"u}r Informatik e.V., GI / Fachbereich 1 der Gesellschaft f{\"u}r Informatik e.V}, number = {1}, publisher = {Springer}, address = {Berlin}, issn = {0933-1875}, doi = {10.1007/s13218-021-00703-z}, pages = {9 -- 35}, year = {2021}, abstract = {Safe human-robot interactions require robots to be able to learn how to behave appropriately in spaces populated by people and thus to cope with the challenges posed by our dynamic and unstructured environment, rather than being provided a rigid set of rules for operations. In humans, these capabilities are thought to be related to our ability to perceive our body in space, sensing the location of our limbs during movement, being aware of other objects and agents, and controlling our body parts to interact with them intentionally. Toward the next generation of robots with bio-inspired capacities, in this paper, we first review the developmental processes of underlying mechanisms of these abilities: The sensory representations of body schema, peripersonal space, and the active self in humans. Second, we provide a survey of robotics models of these sensory representations and robotics models of the self; and we compare these models with the human counterparts. Finally, we analyze what is missing from these robotics models and propose a theoretical computational framework, which aims to allow the emergence of the sense of self in artificial agents by developing sensory representations through self-exploration.}, language = {en} } @article{OmranianAngeleskaNikoloski2021, author = {Omranian, Sara and Angeleska, Angela and Nikoloski, Zoran}, title = {PC2P}, series = {Bioinformatics}, volume = {37}, journal = {Bioinformatics}, number = {1}, publisher = {Oxford Univ. Press}, address = {Oxford}, issn = {1367-4811}, doi = {10.1093/bioinformatics/btaa1089}, pages = {73 -- 81}, year = {2021}, abstract = {Motivation: Prediction of protein complexes from protein-protein interaction (PPI) networks is an important problem in systems biology, as they control different cellular functions. The existing solutions employ algorithms for network community detection that identify dense subgraphs in PPI networks. However, gold standards in yeast and human indicate that protein complexes can also induce sparse subgraphs, introducing further challenges in protein complex prediction. Results: To address this issue, we formalize protein complexes as biclique spanned subgraphs, which include both sparse and dense subgraphs. We then cast the problem of protein complex prediction as a network partitioning into biclique spanned subgraphs with removal of minimum number of edges, called coherent partition. Since finding a coherent partition is a computationally intractable problem, we devise a parameter-free greedy approximation algorithm, termed Protein Complexes from Coherent Partition (PC2P), based on key properties of biclique spanned subgraphs. Through comparison with nine contenders, we demonstrate that PC2P: (i) successfully identifies modular structure in networks, as a prerequisite for protein complex prediction, (ii) outperforms the existing solutions with respect to a composite score of five performance measures on 75\% and 100\% of the analyzed PPI networks and gold standards in yeast and human, respectively, and (iii,iv) does not compromise GO semantic similarity and enrichment score of the predicted protein complexes. Therefore, our study demonstrates that clustering of networks in terms of biclique spanned subgraphs is a promising framework for detection of complexes in PPI networks.}, language = {en} } @article{TrautmannZhouBrahmsetal.2021, author = {Trautmann, Justin and Zhou, Lin and Brahms, Clemens Markus and Tunca, Can and Ersoy, Cem and Granacher, Urs and Arnrich, Bert}, title = {TRIPOD}, series = {Data : open access ʻData in scienceʼ journal}, volume = {6}, journal = {Data : open access ʻData in scienceʼ journal}, number = {9}, publisher = {MDPI}, address = {Basel}, issn = {2306-5729}, doi = {10.3390/data6090095}, pages = {19}, year = {2021}, abstract = {Inertial measurement units (IMUs) enable easy to operate and low-cost data recording for gait analysis. When combined with treadmill walking, a large number of steps can be collected in a controlled environment without the need of a dedicated gait analysis laboratory. In order to evaluate existing and novel IMU-based gait analysis algorithms for treadmill walking, a reference dataset that includes IMU data as well as reliable ground truth measurements for multiple participants and walking speeds is needed. This article provides a reference dataset consisting of 15 healthy young adults who walked on a treadmill at three different speeds. Data were acquired using seven IMUs placed on the lower body, two different reference systems (Zebris FDMT-HQ and OptoGait), and two RGB cameras. Additionally, in order to validate an existing IMU-based gait analysis algorithm using the dataset, an adaptable modular data analysis pipeline was built. Our results show agreement between the pressure-sensitive Zebris and the photoelectric OptoGait system (r = 0.99), demonstrating the quality of our reference data. As a use case, the performance of an algorithm originally designed for overground walking was tested on treadmill data using the data pipeline. The accuracy of stride length and stride time estimations was comparable to that reported in other studies with overground data, indicating that the algorithm is equally applicable to treadmill data. The Python source code of the data pipeline is publicly available, and the dataset will be provided by the authors upon request, enabling future evaluations of IMU gait analysis algorithms without the need of recording new data.}, language = {en} } @article{CabalarFandinoFarinasdelCerro2021, author = {Cabalar, Pedro and Fandi{\~n}o, Jorge and Fari{\~n}as del Cerro, Luis}, title = {Splitting epistemic logic programs}, series = {Theory and practice of logic programming / publ. for the Association for Logic Programming}, volume = {21}, journal = {Theory and practice of logic programming / publ. for the Association for Logic Programming}, number = {3}, publisher = {Cambridge Univ. Press}, address = {Cambridge [u.a.]}, issn = {1471-0684}, doi = {10.1017/S1471068420000058}, pages = {296 -- 316}, year = {2021}, abstract = {Epistemic logic programs constitute an extension of the stable model semantics to deal with new constructs called subjective literals. Informally speaking, a subjective literal allows checking whether some objective literal is true in all or some stable models. As it can be imagined, the associated semantics has proved to be non-trivial, since the truth of subjective literals may interfere with the set of stable models it is supposed to query. As a consequence, no clear agreement has been reached and different semantic proposals have been made in the literature. Unfortunately, comparison among these proposals has been limited to a study of their effect on individual examples, rather than identifying general properties to be checked. In this paper, we propose an extension of the well-known splitting property for logic programs to the epistemic case. We formally define when an arbitrary semantics satisfies the epistemic splitting property and examine some of the consequences that can be derived from that, including its relation to conformant planning and to epistemic constraints. Interestingly, we prove (through counterexamples) that most of the existing approaches fail to fulfill the epistemic splitting property, except the original semantics proposed by Gelfond 1991 and a recent proposal by the authors, called Founded Autoepistemic Equilibrium Logic.}, language = {en} } @article{DeFreitasJohnsonGoldenetal.2021, author = {De Freitas, Jessica K. and Johnson, Kipp W. and Golden, Eddye and Nadkarni, Girish N. and Dudley, Joel T. and B{\"o}ttinger, Erwin and Glicksberg, Benjamin S. and Miotto, Riccardo}, title = {Phe2vec}, series = {Patterns}, volume = {2}, journal = {Patterns}, number = {9}, publisher = {Elsevier}, address = {Amsterdam}, issn = {2666-3899}, doi = {10.1016/j.patter.2021.100337}, pages = {9}, year = {2021}, abstract = {Robust phenotyping of patients from electronic health records (EHRs) at scale is a challenge in clinical informatics. Here, we introduce Phe2vec, an automated framework for disease phenotyping from EHRs based on unsupervised learning and assess its effectiveness against standard rule-based algorithms from Phenotype KnowledgeBase (PheKB). Phe2vec is based on pre-computing embeddings of medical concepts and patients' clinical history. Disease phenotypes are then derived from a seed concept and its neighbors in the embedding space. Patients are linked to a disease if their embedded representation is close to the disease phenotype. Comparing Phe2vec and PheKB cohorts head-to-head using chart review, Phe2vec performed on par or better in nine out of ten diseases. Differently from other approaches, it can scale to any condition and was validated against widely adopted expert-based standards. Phe2vec aims to optimize clinical informatics research by augmenting current frameworks to characterize patients by condition and derive reliable disease cohorts.