@misc{BensonMakaitRabl2021, author = {Benson, Lawrence and Makait, Hendrik and Rabl, Tilmann}, title = {Viper}, 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 = {9}, issn = {2150-8097}, doi = {10.25932/publishup-55966}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-559664}, pages = {15}, 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} } @misc{KruseKaoudiContrerasRojasetal.2020, author = {Kruse, Sebastian and Kaoudi, Zoi and Contreras-Rojas, Bertty and Chawla, Sanjay and Naumann, Felix and Quian{\´e}-Ruiz, Jorge-Arnulfo}, title = {RHEEMix in the data jungle}, 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 = {6}, doi = {10.25932/publishup-51944}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-519443}, pages = {26}, year = {2020}, abstract = {Data analytics are moving beyond the limits of a single platform. In this paper, we present the cost-based optimizer of Rheem, an open-source cross-platform system that copes with these new requirements. The optimizer allocates the subtasks of data analytic tasks to the most suitable platforms. Our main contributions are: (i) a mechanism based on graph transformations to explore alternative execution strategies; (ii) a novel graph-based approach to determine efficient data movement plans among subtasks and platforms; and (iii) an efficient plan enumeration algorithm, based on a novel enumeration algebra. We extensively evaluate our optimizer under diverse real tasks. We show that our optimizer can perform tasks more than one order of magnitude faster when using multiple platforms than when using a single platform.}, language = {en} } @misc{GorskiJungLietal.2020, author = {Gorski, Mathias and Jung, Bettina and Li, Yong and Matias-Garcia, Pamela R. and Wuttke, Matthias and Coassin, Stefan and Thio, Chris H. L. and Kleber, Marcus E. and Winkler, Thomas W. and Wanner, Veronika and Chai, Jin-Fang and Chu, Audrey Y. and Cocca, Massimiliano and Feitosa, Mary F. and Ghasemi, Sahar and Hoppmann, Anselm and Horn, Katrin and Li, Man and Nutile, Teresa and Scholz, Markus and Sieber, Karsten B. and Teumer, Alexander and Tin, Adrienne and Wang, Judy and Tayo, Bamidele O. and Ahluwalia, Tarunveer S. and Almgren, Peter and Bakker, Stephan J. L. and Banas, Bernhard and Bansal, Nisha and Biggs, Mary L. and Boerwinkle, Eric and B{\"o}ttinger, Erwin and Brenner, Hermann and Carroll, Robert J. and Chalmers, John and Chee, Miao-Li and Chee, Miao-Ling and Cheng, Ching-Yu and Coresh, Josef and de Borst, Martin H. and Degenhardt, Frauke and Eckardt, Kai-Uwe and Endlich, Karlhans and Franke, Andre and Freitag-Wolf, Sandra and Gampawar, Piyush and Gansevoort, Ron T. and Ghanbari, Mohsen and Gieger, Christian and Hamet, Pavel and Ho, Kevin and Hofer, Edith and Holleczek, Bernd and Foo, Valencia Hui Xian and Hutri-Kahonen, Nina and Hwang, Shih-Jen and Ikram, M. Arfan and Josyula, Navya Shilpa and Kahonen, Mika and Khor, Chiea-Chuen and Koenig, Wolfgang and Kramer, Holly and Kraemer, Bernhard K. and Kuehnel, Brigitte and Lange, Leslie A. and Lehtimaki, Terho and Lieb, Wolfgang and Loos, Ruth J. F. and Lukas, Mary Ann and Lyytikainen, Leo-Pekka and Meisinger, Christa and Meitinger, Thomas and Melander, Olle and Milaneschi, Yuri and Mishra, Pashupati P. and Mononen, Nina and Mychaleckyj, Josyf C. and Nadkarni, Girish N. and Nauck, Matthias and Nikus, Kjell and Ning, Boting and Nolte, Ilja M. and O'Donoghue, Michelle L. and Orho-Melander, Marju and Pendergrass, Sarah A. and Penninx, Brenda W. J. H. and Preuss, Michael H. and Psaty, Bruce M. and Raffield, Laura M. and Raitakari, Olli T. and Rettig, Rainer and Rheinberger, Myriam and Rice, Kenneth M. and Rosenkranz, Alexander R. and Rossing, Peter and Rotter, Jerome and Sabanayagam, Charumathi and Schmidt, Helena and Schmidt, Reinhold and Schoettker, Ben and Schulz, Christina-Alexandra and Sedaghat, Sanaz and Shaffer, Christian M. and Strauch, Konstantin and Szymczak, Silke and Taylor, Kent D. and Tremblay, Johanne and Chaker, Layal and van der Harst, Pim and van der Most, Peter J. and Verweij, Niek and Voelker, Uwe and Waldenberger, Melanie and Wallentin, Lars and Waterworth, Dawn M. and White, Harvey D. and Wilson, James G. and Wong, Tien-Yin and Woodward, Mark and Yang, Qiong and Yasuda, Masayuki and Yerges-Armstrong, Laura M. and Zhang, Yan and Snieder, Harold and Wanner, Christoph and Boger, Carsten A. and Kottgen, Anna and Kronenberg, Florian and Pattaro, Cristian and Heid, Iris M.