@phdthesis{Sakizloglou2023, author = {Sakizloglou, Lucas}, title = {Evaluating temporal queries over history-aware architectural runtime models}, doi = {10.25932/publishup-60439}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-604396}, school = {Universit{\"a}t Potsdam}, pages = {v, 168}, year = {2023}, abstract = {In model-driven engineering, the adaptation of large software systems with dynamic structure is enabled by architectural runtime models. Such a model represents an abstract state of the system as a graph of interacting components. Every relevant change in the system is mirrored in the model and triggers an evaluation of model queries, which search the model for structural patterns that should be adapted. This thesis focuses on a type of runtime models where the expressiveness of the model and model queries is extended to capture past changes and their timing. These history-aware models and temporal queries enable more informed decision-making during adaptation, as they support the formulation of requirements on the evolution of the pattern that should be adapted. However, evaluating temporal queries during adaptation poses significant challenges. First, it implies the capability to specify and evaluate requirements on the structure, as well as the ordering and timing in which structural changes occur. Then, query answers have to reflect that the history-aware model represents the architecture of a system whose execution may be ongoing, and thus answers may depend on future changes. Finally, query evaluation needs to be adequately fast and memory-efficient despite the increasing size of the history---especially for models that are altered by numerous, rapid changes. The thesis presents a query language and a querying approach for the specification and evaluation of temporal queries. These contributions aim to cope with the challenges of evaluating temporal queries at runtime, a prerequisite for history-aware architectural monitoring and adaptation which has not been systematically treated by prior model-based solutions. The distinguishing features of our contributions are: the specification of queries based on a temporal logic which encodes structural patterns as graphs; the provision of formally precise query answers which account for timing constraints and ongoing executions; the incremental evaluation which avoids the re-computation of query answers after each change; and the option to discard history that is no longer relevant to queries. The query evaluation searches the model for occurrences of a pattern whose evolution satisfies a temporal logic formula. Therefore, besides model-driven engineering, another related research community is runtime verification. The approach differs from prior logic-based runtime verification solutions by supporting the representation and querying of structure via graphs and graph queries, respectively, which is more efficient for queries with complex patterns. We present a prototypical implementation of the approach and measure its speed and memory consumption in monitoring and adaptation scenarios from two application domains, with executions of an increasing size. We assess scalability by a comparison to the state-of-the-art from both related research communities. The implementation yields promising results, which pave the way for sophisticated history-aware self-adaptation solutions and indicate that the approach constitutes a highly effective technique for runtime monitoring on an architectural level.}, language = {en} } @misc{SahlmannSchefflerSchnor2018, author = {Sahlmann, Kristina and Scheffler, Thomas and Schnor, Bettina}, title = {Ontology-driven Device Descriptions for IoT Network Management}, series = {2018 Global Internet of Things Summit (GIoTS)}, journal = {2018 Global Internet of Things Summit (GIoTS)}, publisher = {IEEE}, address = {New York}, isbn = {978-1-5386-6451-3}, doi = {10.1109/GIOTS.2018.8534569}, pages = {295 -- 300}, year = {2018}, abstract = {One particular challenge in the Internet of Things is the management of many heterogeneous things. The things are typically constrained devices with limited memory, power, network and processing capacity. Configuring every device manually is a tedious task. We propose an interoperable way to configure an IoT network automatically using existing standards. The proposed NETCONF-MQTT bridge intermediates between the constrained devices (speaking MQTT) and the network management standard NETCONF. The NETCONF-MQTT bridge generates dynamically YANG data models from the semantic description of the device capabilities based on the oneM2M ontology. We evaluate the approach for two use cases, i.e. describing an actuator and a sensor scenario.}, language = {en} } @article{RuetherSebodeLohseetal.2021, author = {R{\"u}ther, Ferenc Darius and Sebode, Marcial and Lohse, Ansgar W. and Wernicke, Sarah and B{\"o}ttinger, Erwin and Casar, Christian and Braun, Felix and Schramm, Christoph}, title = {Mobile app requirements for patients with rare liver diseases}, series = {Clinics and research in hepatology and gastroenterology}, volume = {45}, journal = {Clinics and research in hepatology and gastroenterology}, number = {6}, publisher = {Elsevier Masson}, address = {Amsterdam}, issn = {2210-7401}, doi = {10.1016/j.clinre.2021.101760}, pages = {10}, year = {2021}, abstract = {Background: More patient data are needed to improve research on rare liver diseases. Mobile health apps enable an exhaustive data collection. Therefore, the European Reference Network on Hepatological diseases (ERN RARE-LIVER) intends to implement an app for patients with rare liver diseases communicating with a patient