@article{ZieglerPfitznerSchulzetal.2022, author = {Ziegler, Joceline and Pfitzner, Bjarne and Schulz, Heinrich and Saalbach, Axel and Arnrich, Bert}, title = {Defending against Reconstruction Attacks through Differentially Private Federated Learning for Classification of Heterogeneous Chest X-ray Data}, series = {Sensors}, volume = {22}, journal = {Sensors}, edition = {14}, publisher = {MDPI}, address = {Basel, Schweiz}, issn = {1424-8220}, doi = {10.3390/s22145195}, pages = {25}, year = {2022}, abstract = {Privacy regulations and the physical distribution of heterogeneous data are often primary concerns for the development of deep learning models in a medical context. This paper evaluates the feasibility of differentially private federated learning for chest X-ray classification as a defense against data privacy attacks. To the best of our knowledge, we are the first to directly compare the impact of differentially private training on two different neural network architectures, DenseNet121 and ResNet50. Extending the federated learning environments previously analyzed in terms of privacy, we simulated a heterogeneous and imbalanced federated setting by distributing images from the public CheXpert and Mendeley chest X-ray datasets unevenly among 36 clients. Both non-private baseline models achieved an area under the receiver operating characteristic curve (AUC) of 0.940.94 on the binary classification task of detecting the presence of a medical finding. We demonstrate that both model architectures are vulnerable to privacy violation by applying image reconstruction attacks to local model updates from individual clients. The attack was particularly successful during later training stages. To mitigate the risk of a privacy breach, we integrated R{\´e}nyi differential privacy with a Gaussian noise mechanism into local model training. We evaluate model performance and attack vulnerability for privacy budgets ε∈{1,3,6,10}�∈{1,3,6,10}. The DenseNet121 achieved the best utility-privacy trade-off with an AUC of 0.940.94 for ε=6�=6. Model performance deteriorated slightly for individual clients compared to the non-private baseline. The ResNet50 only reached an AUC of 0.760.76 in the same privacy setting. Its performance was inferior to that of the DenseNet121 for all considered privacy constraints, suggesting that the DenseNet121 architecture is more robust to differentially private training.}, language = {en} } @misc{ZieglerPfitznerSchulzetal.2022, author = {Ziegler, Joceline and Pfitzner, Bjarne and Schulz, Heinrich and Saalbach, Axel and Arnrich, Bert}, title = {Defending against Reconstruction Attacks through Differentially Private Federated Learning for Classification of Heterogeneous Chest X-ray Data}, series = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t}, journal = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t}, number = {14}, doi = {10.25932/publishup-58132}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-581322}, pages = {25}, year = {2022}, abstract = {Privacy regulations and the physical distribution of heterogeneous data are often primary concerns for the development of deep learning models in a medical context. This paper evaluates the feasibility of differentially private federated learning for chest X-ray classification as a defense against data privacy attacks. To the best of our knowledge, we are the first to directly compare the impact of differentially private training on two different neural network architectures, DenseNet121 and ResNet50. Extending the federated learning environments previously analyzed in terms of privacy, we simulated a heterogeneous and imbalanced federated setting by distributing images from the public CheXpert and Mendeley chest X-ray datasets unevenly among 36 clients. Both non-private baseline models achieved an area under the receiver operating characteristic curve (AUC) of 0.940.94 on the binary classification task of detecting the presence of a medical finding. We demonstrate that both model architectures are vulnerable to privacy violation by applying image reconstruction attacks to local model updates from individual clients. The attack was particularly successful during later training stages. To mitigate the risk of a privacy breach, we integrated R{\´e}nyi differential privacy with a Gaussian noise mechanism into local model training. We evaluate model performance and attack vulnerability for privacy budgets ε∈{1,3,6,10}�∈{1,3,6,10}. The DenseNet121 achieved the best utility-privacy trade-off with an AUC of 0.940.94 for ε=6�=6. Model performance deteriorated slightly for individual clients compared to the non-private baseline. The ResNet50 only reached an AUC of 0.760.76 in the same privacy setting. Its performance was inferior to that of the DenseNet121 for all considered privacy constraints, suggesting that the DenseNet121 architecture is more robust to differentially private training.