}, language = {en} } @article{FreitasdaCruzPfahringerMartensenetal.2021, author = {Freitas da Cruz, Harry and Pfahringer, Boris and Martensen, Tom and Schneider, Frederic and Meyer, Alexander and B{\"o}ttinger, Erwin and Schapranow, Matthieu-Patrick}, title = {Using interpretability approaches to update "black-box" clinical prediction models}, series = {Artificial intelligence in medicine : AIM}, volume = {111}, journal = {Artificial intelligence in medicine : AIM}, publisher = {Elsevier}, address = {Amsterdam}, issn = {0933-3657}, doi = {10.1016/j.artmed.2020.101982}, pages = {13}, year = {2021}, abstract = {Despite advances in machine learning-based clinical prediction models, only few of such models are actually deployed in clinical contexts. Among other reasons, this is due to a lack of validation studies. In this paper, we present and discuss the validation results of a machine learning model for the prediction of acute kidney injury in cardiac surgery patients initially developed on the MIMIC-III dataset when applied to an external cohort of an American research hospital. To help account for the performance differences observed, we utilized interpretability methods based on feature importance, which allowed experts to scrutinize model behavior both at the global and local level, making it possible to gain further insights into why it did not behave as expected on the validation cohort. The knowledge gleaned upon derivation can be potentially useful to assist model update during validation for more generalizable and simpler models. We argue that interpretability methods should be considered by practitioners as a further tool to help explain performance differences and inform model update in validation studies.}, language = {en} } @article{BorchertMockTomczaketal.2021, author = {Borchert, Florian and Mock, Andreas and Tomczak, Aurelie and H{\"u}gel, Jonas and Alkarkoukly, Samer and Knurr, Alexander and Volckmar, Anna-Lena and Stenzinger, Albrecht and Schirmacher, Peter and Debus, J{\"u}rgen and J{\"a}ger, Dirk and Longerich, Thomas and Fr{\"o}hling, Stefan and Eils, Roland and Bougatf, Nina and Sax, Ulrich and Schapranow, Matthieu-Patrick}, title = {Knowledge bases and software support for variant interpretation in precision oncology}, series = {Briefings in bioinformatics}, volume = {22}, journal = {Briefings in bioinformatics}, number = {6}, publisher = {Oxford Univ. Press}, address = {Oxford}, issn = {1467-5463}, doi = {10.1093/bib/bbab134}, pages = {17}, year = {2021}, abstract = {Precision oncology is a rapidly evolving interdisciplinary medical specialty. Comprehensive cancer panels are becoming increasingly available at pathology departments worldwide, creating the urgent need for scalable cancer variant annotation and molecularly informed treatment recommendations. A wealth of mainly academia-driven knowledge bases calls for software tools supporting the multi-step diagnostic process. We derive a comprehensive list of knowledge bases relevant for variant interpretation by a review of existing literature followed by a survey among medical experts from university hospitals in Germany. In addition, we review cancer variant interpretation tools, which integrate multiple knowledge bases. We categorize the knowledge bases along the diagnostic process in precision oncology and analyze programmatic access options as well as the integration of knowledge bases into software tools. The most commonly used knowledge bases provide good programmatic access options and have been integrated into a range of software tools. For the wider set of knowledge bases, access options vary across different parts of the diagnostic process. Programmatic access is limited for information regarding clinical classifications of variants and for therapy recommendations. The main issue for databases used for biological classification of pathogenic variants and pathway context information is the lack of standardized interfaces. There is no single cancer variant interpretation tool that integrates all identified knowledge bases. Specialized tools are available and need to be further developed for different steps in the diagnostic process.}, language = {en} } @article{FandinoLaferriereRomeroetal.2021, author = {Fandi{\~n}o, Jorge and Laferriere, Francois and Romero, Javier and Schaub, Torsten H. and Son, Tran Cao}, title = {Planning with incomplete information in quantified answer set programming}, series = {Theory and practice of logic programming}, volume = {21}, journal = {Theory and practice of logic programming}, number = {5}, publisher = {Cambridge University Press}, address = {Cambridge}, issn = {1471-0684}, doi = {10.1017/S1471068421000259}, pages = {663 -- 679}, year = {2021}, abstract = {We present a general approach to planning with incomplete information in Answer Set Programming (ASP). More precisely, we consider the problems of conformant and conditional planning with sensing actions and assumptions. We represent planning problems using a simple formalism where logic programs describe the transition function between states, the initial states and the goal states. For solving planning problems, we use Quantified Answer Set Programming (QASP), an extension of ASP with existential and universal quantifiers over atoms that is analogous to Quantified Boolean Formulas (QBFs). We define the language of quantified logic programs and use it to represent the solutions different variants of conformant and conditional planning. On the practical side, we present a translation-based QASP solver that converts quantified logic programs into QBFs and then executes a QBF solver, and we evaluate experimentally the approach on conformant and conditional planning benchmarks.}, language = {en} } @article{KayaFreitag2022, author = {Kaya, Adem and Freitag, Melina A.}, title = {Conditioning analysis for discrete Helmholtz problems}, series = {Computers and mathematics with applications : an international journal}, volume = {118}, journal = {Computers and mathematics with applications : an international journal}, publisher = {Elsevier Science}, address = {Amsterdam}, issn = {0898-1221}, doi = {10.1016/j.camwa.2022.05.016}, pages = {171 -- 182}, year = {2022}, abstract = {In this paper, we examine conditioning of the discretization of the Helmholtz problem. Although the discrete Helmholtz problem has been studied from different perspectives, to the best of our knowledge, there is no conditioning analysis for it. We aim to fill this gap in the literature. We propose a novel method in 1D to observe the near-zero eigenvalues of a symmetric indefinite matrix. Standard classification of ill-conditioning based on the matrix condition number is not true for the discrete Helmholtz problem. We relate the ill-conditioning of the discretization of the Helmholtz problem with the condition number of the matrix. We carry out analytical conditioning analysis in 1D and extend our observations to 2D with numerical observations. We examine several discretizations. We find different regions in which the condition number of the problem shows different characteristics. We also explain the general behavior of the solutions in these regions.}, language = {en} } @article{MattisBeckmannReinetal.2022, author = {Mattis, Toni and Beckmann, Tom and Rein, Patrick and Hirschfeld, Robert}, title = {First-class concepts}, series = {Journal of object technology : JOT / ETH Z{\"u}rich, Department of Computer Science}, volume = {21}, journal = {Journal of object technology : JOT / ETH Z{\"u}rich, Department of Computer Science}, number = {2}, publisher = {ETH Z{\"u}rich, Department of Computer Science}, address = {Z{\"u}rich}, issn = {1660-1769}, doi = {10.5381/jot.2022.21.2.a6}, pages = {1 -- 15}, year = {2022}, abstract = {Ideally, programs are partitioned into independently maintainable and understandable modules. As a system grows, its architecture gradually loses the capability to accommodate new concepts in a modular way. While refactoring is expensive and not always possible, and the programming language might lack dedicated primary language constructs to express certain cross-cutting concerns, programmers are still able to explain and delineate convoluted concepts through secondary means: code comments, use of whitespace and arrangement of code, documentation, or communicating tacit knowledge.
Secondary constructs are easy to change and provide high flexibility in communicating cross-cutting concerns and other concepts among programmers. However, such secondary constructs usually have no reified representation that can be explored and manipulated as first-class entities through the programming environment.
In this exploratory work, we discuss novel ways to express a wide range of concepts, including cross-cutting concerns, patterns, and lifecycle artifacts independently of the dominant decomposition imposed by an existing architecture. We propose the representation of concepts as first-class objects inside the programming environment that retain the capability to change as easily as code comments. We explore new tools that allow programmers to view, navigate, and change programs based on conceptual perspectives. In a small case study, we demonstrate how such views can be created and how the programming experience changes from draining programmers' attention by stretching it across multiple modules toward focusing it on cohesively presented concepts. Our designs are geared toward facilitating multiple secondary perspectives on a system to co-exist in symbiosis with the original architecture, hence making it easier to explore, understand, and explain complex contexts and narratives that are hard or impossible to express using primary modularity constructs.}, language = {en} } @article{SchmidlPapenbrock2022, author = {Schmidl, Sebastian and Papenbrock, Thorsten}, title = {Efficient distributed discovery of bidirectional order dependencies}, series = {The VLDB journal}, volume = {31}, journal = {The VLDB journal}, number = {1}, publisher = {Springer}, address = {Berlin ; Heidelberg ; New York}, issn = {1066-8888}, doi = {10.1007/s00778-021-00683-4}, pages = {49 -- 74}, year = {2022}, abstract = {Bidirectional order dependencies (bODs) capture order relationships between lists of attributes in a relational table. They can express that, for example, sorting books by publication date in ascending order also sorts them by age in descending order. The knowledge about order relationships is useful for many data management tasks, such as query optimization, data cleaning, or consistency checking. Because the bODs of a specific dataset are usually not explicitly given, they need to be discovered. The discovery of all minimal bODs (in set-based canonical form) is a task with exponential complexity in the number of attributes, though, which is why existing bOD discovery algorithms cannot process datasets of practically relevant size in a reasonable time. In this paper, we propose the distributed bOD discovery algorithm DISTOD, whose execution time scales with the available hardware. DISTOD is a scalable, robust, and elastic bOD discovery approach that combines efficient pruning techniques for bOD candidates in set-based canonical form with a novel, reactive, and distributed search strategy. Our evaluation on various datasets shows that DISTOD outperforms both single-threaded and distributed state-of-the-art bOD discovery algorithms by up to orders of magnitude; it can, in particular, process much larger datasets.