}, title = {Meta-analysis uncovers genome-wide significant variants for rapid kidney function decline}, 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 = {19}, doi = {10.25932/publishup-56537}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-565379}, pages = {14}, year = {2020}, abstract = {Rapid decline of glomerular filtration rate estimated from creatinine (eGFRcrea) is associated with severe clinical endpoints. In contrast to cross-sectionally assessed eGFRcrea, the genetic basis for rapid eGFRcrea decline is largely unknown. To help define this, we meta-analyzed 42 genome-wide association studies from the Chronic Kidney Diseases Genetics Consortium and United Kingdom Biobank to identify genetic loci for rapid eGFRcrea decline. Two definitions of eGFRcrea decline were used: 3 mL/min/1.73m(2)/year or more ("Rapid3"; encompassing 34,874 cases, 107,090 controls) and eGFRcrea decline 25\% or more and eGFRcrea under 60 mL/min/1.73m(2) at follow-up among those with eGFRcrea 60 mL/min/1.73m(2) or more at baseline ("CKDi25"; encompassing 19,901 cases, 175,244 controls). Seven independent variants were identified across six loci for Rapid3 and/or CKDi25: consisting of five variants at four loci with genome-wide significance (near UMOD-PDILT (2), PRKAG2, WDR72, OR2S2) and two variants among 265 known eGFRcrea variants (near GATM, LARP4B). All these loci were novel for Rapid3 and/or CKDi25 and our bioinformatic follow-up prioritized variants and genes underneath these loci. The OR2S2 locus is novel for any eGFRcrea trait including interesting candidates. For the five genome-wide significant lead variants, we found supporting effects for annual change in blood urea nitrogen or cystatin-based eGFR, but not for GATM or (LARP4B). Individuals at high compared to those at low genetic risk (8-14 vs. 0-5 adverse alleles) had a 1.20-fold increased risk of acute kidney injury (95\% confidence interval 1.08-1.33). Thus, our identified loci for rapid kidney function decline may help prioritize therapeutic targets and identify mechanisms and individuals at risk for sustained deterioration of kidney function.}, 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} } @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} } @misc{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 = {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 = {16}, doi = {10.25932/publishup-58607}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-586078}, 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} } @misc{FehrJaramilloGutierrezOalaetal.2022, author = {Fehr, Jana and Jaramillo-Gutierrez, Giovanna and Oala, Luis and Gr{\"o}schel, Matthias I. and Bierwirth, Manuel and Balachandran, Pradeep and Werneck-Leite, Alixandro and Lippert, Christoph}, title = {Piloting a Survey-Based Assessment of Transparency and Trustworthiness with Three Medical AI Tools}, 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 = {15}, doi = {10.25932/publishup-58328}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-583281}, pages = {30}, year = {2022}, abstract = {Artificial intelligence (AI) offers the potential to support healthcare delivery, but poorly trained or validated algorithms bear risks of harm. Ethical guidelines stated transparency about model development and validation as a requirement for trustworthy AI. Abundant guidance exists to provide transparency through reporting, but poorly reported medical AI tools are common. To close this transparency gap, we developed and piloted a framework to quantify the transparency of medical AI tools with three use cases. Our framework comprises a survey to report on the intended use, training and validation data and processes, ethical considerations, and deployment recommendations. The transparency of each response was scored with either 0, 0.5, or 1 to reflect if the requested information was not, partially, or fully provided. Additionally, we assessed on an analogous three-point scale if the provided responses fulfilled the transparency requirement for a set of trustworthiness criteria from ethical guidelines. The degree of transparency and