}, language = {en} } @misc{ZennerBoettingerKonigorski2022, author = {Zenner, Alexander M. and B{\"o}ttinger, Erwin and Konigorski, Stefan}, title = {StudyMe}, series = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t}, journal = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t}, number = {18}, doi = {10.25932/publishup-58976}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-589763}, pages = {15}, year = {2022}, abstract = {N-of-1 trials are multi-crossover self-experiments that allow individuals to systematically evaluate the effect of interventions on their personal health goals. Although several tools for N-of-1 trials exist, there is a gap in supporting non-experts in conducting their own user-centric trials. In this study, we present StudyMe, an open-source mobile application that is freely available from https://play.google.com/store/apps/details?id=health.studyu.me and offers users flexibility and guidance in configuring every component of their trials. We also present research that informed the development of StudyMe, focusing on trial creation. Through an initial survey with 272 participants, we learned that individuals are interested in a variety of personal health aspects and have unique ideas on how to improve them. In an iterative, user-centered development process with intermediate user tests, we developed StudyMe that features an educational part to communicate N-of-1 trial concepts. A final empirical evaluation of StudyMe showed that all participants were able to create their own trials successfully using StudyMe and the app achieved a very good usability rating. Our findings suggest that StudyMe provides a significant step towards enabling individuals to apply a systematic science-oriented approach to personalize health-related interventions and behavior modifications in their everyday lives.}, language = {en} } @article{ZennerBoettingerKonigorski2022, author = {Zenner, Alexander M. and B{\"o}ttinger, Erwin and Konigorski, Stefan}, title = {StudyMe}, series = {Trials}, volume = {23}, journal = {Trials}, publisher = {BioMed Central}, address = {London}, issn = {1745-6215}, doi = {10.1186/s13063-022-06893-7}, pages = {15}, year = {2022}, abstract = {N-of-1 trials are multi-crossover self-experiments that allow individuals to systematically evaluate the effect of interventions on their personal health goals. Although several tools for N-of-1 trials exist, there is a gap in supporting non-experts in conducting their own user-centric trials. In this study, we present StudyMe, an open-source mobile application that is freely available from https://play.google.com/store/apps/details?id=health.studyu.me and offers users flexibility and guidance in configuring every component of their trials. We also present research that informed the development of StudyMe, focusing on trial creation. Through an initial survey with 272 participants, we learned that individuals are interested in a variety of personal health aspects and have unique ideas on how to improve them. In an iterative, user-centered development process with intermediate user tests, we developed StudyMe that features an educational part to communicate N-of-1 trial concepts. A final empirical evaluation of StudyMe showed that all participants were able to create their own trials successfully using StudyMe and the app achieved a very good usability rating. Our findings suggest that StudyMe provides a significant step towards enabling individuals to apply a systematic science-oriented approach to personalize health-related interventions and behavior modifications in their everyday lives.}, 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{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{TangNakamotoSternetal.2022, author = {Tang, Mitchell and Nakamoto, Carter H. and Stern, Ariel Dora and Mehrotra, Ateev}, title = {Trends in remote patient monitoring use in traditional Medicare}, series = {JAMA Internal Medicine}, volume = {182}, journal = {JAMA Internal Medicine}, number = {9}, publisher = {American Veterinary Medical Association}, address = {Chicago}, issn = {2168-6106}, doi = {10.1001/jamainternmed.2022.3043}, pages = {1005 -- 1006}, year = {2022}, abstract = {This cross-sectional study uses traditional Medicare claims data to assess trends in general remote patient monitoring from January 2018 through September 2021.}, language = {en} } @phdthesis{Sukmana2022, author = {Sukmana, Muhammad Ihsan Haikal}, title = {Security improvements for enterprise file sychronization and sharing system}, doi = {10.25932/publishup-54999}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-549996}, school = {Universit{\"a}t Potsdam}, pages = {xi, 213}, year = {2022}, abstract = {With the fast rise of cloud computing adoption in the past few years, more companies are migrating their confidential files from their private data center to the cloud to help enterprise's digital transformation process. Enterprise file synchronization and share (EFSS) is one of the solutions offered for enterprises to store their files in the cloud with secure and easy file sharing and collaboration between its employees. However, the rapidly increasing number of cyberattacks on the cloud might target company's files on the cloud to be stolen or leaked to the public. It is then the responsibility of the EFSS system to ensure the company's confidential files to only be accessible by authorized employees. CloudRAID is a secure personal cloud storage research collaboration project that provides data availability and confidentiality in the cloud. It combines erasure and cryptographic techniques to securely store files as multiple encrypted file chunks in various cloud service providers (CSPs). However, several aspects of CloudRAID's concept are unsuitable for secure and scalable enterprise cloud storage solutions, particularly key management system, location-based access control, multi-cloud storage management, and cloud file access monitoring. This Ph.D. thesis focuses on CloudRAID for Business (CfB) as it resolves four main challenges