}, language = {en} } @article{KrauseGrosseDetersBaumannetal.2022, author = {Krause, Hannes-Vincent and Große Deters, Fenne and Baumann, Annika and Krasnova, Hanna}, title = {Active social media use and its impact on well-being}, series = {Journal of computer-mediated communication : a journal of the International Communication Association}, volume = {28}, journal = {Journal of computer-mediated communication : a journal of the International Communication Association}, number = {1}, publisher = {Oxford Univ. Press}, address = {Oxford}, issn = {1083-6101}, doi = {10.1093/jcmc/zmac037}, pages = {12}, year = {2022}, abstract = {Active use of social networking sites (SNSs) has long been assumed to benefit users' well-being. However, this established hypothesis is increasingly being challenged, with scholars criticizing its lack of empirical support and the imprecise conceptualization of active use. Nevertheless, with considerable heterogeneity among existing studies on the hypothesis and causal evidence still limited, a final verdict on its robustness is still pending. To contribute to this ongoing debate, we conducted a week-long randomized control trial with N = 381 adult Instagram users recruited via Prolific. Specifically, we tested how active SNS use, operationalized as picture postings on Instagram, affects different dimensions of well-being. The results depicted a positive effect on users' positive affect but null findings for other well-being outcomes. The findings broadly align with the recent criticism against the active use hypothesis and support the call for a more nuanced view on the impact of SNSs.
Lay Summary Active use of social networking sites (SNSs) has long been assumed to benefit users' well-being. However, this established assumption is increasingly being challenged, with scholars criticizing its lack of empirical support and the imprecise conceptualization of active use. Nevertheless, with great diversity among conducted studies on the hypothesis and a lack of causal evidence, a final verdict on its viability is still pending. To contribute to this ongoing debate, we conducted a week-long experimental investigation with 381 adult Instagram users. Specifically, we tested how posting pictures on Instagram affects different aspects of well-being. The results of this study depicted a positive effect of posting Instagram pictures on users' experienced positive emotions but no effects on other aspects of well-being. The findings broadly align with the recent criticism against the active use hypothesis and support the call for a more nuanced view on the impact of SNSs on users.}, language = {en} } @article{UllrichVladovaEigelshovenetal.2022, author = {Ullrich, Andr{\´e} and Vladova, Gergana and Eigelshoven, Felix and Renz, Andr{\´e}}, title = {Data mining of scientific research on artificial intelligence in teaching and administration in higher education institutions}, series = {Discover artificial intelligence}, volume = {2}, journal = {Discover artificial intelligence}, publisher = {Springer}, address = {Cham}, issn = {2731-0809}, doi = {10.1007/s44163-022-00031-7}, pages = {18}, year = {2022}, abstract = {Teaching and learning as well as administrative processes are still experiencing intensive changes with the rise of artificial intelligence (AI) technologies and its diverse application opportunities in the context of higher education. Therewith, the scientific interest in the topic in general, but also specific focal points rose as well. However, there is no structured overview on AI in teaching and administration processes in higher education institutions that allows to identify major research topics and trends, and concretizing peculiarities and develops recommendations for further action. To overcome this gap, this study seeks to systematize the current scientific discourse on AI in teaching and administration in higher education institutions. This study identified an (1) imbalance in research on AI in educational and administrative contexts, (2) an imbalance in disciplines and lack of interdisciplinary research, (3) inequalities in cross-national research activities, as well as (4) neglected research topics and paths. In this way, a comparative analysis between AI usage in administration and teaching and learning processes, a systematization of the state of research, an identification of research gaps as well as further research path on AI in higher education institutions are contributed to research.}, language = {en} } @article{BenderKoerppen2022, author = {Bender, Benedict and K{\"o}rppen, Tim}, title = {Integriert statt isoliert}, series = {Digital business : cloud}, volume = {26}, journal = {Digital business : cloud}, number = {1}, publisher = {WIN-Verlag GmbH \& Co. KG}, address = {Vaterstetten}, issn = {2510-344X}, pages = {26 -- 27}, year = {2022}, abstract = {Dass Daten und Analysen Innovationstreiber sind und nicht mehr nur einen Hygienefaktor darstellen, haben viele Unternehmen erkannt. Um Potenziale zu heben, m{\"u}ssen Daten zielf{\"u}hrend integriert werden. Komplexe Systemlandschaften und isolierte Datenbest{\"a}nde erschweren dies. Technologien f{\"u}r die erfolgreiche Umsetzung von datengetriebenem Management m{\"u}ssen richtig eingesetzt werden.}, language = {de} } @article{SteinertStabernack2022, author = {Steinert, Fritjof and Stabernack, Benno}, title = {Architecture of a low latency H.264/AVC video codec for robust ML based image classification how region of interests can minimize the impact of coding artifacts}, series = {Journal of Signal Processing Systems for Signal, Image, and Video Technology}, volume = {94}, journal = {Journal of Signal Processing Systems for Signal, Image, and Video Technology}, number = {7}, publisher = {Springer}, address = {New York}, issn = {1939-8018}, doi = {10.1007/s11265-021-01727-2}, pages = {693 -- 708}, year = {2022}, abstract = {The use of neural networks is considered as the state of the art in the field of image classification. A large number of different networks are available for this purpose, which, appropriately trained, permit a high level of classification accuracy. Typically, these networks are applied to uncompressed image data, since a corresponding training was also carried out using image data of similar high quality. However, if image data contains image errors, the classification accuracy deteriorates drastically. This applies in particular to coding artifacts which occur due to image and video compression. Typical application scenarios for video compression are narrowband transmission channels for which video coding is required but a subsequent classification is to be carried out on the receiver side. In this paper we present a special H.264/Advanced Video Codec (AVC) based video codec that allows certain regions of a picture to be coded with near constant picture quality in order to allow a reliable classification using neural networks, whereas the remaining image will be coded using constant bit rate. We have combined this feature with the ability to run with lowest latency properties, which is usually also required in remote control applications scenarios. The codec has been implemented as a fully hardwired High Definition video capable hardware architecture which is suitable for Field Programmable Gate Arrays.}, language = {en} } @article{BonifatiMiorNaumannetal.2022, author = {Bonifati, Angela and Mior, Michael J. and Naumann, Felix and Noack, Nele Sina}, title = {How inclusive are we?}, series = {SIGMOD record / Association for Computing Machinery, Special Interest Group on Management of Data}, volume = {50}, journal = {SIGMOD record / Association for Computing Machinery, Special Interest Group on Management of Data}, number = {4}, publisher = {Association for Computing Machinery}, address = {New York}, issn = {0163-5808}, doi = {10.1145/3516431.3516438}, pages = {30 -- 35}, year = {2022}, abstract = {ACM SIGMOD, VLDB and other database organizations have committed to fostering an inclusive and diverse community, as do many other scientific organizations. Recently, different measures have been taken to advance these goals, especially for underrepresented groups. One possible measure is double-blind reviewing, which aims to hide gender, ethnicity, and other properties of the authors.