registry, but little is known about which features patients and their healthcare providers regard as being useful. Aims: This study aimed to investigate how an app for rare liver diseases would be accepted, and to find out which features are considered useful. Methods: An anonymous survey was conducted on adult patients with rare liver diseases at a single academic, tertiary care outpatient-service. Additionally, medical experts of the ERN working group on autoimmune hepatitis were invited to participate in an online survey. Results: In total, the responses from 100 patients with autoimmune (n = 90) or other rare (n = 10) liver diseases and 32 experts were analyzed. Patients were convinced to use a disease specific app (80\%) and expected some benefit to their health (78\%) but responses differed signifi-cantly between younger and older patients (93\% vs. 62\%, p < 0.001; 88\% vs. 64\%, p < 0.01). Comparing patients' and experts' feedback, patients more often expected a simplified healthcare pathway (e.g. 89\% vs. 59\% (p < 0.001) wanted access to one's own medical records), while healthcare providers saw the benefit mainly in improving compliance and treatment outcome (e.g. 93\% vs. 31\% (p < 0.001) and 70\% vs. 21\% (p < 0.001) expected the app to reduce mistakes in taking medication and improve quality of life, respectively).}, language = {en} } @phdthesis{Roumen2023, author = {Roumen, Thijs}, title = {Portable models for laser cutting}, doi = {10.25932/publishup-57814}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-578141}, school = {Universit{\"a}t Potsdam}, pages = {xx, 170}, year = {2023}, abstract = {Laser cutting is a fast and precise fabrication process. This makes laser cutting a powerful process in custom industrial production. Since the patents on the original technology started to expire, a growing community of tech-enthusiasts embraced the technology and started sharing the models they fabricate online. Surprisingly, the shared models appear to largely be one-offs (e.g., they proudly showcase what a single person can make in one afternoon). For laser cutting to become a relevant mainstream phenomenon (as opposed to the current tech enthusiasts and industry users), it is crucial to enable users to reproduce models made by more experienced modelers, and to build on the work of others instead of creating one-offs. We create a technological basis that allows users to build on the work of others—a progression that is currently held back by the use of exchange formats that disregard mechanical differences between machines and therefore overlook implications with respect to how well parts fit together mechanically (aka engineering fit). For the field to progress, we need a machine-independent sharing infrastructure. In this thesis, we outline three approaches that together get us closer to this: (1) 2D cutting plans that are tolerant to machine variations. Our initial take is a minimally invasive approach: replacing machine-specific elements in cutting plans with more tolerant elements using mechanical hacks like springs and wedges. The resulting models fabricate on any consumer laser cutter and in a range of materials. (2) sharing models in 3D. To allow building on the work of others, we build a 3D modeling environment for laser cutting (kyub). After users design a model, they export their 3D models to 2D cutting plans optimized for the machine and material at hand. We extend this volumetric environment with tools to edit individual plates, allowing users to leverage the efficiency of volumetric editing while having control over the most detailed elements in laser-cutting (plates) (3) converting legacy 2D cutting plans to 3D models. To handle legacy models, we build software to interactively reconstruct 3D models from 2D cutting plans. This allows users to reuse the models in more productive ways. We revisit this by automating the assembly process for a large subset of models. The above-mentioned software composes a larger system (kyub, 140,000 lines of code). This system integration enables the push towards actual use, which we demonstrate through a range of workshops where users build complex models such as fully functional guitars. By simplifying sharing and re-use and the resulting increase in model complexity, this line of work forms a small step to enable personal fabrication to scale past the maker phenomenon, towards a mainstream phenomenon—the same way that other fields, such as print (postscript) and ultimately computing itself (portable programming languages, etc.) reached mass adoption.}, language = {en} } @phdthesis{Rothenberger2022, author = {Rothenberger, Ralf}, title = {Satisfiability thresholds for non-uniform random k-SAT}, doi = {10.25932/publishup-54970}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-549702}, school = {Universit{\"a}t Potsdam}, pages = {x, 163}, year = {2022}, abstract = {Boolean Satisfiability (SAT) is one of the problems at the core of theoretical computer science. It was the first problem proven to be NP-complete by Cook and, independently, by Levin. Nowadays it is conjectured that SAT cannot be solved in sub-exponential time. Thus, it is generally assumed that SAT and its restricted version k-SAT are hard to solve. However, state-of-the-art SAT solvers can solve even huge practical instances of these problems in a reasonable amount of time. Why is SAT hard in theory, but easy in practice? One approach to answering this question is investigating the average runtime of SAT. In order to analyze this average runtime the random k-SAT model was introduced. The model generates all k-SAT instances with n variables and m clauses with