of CloudRAID's concept for a secure and scalable EFSS system. First, the key management system is implemented using the attribute-based encryption scheme to provide secure and scalable intra-company and inter-company file-sharing functionalities. Second, an Internet-based location file access control functionality is introduced to ensure files could only be accessed at pre-determined trusted locations. Third, a unified multi-cloud storage resource management framework is utilized to securely manage cloud storage resources available in various CSPs for authorized CfB stakeholders. Lastly, a multi-cloud storage monitoring system is introduced to monitor the activities of files in the cloud using the generated cloud storage log files from multiple CSPs. In summary, this thesis helps CfB system to provide holistic security for company's confidential files on the cloud-level, system-level, and file-level to ensure only authorized company and its employees could access the files.}, language = {en} } @article{ShamsWangRoineetal.2022, author = {Shams, Boshra and Wang, Ziqian and Roine, Timo and Aydogan, Dogu Baran and Vajkoczy, Peter and Lippert, Christoph and Picht, Thomas and Fekonja, Lucius Samo}, title = {Machine learning-based prediction of motor status in glioma patients using diffusion MRI metrics along the corticospinal tract}, series = {Brain communications}, volume = {4}, journal = {Brain communications}, number = {3}, publisher = {Oxford University Press}, address = {Oxford}, issn = {2632-1297}, doi = {10.1093/braincomms/fcac141}, pages = {17}, year = {2022}, abstract = {Shams et al. report that glioma patients' motor status is predicted accurately by diffusion MRI metrics along the corticospinal tract based on support vector machine method, reaching an overall accuracy of 77\%. They show that these metrics are more effective than demographic and clinical variables. Along tract statistics enables white matter characterization using various diffusion MRI metrics. These diffusion models reveal detailed insights into white matter microstructural changes with development, pathology and function. Here, we aim at assessing the clinical utility of diffusion MRI metrics along the corticospinal tract, investigating whether motor glioma patients can be classified with respect to their motor status. We retrospectively included 116 brain tumour patients suffering from either left or right supratentorial, unilateral World Health Organization Grades II, III and IV gliomas with a mean age of 53.51 +/- 16.32 years. Around 37\% of patients presented with preoperative motor function deficits according to the Medical Research Council scale. At group level comparison, the highest non-overlapping diffusion MRI differences were detected in the superior portion of the tracts' profiles. Fractional anisotropy and fibre density decrease, apparent diffusion coefficient axial diffusivity and radial diffusivity increase. To predict motor deficits, we developed a method based on a support vector machine using histogram-based features of diffusion MRI tract profiles (e.g. mean, standard deviation, kurtosis and skewness), following a recursive feature elimination method. Our model achieved high performance (74\% sensitivity, 75\% specificity, 74\% overall accuracy and 77\% area under the curve). We found that apparent diffusion coefficient, fractional anisotropy and radial diffusivity contributed more than other features to the model. Incorporating the patient demographics and clinical features such as age, tumour World Health Organization grade, tumour location, gender and resting motor threshold did not affect the model's performance, revealing that these features were not as effective as microstructural measures. These results shed light on the potential patterns of tumour-related microstructural white matter changes in the prediction of functional deficits.}, language = {en} } @misc{SerthStaubitzvanEltenetal.2022, author = {Serth, Sebastian and Staubitz, Thomas and van Elten, Martin and Meinel, Christoph}, title = {Measuring the effects of course modularizations in online courses for life-long learners}, series = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t}, journal = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t}, number = {17}, editor = {Gamage, Dilrukshi}, doi = {10.25932/publishup-58918}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-589182}, pages = {15}, year = {2022}, abstract = {Many participants in Massive Open Online Courses are full-time employees seeking greater flexibility in their time commitment and the available learning paths. We recently addressed these requirements by splitting up our 6-week courses into three 2-week modules followed by a separate exam. Modularizing courses offers many advantages: Shorter modules are more sustainable and can be combined, reused, and incorporated into learning paths more easily. Time flexibility for learners is also improved as exams can now be offered multiple times per year, while the learning content is available independently. In this article, we answer the question of which impact this modularization has on key learning metrics, such as course completion rates, learning success, and no-show rates. Furthermore, we investigate the influence of longer breaks between modules on these metrics. According to our analysis, course modules facilitate more selective learning behaviors that encourage learners to focus on topics they are the most interested in. At the same time, participation in overarching exams across all modules seems to be less appealing compared to an integrated exam of a 6-week course. While breaks between the modules increase the distinctive appearance of individual modules, a break before the final exam further reduces initial interest in the exams. We further reveal that participation in self-paced courses as a preparation for the final exam is unlikely to attract new learners to the course offerings, even though learners' performance is comparable to instructor-paced courses. The results of our long-term study on course modularization provide a solid foundation for future research and enable educators to make informed decisions about the design of their courses.