We report the preliminary results of a gender diversity analysis of publications of the database community across several peer-reviewed venues, and also compare women's authorship percentages in both single-blind and double-blind venues along the years. We also obtained a cross comparison of the obtained results in data management with other relevant areas in Computer Science.}, language = {en} } @article{AlnoorTiberiusAtiyahetal.2022, author = {Alnoor, Alhamzah and Tiberius, Victor and Atiyah, Abbas Gatea and Khaw, Khai Wah and Yin, Teh Sin and Chew, XinYing and Abbas, Sammar}, title = {How positive and negative electronic word of mouth (eWOM) affects customers' intention to use social commerce?}, series = {International journal of human computer interaction}, journal = {International journal of human computer interaction}, publisher = {Taylor \& Francis}, address = {New York}, issn = {1044-7318}, doi = {10.1080/10447318.2022.2125610}, pages = {1 -- 30}, year = {2022}, abstract = {Advances in Web 2.0 technologies have led to the widespread assimilation of electronic commerce platforms as an innovative shopping method and an alternative to traditional shopping. However, due to pro-technology bias, scholars focus more on adopting technology, and slightly less attention has been given to the impact of electronic word of mouth (eWOM) on customers' intention to use social commerce. This study addresses the gap by examining the intention through exploring the effect of eWOM on males' and females' intentions and identifying the mediation of perceived crowding. To this end, we adopted a dual-stage multi-group structural equation modeling and artificial neural network (SEM-ANN) approach. We successfully extended the eWOM concept by integrating negative and positive factors and perceived crowding. The results reveal the causal and non-compensatory relationships between the constructs. The variables supported by the SEM analysis are adopted as the ANN model's input neurons. According to the natural significance obtained from the ANN approach, males' intentions to accept social commerce are related mainly to helping the company, followed by core functionalities. In contrast, females are highly influenced by technical aspects and mishandling. The ANN model predicts customers' intentions to use social commerce with an accuracy of 97\%. We discuss the theoretical and practical implications of increasing customers' intention toward social commerce channels among consumers based on our findings.}, language = {en} } @article{RichlySchlosserBoissier2022, author = {Richly, Keven and Schlosser, Rainer and Boissier, Martin}, title = {Budget-conscious fine-grained configuration optimization for spatio-temporal applications}, series = {Proceedings of the VLDB Endowment}, volume = {15}, journal = {Proceedings of the VLDB Endowment}, number = {13}, publisher = {Association for Computing Machinery (ACM)}, address = {[New York]}, issn = {2150-8097}, doi = {10.14778/3565838.3565858}, pages = {4079 -- 4092}, year = {2022}, abstract = {Based on the performance requirements of modern spatio-temporal data mining applications, in-memory database systems are often used to store and process the data. To efficiently utilize the scarce DRAM capacities, modern database systems support various tuning possibilities to reduce the memory footprint (e.g., data compression) or increase performance (e.g., additional indexes). However, the selection of cost and performance balancing configurations is challenging due to the vast number of possible setups consisting of mutually dependent individual decisions. In this paper, we introduce a novel approach to jointly optimize the compression, sorting, indexing, and tiering configuration for spatio-temporal workloads. Further, we consider horizontal data partitioning, which enables the independent application of different tuning options on a fine-grained level. We propose different linear programming (LP) models addressing cost dependencies at different levels of accuracy to compute optimized tuning configurations for a given workload and memory budgets. To yield maintainable and robust configurations, we extend our LP-based approach to incorporate reconfiguration costs as well as a worst-case optimization for potential workload scenarios. Further, we demonstrate on a real-world dataset that our models allow to significantly reduce the memory footprint with equal performance or increase the performance with equal memory size compared to existing tuning heuristics.}, language = {en} } @article{BlaesiusFriedrichLischeidetal.2022, author = {Bl{\"a}sius, Thomas and Friedrich, Tobias and Lischeid, Julius and Meeks, Kitty and Schirneck, Friedrich Martin}, title = {Efficiently enumerating hitting sets of hypergraphs arising in data profiling}, series = {Journal of computer and system sciences : JCSS}, volume = {124}, journal = {Journal of computer and system sciences : JCSS}, publisher = {Elsevier}, address = {San Diego}, issn = {0022-0000}, doi = {10.1016/j.jcss.2021.10.002}, pages = {192 -- 213}, year = {2022}, abstract = {The transversal hypergraph problem asks to enumerate the minimal hitting sets of a hypergraph. If the solutions have bounded size, Eiter and Gottlob [SICOMP'95] gave an algorithm running in output-polynomial time, but whose space requirement also scales with the output. We improve this to polynomial delay and space. Central to our approach is the extension problem, deciding for a set X of vertices whether it is contained in any minimal hitting set. We show that this is one of the first natural problems to be W[3]-complete. We give an algorithm for the extension problem running in time O(m(vertical bar X vertical bar+1) n) and prove a SETH-lower bound showing that this is close to optimal. We apply our enumeration method to the discovery problem of minimal unique column combinations from data profiling. Our empirical evaluation suggests that the algorithm outperforms its worst-case guarantees on hypergraphs stemming from real-world databases.}, language = {en} } @article{vonSteinauSteinrueckKurth2022, author = {von Steinau-Steinr{\"u}ck, Robert and Kurth, Paula Sophie}, title = {Das reformierte Statusfeststellungsverfahren in der Praxis}, series = {NJW spezial}, volume = {19}, journal = {NJW spezial}, number = {24}, publisher = {C.H. Beck}, address = {M{\"u}nchen}, issn = {1613-4621}, pages = {754 -- 755}, year = {2022}, abstract = {Das Statusfeststellungsverfahren erm{\"o}glicht auf Antrag bei der alleinzust{\"a}ndigen Deutschen Rentenversicherung Bund den Erhalt einer verbindlichen Einsch{\"a}tzung der h{\"a}ufig komplizierten und folgenschweren Abgrenzung einer selbstst{\"a}ndigen T{\"a}tigkeit von einer abh{\"a}ngigen Besch{\"a}ftigung. Zum 1.4.2022 wurde das Statusfeststellungsverfahren umfassend reformiert. In der Praxis haben sich die eingef{\"u}hrten Novellierungen bislang unterschiedlich bew{\"a}hrt.}, language = {de} } @article{vonSteinauSteinrueckMiller2022, author = {von Steinau-Steinr{\"u}ck, Robert and Miller, Denis}, title = {R{\"u}ckzahlungsklauseln f{\"u}r Fortbildungen}, series = {Neue juristische Wochenschrift : NJW Spezial}, volume = {19}, journal = {Neue juristische Wochenschrift : NJW Spezial}, number = {12}, publisher = {C.H. Beck}, address = {M{\"u}nchen}, issn = {1613-4621}, pages = {370 -- 371}, year = {2022}, abstract = {Mit Urteil vom 1.3.2022 (NZA2022, NZA Jahr 2022 Seite 780) hat das BAG erneut {\"u}ber die Wirksamkeit einer R{\"u}ckzahlungsklausel in einer Fortbildungsvereinbarung entschieden. Die Entscheidung reiht sich in eine nicht leicht zu durchschauende Anzahl von Urteilen hierzu ein. Sie dient uns zum Anlass, einen {\"U}berblick {\"u}ber die Rechtsprechung zu geben.}, language = {de} } @article{vonSteinauSteinrueckHoeltge2022, author = {von Steinau-Steinr{\"u}ck, Robert and H{\"o}ltge, Clara}, title = {Krieg in Europa}, series = {NJW spezial}, volume = {19}, journal = {NJW spezial}, number = {8}, publisher = {C.H. Beck}, address = {M{\"u}nchen}, issn = {1613-4621}, pages = {242 -- 243}, year = {2022}, abstract = {Am 24.2.2022 begann der russische Angriffskrieg in der Ukraine. Seitdem fliehen t{\"a}glich zahlreiche ukrainische Staatsb{\"u}rger in die Europ{\"a}ische Union, viele davon nach Deutschland. Vorrangig ist jetzt die Sicherung der Grundbed{\"u}rfnisse, wie Verpflegung, Unterkunft und medizinischer Versorgung. Daneben fragen sich Arbeitgeber, wie sie ukrainische Staatsb{\"u}rger m{\"o}glichst schnell besch{\"a}ftigen k{\"o}nnen. Wir geben einen {\"U}berblick {\"u}ber die M{\"o}glichkeiten, ukrainische Gefl{\"u}chtete m{\"o}glichst schnell in den deutschen Arbeitsmarkt zu integrieren.}, language = {de} } @article{IhdePufahlVoelkeretal.2022, author = {Ihde, Sven and Pufahl, Luise and V{\"o}lker, Maximilian and Goel, Asvin and Weske, Mathias}, title = {A framework for modeling and executing task}, series = {Computing : archives for informatics and numerical computation}, volume = {104}, journal = {Computing : archives for informatics and numerical computation}, publisher = {Springer}, address = {Wien}, issn = {0010-485X}, doi = {10.1007/s00607-022-01093-2}, pages = {2405 -- 2429}, year = {2022}, abstract = {As resources are valuable assets, organizations have to decide which resources to allocate to business process tasks in a way that the process is executed not only effectively but also efficiently. Traditional role-based resource allocation leads to effective process executions, since each task is performed by a resource that has the required skills and competencies to do so. However, the resulting allocations are typically not as efficient as they could be, since optimization techniques have yet to find their way in traditional business process management scenarios. On the other hand, operations research provides a rich set of analytical methods for supporting problem-specific decisions on resource allocation. This paper provides a novel framework for creating transparency on existing tasks and resources, supporting individualized allocations for each activity in a process, and the possibility to integrate problem-specific analytical methods of the operations research domain. To validate the framework, the paper reports on the design and prototypical implementation of a software architecture, which extends a traditional process engine with a dedicated resource management component. This component allows us to define specific resource allocation problems at design time, and it also facilitates optimized resource allocation at run time. The framework is evaluated using a real-world parcel delivery process. The evaluation shows that the quality of the allocation results increase significantly with a technique from operations research in contrast to the traditional applied rule-based approach.