uniform probability. Researching random k-SAT led to a multitude of insights and tools for analyzing random structures in general. One major observation was the emergence of the so-called satisfiability threshold: A phase transition point in the number of clauses at which the generated formulas go from asymptotically almost surely satisfiable to asymptotically almost surely unsatisfiable. Additionally, instances around the threshold seem to be particularly hard to solve. In this thesis we analyze a more general model of random k-SAT that we call non-uniform random k-SAT. In contrast to the classical model each of the n Boolean variables now has a distinct probability of being drawn. For each of the m clauses we draw k variables according to the variable distribution and choose their signs uniformly at random. Non-uniform random k-SAT gives us more control over the distribution of Boolean variables in the resulting formulas. This allows us to tailor distributions to the ones observed in practice. Notably, non-uniform random k-SAT contains the previously proposed models random k-SAT, power-law random k-SAT and geometric random k-SAT as special cases. We analyze the satisfiability threshold in non-uniform random k-SAT depending on the variable probability distribution. Our goal is to derive conditions on this distribution under which an equivalent of the satisfiability threshold conjecture holds. We start with the arguably simpler case of non-uniform random 2-SAT. For this model we show under which conditions a threshold exists, if it is sharp or coarse, and what the leading constant of the threshold function is. These are exactly the three ingredients one needs in order to prove or disprove the satisfiability threshold conjecture. For non-uniform random k-SAT with k=3 we only prove sufficient conditions under which a threshold exists. We also show some properties of the variable probabilities under which the threshold is sharp in this case. These are the first results on the threshold behavior of non-uniform random k-SAT.}, 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} } @phdthesis{Rohloff2021, author = {Rohloff, Tobias}, title = {Learning analytics at scale}, doi = {10.25932/publishup-52623}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-526235}, school = {Universit{\"a}t Potsdam}, pages = {xvii, 138, lxvii}, year = {2021}, abstract = {Digital technologies are paving the way for innovative educational approaches. The learning format of Massive Open Online Courses (MOOCs) provides a highly accessible path to lifelong learning while being more affordable and flexible than face-to-face courses. Thereby, thousands of learners can enroll in courses mostly without admission restrictions, but this also raises challenges. Individual supervision by teachers is barely feasible, and learning persistence and success depend on students' self-regulatory skills. Here, technology provides the means for support. The use of data for decision-making is already transforming many fields, whereas in education, it is still a young research discipline. Learning Analytics (LA) is defined as the measurement, collection, analysis, and reporting of data about learners and their learning contexts with the purpose of understanding and improving learning and learning environments. The vast amount of data that MOOCs produce on the learning behavior and success of thousands of students provides the opportunity to study human learning and develop approaches addressing the demands of learners and teachers. The overall purpose of this dissertation is to investigate the implementation of LA at the scale of MOOCs and to explore how data-driven technology can support learning and teaching in this context. To this end, several research prototypes have been iteratively developed for the HPI MOOC Platform. Hence, they were tested and evaluated in an authentic real-world learning environment. Most of the results can be applied on a conceptual level to other MOOC platforms as well. The research contribution of this thesis thus provides practical insights beyond what is theoretically possible. In total, four system components were developed and extended: (1) The Learning Analytics Architecture: A technical infrastructure to collect, process, and analyze event-driven learning data based on schema-agnostic pipelining in a service-oriented MOOC platform. (2) The Learning Analytics Dashboard for Learners: A tool for data-driven support of self-regulated learning, in particular to enable learners to evaluate and plan their learning activities, progress, and success by themselves. (3) Personalized Learning Objectives: A set of features to better connect learners' success to their personal intentions based on selected learning objectives to offer guidance and align the provided data-driven insights about their learning progress. (4) The Learning Analytics Dashboard for Teachers: A tool supporting teachers with data-driven insights to enable the monitoring of their courses with thousands of learners, identify potential issues, and take informed action. For all aspects examined in this dissertation, related research is presented, development processes and implementation concepts are explained, and evaluations are conducted in case studies. Among other findings, the usage of the learner dashboard in combination with personalized learning objectives demonstrated improved certification rates of 11.62\% to 12.63\%. Furthermore, it was observed that the teacher dashboard is a key tool and an integral part for teaching in MOOCs. In addition to the results and contributions, general limitations of the work are discussed—which altogether provide a solid foundation for practical implications and future research.