}, language = {en} } @article{SerthStaubitzvanEltenetal.2022, author = {Serth, Sebastian and Staubitz, Thomas and van Elten, Martin and Meinel, Christoph}, title = {Measuring the effects of course modularizations in online courses for life-long learners}, series = {Frontiers in Education}, volume = {7}, journal = {Frontiers in Education}, editor = {Gamage, Dilrukshi}, publisher = {Frontiers}, address = {Lausanne, Schweiz}, issn = {2504-284X}, doi = {10.3389/feduc.2022.1008545}, pages = {15}, year = {2022}, abstract = {Many participants in Massive Open Online Courses are full-time employees seeking greater flexibility in their time commitment and the available learning paths. We recently addressed these requirements by splitting up our 6-week courses into three 2-week modules followed by a separate exam. Modularizing courses offers many advantages: Shorter modules are more sustainable and can be combined, reused, and incorporated into learning paths more easily. Time flexibility for learners is also improved as exams can now be offered multiple times per year, while the learning content is available independently. In this article, we answer the question of which impact this modularization has on key learning metrics, such as course completion rates, learning success, and no-show rates. Furthermore, we investigate the influence of longer breaks between modules on these metrics. According to our analysis, course modules facilitate more selective learning behaviors that encourage learners to focus on topics they are the most interested in. At the same time, participation in overarching exams across all modules seems to be less appealing compared to an integrated exam of a 6-week course. While breaks between the modules increase the distinctive appearance of individual modules, a break before the final exam further reduces initial interest in the exams. We further reveal that participation in self-paced courses as a preparation for the final exam is unlikely to attract new learners to the course offerings, even though learners' performance is comparable to instructor-paced courses. The results of our long-term study on course modularization provide a solid foundation for future research and enable educators to make informed decisions about the design of their courses.}, language = {en} } @book{SchneiderMaximovaGiese2022, author = {Schneider, Sven and Maximova, Maria and Giese, Holger}, title = {Invariant Analysis for Multi-Agent Graph Transformation Systems using k-Induction}, number = {143}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-531-6}, issn = {1613-5652}, doi = {10.25932/publishup-54585}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-545851}, publisher = {Universit{\"a}t Potsdam}, pages = {37}, year = {2022}, abstract = {The analysis of behavioral models such as Graph Transformation Systems (GTSs) is of central importance in model-driven engineering. However, GTSs often result in intractably large or even infinite state spaces and may be equipped with multiple or even infinitely many start graphs. To mitigate these problems, static analysis techniques based on finite symbolic representations of sets of states or paths thereof have been devised. We focus on the technique of k-induction for establishing invariants specified using graph conditions. To this end, k-induction generates symbolic paths backwards from a symbolic state representing a violation of a candidate invariant to gather information on how that violation could have been reached possibly obtaining contradictions to assumed invariants. However, GTSs where multiple agents regularly perform actions independently from each other cannot be analyzed using this technique as of now as the independence among backward steps may prevent the gathering of relevant knowledge altogether. In this paper, we extend k-induction to GTSs with multiple agents thereby supporting a wide range of additional GTSs. As a running example, we consider an unbounded number of shuttles driving on a large-scale track topology, which adjust their velocity to speed limits to avoid derailing. As central contribution, we develop pruning techniques based on causality and independence among backward steps and verify that k-induction remains sound under this adaptation as well as terminates in cases where it did not terminate before.