}, language = {en} } @article{Schladebach2022, author = {Schladebach, Marcus}, title = {Satelliten-Megakonstellationen im Weltraumrecht}, series = {Kommunikation \& Recht : K \& R / Beihefter}, journal = {Kommunikation \& Recht : K \& R / Beihefter}, number = {2}, publisher = {dfv-Mediengruppe}, address = {Frankfurt am Main}, issn = {1434-6354}, pages = {26 -- 29}, year = {2022}, language = {de} } @article{RoostapourNeumannNeumannetal.2022, author = {Roostapour, Vahid and Neumann, Aneta and Neumann, Frank and Friedrich, Tobias}, title = {Pareto optimization for subset selection with dynamic cost constraints}, series = {Artificial intelligence}, volume = {302}, journal = {Artificial intelligence}, publisher = {Elsevier}, address = {Amsterdam}, issn = {0004-3702}, doi = {10.1016/j.artint.2021.103597}, pages = {17}, year = {2022}, abstract = {We consider the subset selection problem for function f with constraint bound B that changes over time. Within the area of submodular optimization, various greedy approaches are commonly used. For dynamic environments we observe that the adaptive variants of these greedy approaches are not able to maintain their approximation quality. Investigating the recently introduced POMC Pareto optimization approach, we show that this algorithm efficiently computes a phi=(alpha(f)/2)(1 - 1/e(alpha)f)-approximation, where alpha(f) is the submodularity ratio of f, for each possible constraint bound b <= B. Furthermore, we show that POMC is able to adapt its set of solutions quickly in the case that B increases. Our experimental investigations for the influence maximization in social networks show the advantage of POMC over generalized greedy algorithms. We also consider EAMC, a new evolutionary algorithm with polynomial expected time guarantee to maintain phi approximation ratio, and NSGA-II with two different population sizes as advanced multi-objective optimization algorithm, to demonstrate their challenges in optimizing the maximum coverage problem. Our empirical analysis shows that, within the same number of evaluations, POMC is able to perform as good as NSGA-II under linear constraint, while EAMC performs significantly worse than all considered algorithms in most cases.}, language = {en} } @article{NdashimyeHebieTjaden2022, author = {Ndashimye, Felix and Hebie, Oumarou and Tjaden, Jasper}, title = {Effectiveness of WhatsApp for measuring migration in follow-up phone surveys}, series = {Social science computer review}, journal = {Social science computer review}, publisher = {Sage}, address = {Thousand Oaks}, issn = {0894-4393}, doi = {10.1177/08944393221111340}, pages = {20}, year = {2022}, abstract = {Phone surveys have increasingly become important data collection tools in developing countries, particularly in the context of sudden contact restrictions due to the COVID-19 pandemic. So far, there is limited evidence regarding the potential of the messenger service WhatsApp for remote data collection despite its large global coverage and expanding membership. WhatsApp may offer advantages in terms of reducing panel attrition and cutting survey costs. WhatsApp may offer additional benefits to migration scholars interested in cross-border migration behavior which is notoriously difficult to measure using conventional face-to-face surveys. In this field experiment, we compared the response rates between WhatsApp and interactive voice response (IVR) modes using a sample of 8446 contacts in Senegal and Guinea. At 12\%, WhatsApp survey response rates were nearly eight percentage points lower than IVR survey response rates. However, WhatsApp offers higher survey completion rates, substantially lower costs and does not introduce more sample selection bias compared to IVR. We discuss the potential of WhatsApp surveys in low-income contexts and provide practical recommendations for field implementation.}, language = {en} } @article{SpiekermannKrasnovaHinzetal.2022, author = {Spiekermann, Sarah and Krasnova, Hanna and Hinz, Oliver and Baumann, Annika and Benlian, Alexander and Gimpel, Henner and Heimbach, Irina and Koester, Antonia and Maedche, Alexander and Niehaves, Bjoern and Risius, Marten and Trenz, Manuel}, title = {Values and ethics in information systems}, series = {Business \& information systems engineering}, volume = {64}, journal = {Business \& information systems engineering}, number = {2}, publisher = {Springer Gabler}, address = {Wiesbaden}, issn = {2363-7005}, doi = {10.1007/s12599-021-00734-8}, pages = {247 -- 264}, year = {2022}, language = {en} } @article{StaufferMengeshaSeifertetal.2022, author = {Stauffer, Maxime and Mengesha, Isaak and Seifert, Konrad and Krawczuk, Igor and Fischer, Jens and Serugendo, Giovanna Di Marzo}, title = {A computational turn in policy process studies}, series = {Complexity}, volume = {2022}, journal = {Complexity}, publisher = {Wiley-Hindawi}, address = {London}, issn = {1076-2787}, doi = {10.1155/2022/8210732}, pages = {17}, year = {2022}, abstract = {The past three decades of policy process studies have seen the emergence of a clear intellectual lineage with regard to complexity. Implicitly or explicitly, scholars have employed complexity theory to examine the intricate dynamics of collective action in political contexts. However, the methodological counterparts to complexity theory, such as computational methods, are rarely used and, even if they are, they are often detached from established policy process theory. Building on a critical review of the application of complexity theory to policy process studies, we present and implement a baseline model of policy processes using the logic of coevolving networks. Our model suggests that an actor's influence depends on their environment and on exogenous events facilitating dialogue and consensus-building. Our results validate previous opinion dynamics models and generate novel patterns. Our discussion provides ground for further research and outlines the path for the field to achieve a computational turn.}, language = {en} } @article{WenderingNikoloski2022, author = {Wendering, Philipp and Nikoloski, Zoran}, title = {COMMIT}, series = {PLoS Computational Biology : a new community journal / publ. by the Public Library of Science (PLoS) in association with the International Society for Computational Biology (ISCB)}, volume = {18}, journal = {PLoS Computational Biology : a new community journal / publ. by the Public Library of Science (PLoS) in association with the International Society for Computational Biology (ISCB)}, number = {3}, publisher = {Public Library of Science}, address = {San Fransisco}, issn = {1553-734X}, doi = {10.1371/journal.pcbi.1009906}, pages = {24}, year = {2022}, abstract = {Composition and functions of microbial communities affect important traits in diverse hosts, from crops to humans. Yet, mechanistic understanding of how metabolism of individual microbes is affected by the community composition and metabolite leakage is lacking. Here, we first show that the consensus of automatically generated metabolic reconstructions improves the quality of the draft reconstructions, measured by comparison to reference models. We then devise an approach for gap filling, termed COMMIT, that considers metabolites for secretion based on their permeability and the composition of the community. By applying COMMIT with two soil communities from the Arabidopsis thaliana culture collection, we could significantly reduce the gap-filling solution in comparison to filling gaps in individual reconstructions without affecting the genomic support. Inspection of the metabolic interactions in the soil communities allows us to identify microbes with community roles of helpers and beneficiaries. Therefore, COMMIT offers a versatile fully automated solution for large-scale modelling of microbial communities for diverse biotechnological applications.
Author summaryMicrobial communities are important in ecology, human health, and crop productivity. However, detailed information on the interactions within natural microbial communities is hampered by the community size, lack of detailed information on the biochemistry of single organisms, and the complexity of interactions between community members. Metabolic models are comprised of biochemical reaction networks based on the genome annotation, and can provide mechanistic insights into community functions. Previous analyses of microbial community models have been performed with high-quality reference models or models generated using a single reconstruction pipeline. However, these models do not contain information on the composition of the community that determines the metabolites exchanged between the community members. In addition, the quality of metabolic models is affected by the reconstruction approach used, with direct consequences on the inferred interactions between community members. Here, we use fully automated consensus reconstructions from four approaches to arrive at functional models with improved genomic support while considering the community composition. We applied our pipeline to two soil communities from the Arabidopsis thaliana culture collection, providing only genome sequences. Finally, we show that the obtained models have 90\% genomic support and demonstrate that the derived interactions are corroborated by independent computational predictions.}, language = {en} } @article{BenlianWienerCrametal.2022, author = {Benlian, Alexander and Wiener, Martin and Cram, W. Alec and Krasnova, Hanna and Maedche, Alexander and Mohlmann, Mareike and Recker, Jan and Remus, Ulrich}, title = {Algorithmic management}, series = {Business and information systems engineering}, volume = {64}, journal = {Business and information systems engineering}, number = {6}, publisher = {Springer Gabler}, address = {Wiesbaden}, issn = {2363-7005}, doi = {10.1007/s12599-022-00764-w}, pages = {825 -- 839}, year = {2022}, language = {en} } @article{SeewannVerwiebeBuderetal.2022, author = {Seewann, Lena and Verwiebe, Roland and Buder, Claudia and Fritsch, Nina-Sophie}, title = {"Broadcast your gender."