}, language = {en} } @misc{RischKrestel2018, author = {Risch, Julian and Krestel, Ralf}, title = {My Approach = Your Apparatus?}, series = {Libraries}, journal = {Libraries}, publisher = {Association for Computing Machinery}, address = {New York}, isbn = {978-1-4503-5178-2}, issn = {2575-7865}, doi = {10.1145/3197026.3197038}, pages = {283 -- 292}, year = {2018}, abstract = {Comparative text mining extends from genre analysis and political bias detection to the revelation of cultural and geographic differences, through to the search for prior art across patents and scientific papers. These applications use cross-collection topic modeling for the exploration, clustering, and comparison of large sets of documents, such as digital libraries. However, topic modeling on documents from different collections is challenging because of domain-specific vocabulary. We present a cross-collection topic model combined with automatic domain term extraction and phrase segmentation. This model distinguishes collection-specific and collection-independent words based on information entropy and reveals commonalities and differences of multiple text collections. We evaluate our model on patents, scientific papers, newspaper articles, forum posts, and Wikipedia articles. In comparison to state-of-the-art cross-collection topic modeling, our model achieves up to 13\% higher topic coherence, up to 4\% lower perplexity, and up to 31\% higher document classification accuracy. More importantly, our approach is the first topic model that ensures disjunct general and specific word distributions, resulting in clear-cut topic representations.}, language = {en} } @article{RischKrestel2019, author = {Risch, Julian and Krestel, Ralf}, title = {Domain-specific word embeddings for patent classification}, series = {Data Technologies and Applications}, volume = {53}, journal = {Data Technologies and Applications}, number = {1}, publisher = {Emerald Group Publishing Limited}, address = {Bingley}, issn = {2514-9288}, doi = {10.1108/DTA-01-2019-0002}, pages = {108 -- 122}, year = {2019}, abstract = {Purpose Patent offices and other stakeholders in the patent domain need to classify patent applications according to a standardized classification scheme. The purpose of this paper is to examine the novelty of an application it can then be compared to previously granted patents in the same class. Automatic classification would be highly beneficial, because of the large volume of patents and the domain-specific knowledge needed to accomplish this costly manual task. However, a challenge for the automation is patent-specific language use, such as special vocabulary and phrases. Design/methodology/approach To account for this language use, the authors present domain-specific pre-trained word embeddings for the patent domain. The authors train the model on a very large data set of more than 5m patents and evaluate it at the task of patent classification. To this end, the authors propose a deep learning approach based on gated recurrent units for automatic patent classification built on the trained word embeddings. Findings Experiments on a standardized evaluation data set show that the approach increases average precision for patent classification by 17 percent compared to state-of-the-art approaches. In this paper, the authors further investigate the model's strengths and weaknesses. An extensive error analysis reveals that the learned embeddings indeed mirror patent-specific language use. The imbalanced training data and underrepresented classes are the most difficult remaining challenge. Originality/value The proposed approach fulfills the need for domain-specific word embeddings for downstream tasks in the patent domain, such as patent classification or patent analysis.}, language = {en} } @article{RischKrestel2020, author = {Risch, Julian and Krestel, Ralf}, title = {Toxic comment detection in online discussions}, series = {Deep learning-based approaches for sentiment analysis}, journal = {Deep learning-based approaches for sentiment analysis}, editor = {Agarwal, Basant and Nayak, Richi and Mittal, Namita and Patnaik, Srikanta}, publisher = {Springer}, address = {Singapore}, isbn = {978-981-15-1216-2}, issn = {2524-7565}, doi = {10.1007/978-981-15-1216-2_4}, pages = {85 -- 109}, year = {2020}, abstract = {Comment sections of online news platforms are an essential space to express opinions and discuss political topics. In contrast to other online posts, news discussions are related to particular news articles, comments refer to each other, and individual conversations emerge. However, the misuse by spammers, haters, and trolls makes costly content moderation necessary. Sentiment analysis can not only support moderation but also help to understand the dynamics of online discussions. A subtask of content moderation is the identification of toxic comments. To this end, we describe the concept of toxicity and characterize its subclasses. Further, we present various deep learning approaches, including datasets and architectures, tailored to sentiment analysis in online discussions. One way to make these approaches more comprehensible and trustworthy is fine-grained instead of binary comment classification. On the downside, more classes require more training data. Therefore, we propose to augment training data by using transfer learning. We discuss real-world applications, such as semi-automated comment moderation and troll detection. Finally, we outline future challenges and current limitations in light of most recent research publications.}, language = {en} }