}, language = {en} } @book{SchneiderMaximovaGiese2022, author = {Schneider, Sven and Maximova, Maria and Giese, Holger}, title = {Probabilistic metric temporal graph logic}, number = {146}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-532-3}, issn = {1613-5652}, doi = {10.25932/publishup-54586}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-545867}, publisher = {Universit{\"a}t Potsdam}, pages = {34}, year = {2022}, abstract = {Cyber-physical systems often encompass complex concurrent behavior with timing constraints and probabilistic failures on demand. The analysis whether such systems with probabilistic timed behavior adhere to a given specification is essential. When the states of the system can be represented by graphs, the rule-based formalism of Probabilistic Timed Graph Transformation Systems (PTGTSs) can be used to suitably capture structure dynamics as well as probabilistic and timed behavior of the system. The model checking support for PTGTSs w.r.t. properties specified using Probabilistic Timed Computation Tree Logic (PTCTL) has been already presented. Moreover, for timed graph-based runtime monitoring, Metric Temporal Graph Logic (MTGL) has been developed for stating metric temporal properties on identified subgraphs and their structural changes over time. In this paper, we (a) extend MTGL to the Probabilistic Metric Temporal Graph Logic (PMTGL) by allowing for the specification of probabilistic properties, (b) adapt our MTGL satisfaction checking approach to PTGTSs, and (c) combine the approaches for PTCTL model checking and MTGL satisfaction checking to obtain a Bounded Model Checking (BMC) approach for PMTGL. In our evaluation, we apply an implementation of our BMC approach in AutoGraph to a running example.}, language = {en} } @phdthesis{Schirneck2022, author = {Schirneck, Friedrich Martin}, title = {Enumeration algorithms in data profiling}, doi = {10.25932/publishup-55672}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-556726}, school = {Universit{\"a}t Potsdam}, pages = {xiv, 192}, year = {2022}, abstract = {Data profiling is the extraction of metadata from relational databases. An important class of metadata are multi-column dependencies. They come associated with two computational tasks. The detection problem is to decide whether a dependency of a given type and size holds in a database. The discovery problem instead asks to enumerate all valid dependencies of that type. We investigate the two problems for three types of dependencies: unique column combinations (UCCs), functional dependencies (FDs), and inclusion dependencies (INDs). We first treat the parameterized complexity of the detection variants. We prove that the detection of UCCs and FDs, respectively, is W[2]-complete when parameterized by the size of the dependency. The detection of INDs is shown to be one of the first natural W[3]-complete problems. We further settle the enumeration complexity of the three discovery problems by presenting parsimonious equivalences with well-known enumeration problems. Namely, the discovery of UCCs is equivalent to the famous transversal hypergraph problem of enumerating the hitting sets of a hypergraph. The discovery of FDs is equivalent to the simultaneous enumeration of the hitting sets of multiple input hypergraphs. Finally, the discovery of INDs is shown to be equivalent to enumerating the satisfying assignments of antimonotone, 3-normalized Boolean formulas. In the remainder of the thesis, we design and analyze discovery algorithms for unique column combinations. Since this is as hard as the general transversal hypergraph problem, it is an open question whether the UCCs of a database can be computed in output-polynomial time in the worst case. For the analysis, we therefore focus on instances that are structurally close to databases in practice, most notably, inputs that have small solutions. The equivalence between UCCs and hitting sets transfers the computational hardness, but also allows us to apply ideas from hypergraph theory to data profiling. We devise an discovery algorithm that runs in polynomial space on arbitrary inputs and achieves polynomial delay whenever the maximum size of any minimal UCC is bounded. Central to our approach is the extension problem for minimal hitting sets, that is, to decide for a set of vertices whether they are contained in any minimal solution. We prove that this is yet another problem that is complete for the complexity class W[3], when parameterized by the size of the set that is to be extended. We also give several conditional lower bounds under popular hardness conjectures such as the Strong Exponential Time Hypothesis (SETH). The lower bounds suggest that the running time of our algorithm for the extension problem is close to optimal. We further conduct an empirical analysis of our discovery algorithm on real-world databases to confirm that the hitting set perspective on data profiling has merits also in practice. We show that the resulting enumeration times undercut their theoretical worst-case bounds on practical data, and that the memory consumption of our method is much smaller than that of previous solutions. During the analysis we make two observations about the connection between databases and their corresponding hypergraphs. On the one hand, the hypergraph representations containing all relevant information are usually significantly smaller than the original inputs. On the other hand, obtaining those hypergraphs is the actual bottleneck of any practical application. The latter often takes much longer than enumerating the solutions, which is in stark contrast to the fact that the preprocessing is guaranteed to be polynomial while the enumeration may take exponential time. To make the first observation rigorous, we introduce a maximum-entropy model for non-uniform random hypergraphs and prove that their expected number of minimal hyperedges undergoes a phase transition with respect to the total number of edges. The result also explains why larger databases may have smaller hypergraphs. Motivated by the second observation, we present a new kind of UCC discovery algorithm called Hitting Set Enumeration with Partial Information and Validation (HPIValid). It utilizes the fast enumeration times in practice in order to speed up the computation of the corresponding hypergraph. This way, we sidestep the bottleneck while maintaining the advantages of the hitting set perspective. An exhaustive empirical evaluation shows that HPIValid outperforms the current state of the art in UCC discovery. It is capable of processing databases that were previously out of reach for data profiling.