}, series = {Frontiers in Big Data}, journal = {Frontiers in Big Data}, number = {5}, publisher = {Frontiers}, address = {Lausanne, Schweiz}, issn = {2624-909X}, doi = {10.3389/fdata.2022.908636}, pages = {16}, year = {2022}, abstract = {Social media platforms provide a large array of behavioral data relevant to social scientific research. However, key information such as sociodemographic characteristics of agents are often missing. This paper aims to compare four methods of classifying social attributes from text. Specifically, we are interested in estimating the gender of German social media creators. By using the example of a random sample of 200 YouTube channels, we compare several classification methods, namely (1) a survey among university staff, (2) a name dictionary method with the World Gender Name Dictionary as a reference list, (3) an algorithmic approach using the website gender-api.com, and (4) a Multinomial Na{\"i}ve Bayes (MNB) machine learning technique. These different methods identify gender attributes based on YouTube channel names and descriptions in German but are adaptable to other languages. Our contribution will evaluate the share of identifiable channels, accuracy and meaningfulness of classification, as well as limits and benefits of each approach. We aim to address methodological challenges connected to classifying gender attributes for YouTube channels as well as related to reinforcing stereotypes and ethical implications.}, language = {en} } @article{ChenLangeAndjelkovicetal.2022, author = {Chen, Junchao and Lange, Thomas and Andjelkovic, Marko and Simevski, Aleksandar and Lu, Li and Krstić, Miloš}, title = {Solar particle event and single event upset prediction from SRAM-based monitor and supervised machine learning}, series = {IEEE transactions on emerging topics in computing / IEEE Computer Society, Institute of Electrical and Electronics Engineers}, volume = {10}, journal = {IEEE transactions on emerging topics in computing / IEEE Computer Society, Institute of Electrical and Electronics Engineers}, number = {2}, publisher = {Institute of Electrical and Electronics Engineers}, address = {[New York, NY]}, issn = {2168-6750}, doi = {10.1109/TETC.2022.3147376}, pages = {564 -- 580}, year = {2022}, abstract = {The intensity of cosmic radiation may differ over five orders of magnitude within a few hours or days during the Solar Particle Events (SPEs), thus increasing for several orders of magnitude the probability of Single Event Upsets (SEUs) in space-borne electronic systems. Therefore, it is vital to enable the early detection of the SEU rate changes in order to ensure timely activation of dynamic radiation hardening measures. In this paper, an embedded approach for the prediction of SPEs and SRAM SEU rate is presented. The proposed solution combines the real-time SRAM-based SEU monitor, the offline-trained machine learning model and online learning algorithm for the prediction. With respect to the state-of-the-art, our solution brings the following benefits: (1) Use of existing on-chip data storage SRAM as a particle detector, thus minimizing the hardware and power overhead, (2) Prediction of SRAM SEU rate one hour in advance, with the fine-grained hourly tracking of SEU variations during SPEs as well as under normal conditions, (3) Online optimization of the prediction model for enhancing the prediction accuracy during run-time, (4) Negligible cost of hardware accelerator design for the implementation of selected machine learning model and online learning algorithm. The proposed design is intended for a highly dependable and self-adaptive multiprocessing system employed in space applications, allowing to trigger the radiation mitigation mechanisms before the onset of high radiation levels.}, language = {en} } @article{TalebRohrerBergneretal.2022, author = {Taleb, Aiham and Rohrer, Csaba and Bergner, Benjamin and De Leon, Guilherme and Rodrigues, Jonas Almeida and Schwendicke, Falk and Lippert, Christoph and Krois, Joachim}, title = {Self-supervised learning methods for label-efficient dental caries classification}, series = {Diagnostics : open access journal}, volume = {12}, journal = {Diagnostics : open access journal}, number = {5}, publisher = {MDPI}, address = {Basel}, issn = {2075-4418}, doi = {10.3390/diagnostics12051237}, pages = {15}, year = {2022}, abstract = {High annotation costs are a substantial bottleneck in applying deep learning architectures to clinically relevant use cases, substantiating the need for algorithms to learn from unlabeled data. In this work, we propose employing self-supervised methods. To that end, we trained with three self-supervised algorithms on a large corpus of unlabeled dental images, which contained 38K bitewing radiographs (BWRs). We then applied the learned neural network representations on tooth-level dental caries classification, for which we utilized labels extracted from electronic health records (EHRs). Finally, a holdout test-set was established, which consisted of 343 BWRs and was annotated by three dental professionals and approved by a senior dentist. This test-set was used to evaluate the fine-tuned caries classification models. Our experimental results demonstrate the obtained gains by pretraining models using self-supervised algorithms. These include improved caries classification performance (6 p.p. increase in sensitivity) and, most importantly, improved label-efficiency. In other words, the resulting models can be fine-tuned using few labels (annotations). Our results show that using as few as 18 annotations can produce >= 45\% sensitivity, which is comparable to human-level diagnostic performance. This study shows that self-supervision can provide gains in medical image analysis, particularly when obtaining labels is costly and expensive.}, language = {en} } @article{PanzerBenderGronau2022, author = {Panzer, Marcel and Bender, Benedict and Gronau, Norbert}, title = {Neural agent-based production planning and control}, series = {Journal of Manufacturing Systems}, volume = {65}, journal = {Journal of Manufacturing Systems}, publisher = {Elsevier}, address = {Amsterdam}, issn = {0278-6125}, doi = {10.1016/j.jmsy.2022.10.019}, pages = {743 -- 766}, year = {2022}, abstract = {Nowadays, production planning and control must cope with mass customization, increased fluctuations in demand, and high competition pressures. Despite prevailing market risks, planning accuracy and increased adaptability in the event of disruptions or failures must be ensured, while simultaneously optimizing key process indicators. To manage that complex task, neural networks that can process large quantities of high-dimensional data in real time have been widely adopted in recent years. Although these are already extensively deployed in production systems, a systematic review of applications and implemented agent embeddings and architectures has not yet been conducted. The main contribution of this paper is to provide researchers and practitioners with an overview of applications and applied embeddings and to motivate further research in neural agent-based production. Findings indicate that neural agents are not only deployed in diverse applications, but are also increasingly implemented in multi-agent environments or in combination with conventional methods — leveraging performances compared to benchmarks and reducing dependence on human experience. This not only implies a more sophisticated focus on distributed production resources, but also broadening the perspective from a local to a global scale. Nevertheless, future research must further increase scalability and reproducibility to guarantee a simplified transfer of results to reality.}, language = {en} } @article{MontiRautenstrauchGhanbarietal.2022, author = {Monti, Remo and Rautenstrauch, Pia and Ghanbari, Mahsa and Rani James, Alva and Kirchler, Matthias and Ohler, Uwe and Konigorski, Stefan and Lippert, Christoph}, title = {Identifying interpretable gene-biomarker associations with functionally informed kernel-based tests in 190,000 exomes}, series = {Nature Communications}, volume = {13}, journal = {Nature Communications}, publisher = {Nature Publishing Group UK}, address = {London}, issn = {2041-1723}, doi = {10.1038/s41467-022-32864-2}, pages = {16}, year = {2022}, abstract = {Here we present an exome-wide rare genetic variant association study for 30 blood biomarkers in 191,971 individuals in the UK Biobank. We compare gene- based association tests for separate functional variant categories to increase interpretability and identify 193 significant gene-biomarker associations. Genes associated with biomarkers were ~ 4.5-fold enriched for conferring Mendelian disorders. In addition to performing weighted gene-based variant collapsing tests, we design and apply variant-category-specific kernel-based tests that integrate quantitative functional variant effect predictions for mis- sense variants, splicing and the binding of RNA-binding proteins. For these tests, we present a computationally efficient combination of the likelihood- ratio and score tests that found 36\% more associations than the score test alone while also controlling the type-1 error. Kernel-based tests identified 13\% more associations than their gene-based collapsing counterparts and had advantages in the presence of gain of function missense variants. We introduce local collapsing by amino acid position for missense variants and use it to interpret associations and identify potential novel gain of function variants in PIEZO1. Our results show the benefits of investigating different functional mechanisms when performing rare-variant association tests, and demonstrate pervasive rare-variant contribution to biomarker variability.}, language = {en} } @article{WiemkerBunovaNeufeldetal.2022, author = {Wiemker, Veronika and Bunova, Anna and Neufeld, Maria and Gornyi, Boris and Yurasova, Elena and Konigorski, Stefan and Kalinina, Anna and Kontsevaya, Anna and Ferreira-Borges, Carina and Probst, Charlotte}, title = {Pilot study to evaluate usability and acceptability of the 'Animated Alcohol Assessment Tool' in Russian primary healthcare}, series = {Digital health}, volume = {8}, journal = {Digital health}, publisher = {Sage Publications}, address = {London}, issn = {2055-2076}, doi = {10.1177/20552076211074491}, pages = {11}, year = {2022}, abstract = {Background and aims: Accurate and user-friendly assessment tools quantifying alcohol consumption are a prerequisite to effective prevention and treatment programmes, including Screening and Brief Intervention. Digital tools offer new potential in this field. We developed the 'Animated Alcohol Assessment Tool' (AAA-Tool), a mobile app providing an interactive version of the World Health Organization's Alcohol Use Disorders Identification Test (AUDIT) that facilitates the description of individual alcohol consumption via culturally informed animation features. This pilot study evaluated the Russia-specific version of the Animated Alcohol Assessment Tool with regard to (1) its usability and acceptability in a primary healthcare setting, (2) the plausibility of its alcohol consumption assessment results and (3) the adequacy of its Russia-specific vessel and beverage selection. Methods: Convenience samples of 55 patients (47\% female) and 15 healthcare practitioners (80\% female) in 2 Russian primary healthcare facilities self-administered the Animated Alcohol Assessment Tool and rated their experience on the Mobile Application Rating Scale - User Version. Usage data was automatically collected during app usage, and additional feedback on regional content was elicited in semi-structured interviews. Results: On average, patients completed the Animated Alcohol Assessment Tool in 6:38 min (SD = 2.49, range = 3.00-17.16). User satisfaction was good, with all subscale Mobile Application Rating Scale - User Version scores averaging >3 out of 5 points. A majority of patients (53\%) and practitioners (93\%) would recommend the tool to 'many people' or 'everyone'. Assessed alcohol consumption was plausible, with a low number (14\%) of logically impossible entries. Most patients reported the Animated Alcohol Assessment Tool to reflect all vessels (78\%) and all beverages (71\%) they typically used. Conclusion: High acceptability ratings by patients and healthcare practitioners, acceptable completion time, plausible alcohol usage assessment results and perceived adequacy of region-specific content underline the Animated Alcohol Assessment Tool's potential to provide a novel approach to alcohol assessment in primary healthcare. After its validation, the Animated Alcohol Assessment Tool might contribute to reducing alcohol-related harm by facilitating Screening and Brief Intervention implementation in Russia and beyond.}, language = {en} } @article{UlrichLutfiRutzenetal.2022, author = {Ulrich, Jens-Uwe and Lutfi, Ahmad and Rutzen, Kilian and Renard, Bernhard Y.}, title = {ReadBouncer}, series = {Bioinformatics}, volume = {38}, journal = {Bioinformatics}, number = {SUPPL 1}, publisher = {Oxford Univ. Press}, address = {Oxford}, issn = {1367-4803}, doi = {10.1093/bioinformatics/btac223}, pages = {153 -- 160}, year = {2022}, abstract = {Motivation: Nanopore sequencers allow targeted sequencing of interesting nucleotide sequences by rejecting other sequences from individual pores. This feature facilitates the enrichment of low-abundant sequences by depleting overrepresented ones in-silico. Existing tools for adaptive sampling either apply signal alignment, which cannot handle human-sized reference sequences, or apply read mapping in sequence space relying on fast graphical processing units (GPU) base callers for real-time read rejection. Using nanopore long-read mapping tools is also not optimal when mapping shorter reads as usually analyzed in adaptive sampling applications. Results: Here, we present a new approach for nanopore adaptive sampling that combines fast CPU and GPU base calling with read classification based on Interleaved Bloom Filters. ReadBouncer improves the potential enrichment of low abundance sequences by its high read classification sensitivity and specificity, outperforming existing tools in the field. It robustly removes even reads belonging to large reference sequences while running on commodity hardware without GPUs, making adaptive sampling accessible for in-field researchers. Readbouncer also provides a user-friendly interface and installer files for end-users without a bioinformatics background.}, language = {en} } @article{WittigMirandaHoelzeretal.2022, author = {Wittig, Alice and Miranda, Fabio Malcher and H{\"o}lzer, Martin and Altenburg, Tom and Bartoszewicz, Jakub Maciej and Beyvers, Sebastian and Dieckmann, Marius Alfred and Genske, Ulrich and Giese, Sven Hans-Joachim and Nowicka, Melania and Richard, Hugues and Schiebenhoefer, Henning and Schmachtenberg, Anna-Juliane and Sieben, Paul and Tang, Ming and Tembrockhaus, Julius and Renard, Bernhard Y. and Fuchs, Stephan}, title = {CovRadar}, series = {Bioinformatics}, volume = {38}, journal = {Bioinformatics}, number = {17}, publisher = {Oxford Univ. Press}, address = {Oxford}, issn = {1367-4803}, doi = {10.1093/bioinformatics/btac411}, pages = {4223 -- 4225}, year = {2022}, abstract = {The ongoing pandemic caused by SARS-CoV-2 emphasizes the importance of genomic surveillance to understand the evolution of the virus, to monitor the viral population, and plan epidemiological responses. Detailed analysis, easy visualization and intuitive filtering of the latest viral sequences are powerful for this purpose. We present CovRadar, a tool for genomic surveillance of the SARS-CoV-2 Spike protein. CovRadar consists of an analytical pipeline and a web application that enable the analysis and visualization of hundreds of thousand sequences. First, CovRadar extracts the regions of interest using local alignment, then builds a multiple sequence alignment, infers variants and consensus and finally presents the results in an interactive app, making accessing and reporting simple, flexible and fast.}, language = {en} } @article{RosinLaiMouldetal.2022, author = {Rosin, Paul L. and Lai, Yu-Kun and Mould, David and Yi, Ran and Berger, Itamar and Doyle, Lars and Lee, Seungyong and Li, Chuan and Liu, Yong-Jin and Semmo, Amir and Shamir, Ariel and Son, Minjung and Winnem{\"o}ller, Holger}, title = {NPRportrait 1.0: A three-level benchmark for non-photorealistic rendering of portraits}, series = {Computational visual media}, volume = {8}, journal = {Computational visual media}, number = {3}, publisher = {Springer Nature}, address = {London}, issn = {2096-0433}, doi = {10.1007/s41095-021-0255-3}, pages = {445 -- 465}, year = {2022}, abstract = {Recently, there has been an upsurge of activity in image-based non-photorealistic rendering (NPR), and in particular portrait image stylisation, due to the advent of neural style transfer (NST). However, the state of performance evaluation in this field is poor, especially compared to the norms in the computer vision and machine learning communities. Unfortunately, the task of evaluating image stylisation is thus far not well defined, since it involves subjective, perceptual, and aesthetic aspects. To make progress towards a solution, this paper proposes a new structured, three-level, benchmark dataset for the evaluation of stylised portrait images. Rigorous criteria were used for its construction, and its consistency was validated by user studies. Moreover, a new methodology has been developed for evaluating portrait stylisation algorithms, which makes use of the different benchmark levels as well as annotations provided by user studies regarding the characteristics of the faces. We perform evaluation for a wide variety of image stylisation methods (both portrait-specific and general purpose, and also both traditional NPR approaches and NST) using the new benchmark dataset.}, language = {en} } @article{RojahnWeberGronau2023, author = {Rojahn, Marcel and Weber, Edzard and Gronau, Norbert}, title = {Towards a standardization in scheduling models}, series = {International journal of industrial and systems engineering}, volume = {17}, journal = {International journal of industrial and systems engineering}, number = {6}, publisher = {Inderscience Enterprises}, address = {Gen{\`e}ve}, issn = {1748-5037}, pages = {401 -- 408}, year = {2023}, abstract = {Terminology is a critical instrument for each researcher. Different terminologies for the same research object may arise in different research communities. By this inconsistency, many synergistic effects get lost. Theories and models will be more understandable and reusable if a common terminology is applied. This paper examines the terminological (in)consistence for the research field of job-shop scheduling by a literature review. There is an enormous variety in the choice of terms and mathematical notation for the same concept. The comparability, reusability and combinability of scheduling methods is unnecessarily hampered by the arbitrary use of homonyms and synonyms. The acceptance in the community of used variables and notation forms is shown by means of a compliance quotient. This is proven by the evaluation of 240 scientific publications on planning methods.}, language = {en} } @article{RitterbuschTeichmann2023, author = {Ritterbusch, Georg David and Teichmann, Malte Rolf}, title = {Defining the metaverse}, series = {IEEE Access}, volume = {11}, journal = {IEEE Access}, publisher = {Institute of Electrical and Electronics Engineers}, address = {New York, NY}, issn = {2169-3536}, doi = {10.1109/ACCESS.2023.3241809}, pages = {12368 -- 12377}, year = {2023}, abstract = {The term Metaverse is emerging as a result of the late push by multinational technology conglomerates and a recent surge of interest in Web 3.0, Blockchain, NFT, and Cryptocurrencies. From a scientific point of view, there is no definite consensus on what the Metaverse will be like. This paper collects, analyzes, and synthesizes scientific definitions and the accompanying major characteristics of the Metaverse using the methodology of a Systematic Literature Review (SLR). Two revised definitions for the Metaverse are presented, both condensing the key attributes, where the first one is rather simplistic holistic describing "a three-dimensional online environment in which users represented by avatars interact with each other in virtual spaces decoupled from the real physical world". In contrast, the second definition is specified in a more detailed manner in the paper and further discussed. These comprehensive definitions offer specialized and general scholars an application within and beyond the scientific context of the system science, information system science, computer science, and business informatics, by also introducing open research challenges. Furthermore, an outlook on the social, economic, and technical implications is given, and the preconditions that are necessary for a successful implementation are discussed.