}, language = {en} } @article{RuiperezValienteStaubitzJenneretal.2022, author = {Ruip{\´e}rez-Valiente, Jos{\´e} A. and Staubitz, Thomas and Jenner, Matt and Halawa, Sherif and Zhang, Jiayin and Despujol, Ignacio and Maldonado-Mahauad, Jorge and Montoro, German and Peffer, Melanie and Rohloff, Tobias and Lane, Jenny and Turro, Carlos and Li, Xitong and P{\´e}rez-Sanagust{\´i}n, Mar and Reich, Justin}, title = {Large scale analytics of global and regional MOOC providers: Differences in learners' demographics, preferences, and perceptions}, series = {Computers \& education}, volume = {180}, journal = {Computers \& education}, publisher = {Elsevier}, address = {Oxford}, issn = {0360-1315}, doi = {10.1016/j.compedu.2021.104426}, pages = {17}, year = {2022}, abstract = {Massive Open Online Courses (MOOCs) remarkably attracted global media attention, but the spotlight has been concentrated on a handful of English-language providers. While Coursera, edX, Udacity, and FutureLearn received most of the attention and scrutiny, an entirely new ecosystem of local MOOC providers was growing in parallel. This ecosystem is harder to study than the major players: they are spread around the world, have less staff devoted to maintaining research data, and operate in multiple languages with university and corporate regional partners. To better understand how online learning opportunities are expanding through this regional MOOC ecosystem, we created a research partnership among 15 different MOOC providers from nine countries. We gathered data from over eight million learners in six thousand MOOCs, and we conducted a large-scale survey with more than 10 thousand participants. From our analysis, we argue that these regional providers may be better positioned to meet the goals of expanding access to higher education in their regions than the better-known global providers. To make this claim we highlight three trends: first, regional providers attract a larger local population with more inclusive demographic profiles; second, students predominantly choose their courses based on topical interest, and regional providers do a better job at catering to those needs; and third, many students feel more at ease learning from institutions they already know and have references from. Our work raises the importance of local education in the global MOOC ecosystem, while calling for additional research and conversations across the diversity of MOOC providers.}, 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} } @article{RingEisenmannKandiletal.2022, author = {Ring, Raphaela M. and Eisenmann, Clemens and Kandil, Farid and Steckhan, Nico and Demmrich, Sarah and Klatte, Caroline and Kessler, Christian S. and Jeitler, Michael and Boschmann, Michael and Michalsen, Andreas and Blakeslee, Sarah B. and St{\"o}ckigt, Barbara and Stritter, Wiebke and Koppold-Liebscher, Daniela A.}, title = {Mental and behavioural responses to Bah{\´a}'{\´i} fasting: Looking behind the scenes of a religiously motivated intermittent fast using a mixed methods approach}, series = {Nutrients}, volume = {14}, journal = {Nutrients}, number = {5}, publisher = {MDPI}, address = {Basel}, issn = {2072-6643}, doi = {10.3390/nu14051038}, pages = {23}, year = {2022}, abstract = {Background/Objective: Historically, fasting has been practiced not only for medical but also for religious reasons. Baha'is follow an annual religious intermittent dry fast of 19 days. We inquired into motivation behind and subjective health impacts of Baha'i fasting. Methods: A convergent parallel mixed methods design was embedded in a clinical single arm observational study. Semi-structured individual interviews were conducted before (n = 7), during (n = 8), and after fasting (n = 8). Three months after the fasting period, two focus group interviews were conducted (n = 5/n = 3). A total of 146 Baha'i volunteers answered an online survey at five time points before, during, and after fasting. Results: Fasting was found to play a central role for the religiosity of interviewees, implying changes in daily structures, spending time alone, engaging in religious practices, and experiencing social belonging. Results show an increase in mindfulness and well-being, which were accompanied by behavioural changes and experiences of self-efficacy and inner freedom. Survey scores point to an increase in mindfulness and well-being during fasting, while stress, anxiety, and fatigue decreased. Mindfulness remained elevated even three months after the fast. Conclusion: Baha'i fasting seems to enhance participants' mindfulness and well-being, lowering stress levels and reducing fatigue. Some of these effects lasted more than three months after fasting.}, 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} }