}, language = {en} } @article{MarxStieglitzBruenkeretal.2023, author = {Marx, Julian and Stieglitz, Stefan and Br{\"u}nker, Felix and Mirbabaie, Milad}, title = {Home (office) is where your heart is}, series = {Business \& information systems engineering}, volume = {65}, journal = {Business \& information systems engineering}, number = {3}, publisher = {Springer Gabler}, address = {Wiesbaden}, issn = {2363-7005}, doi = {10.1007/s12599-023-00807-w}, pages = {293 -- 308}, year = {2023}, abstract = {Working conditions of knowledge workers have been subject to rapid change recently. Digital nomadism is no longer a phenomenon that relates only to entrepreneurs, freelancers, and gig workers. Corporate employees, too, have begun to uncouple their work from stationary (home) offices and 9-to-5 schedules. However, pursuing a permanent job in a corporate environment is still subject to fundamentally different values than postulated by the original notion of digital nomadism. Therefore, this paper explores the work identity of what is referred to as 'corporate nomads'. By drawing on identity theory and the results of semi-structured interviews, the paper proposes a conceptualization of the corporate nomad archetype and presents nine salient identity issues of corporate nomads (e.g., holding multiple contradictory identities, the flexibility paradox, or collaboration constraints). By introducing the 'corporate nomad' archetype to the Information Systems literature, this article helps to rethink established conceptions of "home office" and socio-spatial configurations of knowledge work.}, language = {en} } @article{HofeditzMirbabaieOrtmann2023, author = {Hofeditz, Lennart and Mirbabaie, Milad and Ortmann, Mara}, title = {Ethical challenges for human-agent interaction in virtual collaboration at work}, series = {International journal of human computer interaction}, journal = {International journal of human computer interaction}, publisher = {Taylor \& Francis}, address = {New York, NY}, issn = {1044-7318}, doi = {10.1080/10447318.2023.2279400}, pages = {17}, year = {2023}, abstract = {In virtual collaboration at the workplace, a growing number of teams apply supportive conversational agents (CAs). They take on different work-related tasks for teams and single users such as scheduling meetings or stimulating creativity. Previous research merely focused on these positive aspects of introducing CAs at the workplace, omitting ethical challenges faced by teams using these often artificial intelligence (AI)-enabled technologies. Thus, on the one hand, CAs can present themselves as benevolent teammates, but on the other hand, they can collect user data, reduce worker autonomy, or foster social isolation by their service. In this work, we conducted 15 expert interviews with senior researchers from the fields of ethics, collaboration, and computer science in order to derive ethical guidelines for introducing CAs in virtual team collaboration. We derived 14 guidelines and seven research questions to pave the way for future research on the dark sides of human-agent interaction in organizations.}, language = {en} } @article{BruenkerMarxMirbabaieetal.2023, author = {Br{\"u}nker, Felix and Marx, Julian and Mirbabaie, Milad and Stieglitz, Stefan}, title = {Proactive digital workplace transformation}, series = {Journal of information technology}, journal = {Journal of information technology}, publisher = {Sage Publishing}, address = {London}, issn = {0268-3962}, doi = {10.1177/02683962231219516}, pages = {19}, year = {2023}, abstract = {Digital transformation fundamentally changes the way individuals conduct work in organisations. In accordance with this statement, prevalent literature understands digital workplace transformation as a second-order effect of implementing new information technology to increase organisational effectiveness or reach other strategic goals. This paper, in contrast, provides empirical evidence from two remote-first organisations that undergo a proactive rather than reactive digital workplace transformation. The analysis of these cases suggests that new ways of working can be the consequence of an identity change that is a precondition for introducing new information technology rather than its outcome. The resulting process model contributes a competing argument to the existing debate in digital transformation literature. Instead of issuing digital workplace transformation as a deliverable of technological progress and strategic goals, this paper supports a notion of digital workplace transformation that serves a desired identity based on work preferences.}, language = {en} } @article{Draude2023, author = {Draude, Claude}, title = {Working with Diversity in Informatics}, series = {Hochschuldidaktik Informatik HDI 2021 (Commentarii informaticae didacticae)}, journal = {Hochschuldidaktik Informatik HDI 2021 (Commentarii informaticae didacticae)}, number = {13}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-548-4}, issn = {1868-0844}, doi = {10.25932/publishup-61378}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-613787}, pages = {13 -- 33}, year = {2023}, abstract = {Diversity is a term that is broadly used and challenging for informatics research, development and education. Diversity concerns may relate to unequal participation, knowledge and methodology, curricula, institutional planning etc. For a lot of these areas, measures, guidelines and best practices on diversity awareness exist. A systemic, sustainable impact of diversity measures on informatics is still largely missing. In this paper I explore what working with diversity and gender concepts in informatics entails, what the main challenges are and provide thoughts for improvement. The paper includes definitions of diversity and intersectionality, reflections on the disciplinary basis of informatics and practical implications of integrating diversity in informatics research and development. In the final part, two concepts from the social sciences and the humanities, the notion of "third space"/hybridity and the notion of "feminist ethics of care", serve as a lens to foster more sustainable ways of working with diversity in informatics.}, language = {en} } @article{GerstenbergerWinkelnkemperSchulte2023, author = {Gerstenberger, Dietrich and Winkelnkemper, Felix and Schulte, Carsten}, title = {Nutzung der Personas-Methode zum Umgang mit der Heterogenit{\"a}t von Informatikstudierenden}, series = {Hochschuldidaktik Informatik HDI 2021 (Commentarii informaticae didacticae)}, journal = {Hochschuldidaktik Informatik HDI 2021 (Commentarii informaticae didacticae)}, number = {13}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-548-4}, issn = {1868-0844}, doi = {10.25932/publishup-61568}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-615682}, pages = {117 -- 135}, year = {2023}, abstract = {Informatikstudieng{\"a}nge verzeichnen hohe Abbruchquoten innerhalb der ersten beiden Semester, die h{\"a}ufig mit Leistungsdefiziten oder Motivationsproblemen begr{\"u}ndet werden. Eine Ursache daf{\"u}r, dass trotz intensiver Bem{\"u}hungen um bessere Lehre und motivationsf{\"o}rdernde Maßnahmen diese Situation imWesentlichen unver{\"a}ndert bleibt, k{\"o}nnte darin liegen, dass nicht die eine Maßnahme oder der eine Ansatz das Problem im Ganzen l{\"o}sen kann, sondern dass eine heterogene Studierendenschaft vielmehr nach unterschiedlichen Maßnahmen verlangt. Bisher findet sich wenig Forschung zu differenzierten Studierendentypen in der Informatik. Wir stellen in dieser Arbeit einen Ansatz daf{\"u}r vor, die Heterogenit{\"a}t der Informatikstudierenden zu ergr{\"u}nden, und beschreiben die Ergebnisse erster Versuche mit diesem Ansatz. Um die große Anzahl von Studierenden auf eine {\"u}berschaubare Anzahl von Typen mit jeweils {\"a}hnlichen Bed{\"u}rfnissen und Erwartungen zu reduzieren, wird dazu die im Produktmanagement bew{\"a}hrte Personas-Methode adaptiert. Im Rahmen einer Befragung von 170 Informatikstudierenden konnten hierzu bereits einige Personas mit unterschiedlichen Merkmalsh{\"a}ufungen ausgearbeitet werden, die eine gute Grundlage darstellen, um auf dieser Basis differenzierte Interventionen zur F{\"o}rderung und Motivation der Informatikstudierenden zu entwickeln.}, language = {de} } @article{Bonorden2023, author = {Bonorden, Leif}, title = {Forschendes Lernen im Bachelorseminar „Software Engineering"}, series = {Hochschuldidaktik Informatik HDI 2021 (Commentarii informaticae didacticae)}, journal = {Hochschuldidaktik Informatik HDI 2021 (Commentarii informaticae didacticae)}, number = {13}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-548-4}, issn = {1868-0844}, doi = {10.25932/publishup-61600}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-616009}, pages = {213 -- 230}, year = {2023}, abstract = {Forschendes Lernen ist eine Lehr-Lernform, in der Studierende einen eigenen Forschungsprozess vollst{\"a}ndig durchlaufen. In Informatikstudieng{\"a}ngen und insbesondere in Informatikbachelorstudieng{\"a}ngen ist die Forschungsorientierung allerdings nur gering ausgepr{\"a}gt: Forschendes Lernen wird kaum eingesetzt, obwohl dies m{\"o}glich und sinnvoll ist. Dieser Artikel stellt ein Konzept f{\"u}r ein Seminar Software Engineering im Bachelorstudium vor und beschreibt dessen Durchf{\"u}hrung. Abschließend wird das Konzept diskutiert und sowohl aus Studierenden- als auch aus Lehrendensicht positiv evaluiert.}, language = {de} }