trustworthiness was calculated on a scale from 0\% to 100\%. Our assessment of three medical AI use cases pin-pointed reporting gaps and resulted in transparency scores of 67\% for two use cases and one with 59\%. We report anecdotal evidence that business constraints and limited information from external datasets were major obstacles to providing transparency for the three use cases. The observed transparency gaps also lowered the degree of trustworthiness, indicating compliance gaps with ethical guidelines. All three pilot use cases faced challenges to provide transparency about medical AI tools, but more studies are needed to investigate those in the wider medical AI sector. Applying this framework for an external assessment of transparency may be infeasible if business constraints prevent the disclosure of information. New strategies may be necessary to enable audits of medical AI tools while preserving business secrets.}, 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{HeckerSteckhanEybenetal.2022, author = {Hecker, Pascal and Steckhan, Nico and Eyben, Florian and Schuller, Bj{\"o}rn Wolfgang and Arnrich, Bert}, title = {Voice Analysis for Neurological Disorder Recognition - A Systematic Review and Perspective on Emerging Trends}, 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 = {13}, doi = {10.25932/publishup-58101}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-581019}, pages = {16}, year = {2022}, abstract = {Quantifying neurological disorders from voice is a rapidly growing field of research and holds promise for unobtrusive and large-scale disorder monitoring. The data recording setup and data analysis pipelines are both crucial aspects to effectively obtain relevant information from participants. Therefore, we performed a systematic review to provide a high-level overview of practices across various neurological disorders and highlight emerging trends. PRISMA-based literature searches were conducted through PubMed, Web of Science, and IEEE Xplore to identify publications in which original (i.e., newly recorded) datasets were collected. Disorders of interest were psychiatric as well as neurodegenerative disorders, such as bipolar disorder, depression, and stress, as well as amyotrophic lateral sclerosis amyotrophic lateral sclerosis, Alzheimer's, and Parkinson's disease, and speech impairments (aphasia, dysarthria, and dysphonia). Of the 43 retrieved studies, Parkinson's disease is represented most prominently with 19 discovered datasets. Free speech and read speech tasks are most commonly used across disorders. Besides popular feature extraction toolkits, many studies utilise custom-built feature sets. Correlations of acoustic features with psychiatric and neurodegenerative disorders are presented. In terms of analysis, statistical analysis for significance of individual features is commonly used, as well as predictive modeling approaches, especially with support vector machines and a small number of artificial neural networks. An emerging trend and recommendation for future studies is to collect data in everyday life to facilitate longitudinal data collection and to capture the behavior of participants more naturally. Another emerging trend is to record additional modalities to voice, which can potentially increase analytical performance.}, language = {en} } @misc{LadleifWeske2021, author = {Ladleif, Jan and Weske, Mathias}, title = {Which Event Happened First? Deferred Choice on Blockchain Using Oracles}, series = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t}, volume = {4}, journal = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, doi = {10.25932/publishup-55068}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-550681}, pages = {1 -- 16}, year = {2021}, abstract = {First come, first served: Critical choices between alternative actions are often made based on events external to an organization, and reacting promptly to their occurrence can be a major advantage over the competition. In Business Process Management (BPM), such deferred choices can be expressed in process models, and they are an important aspect of process engines. Blockchain-based process execution approaches are no exception to this, but are severely limited by the inherent properties of the platform: The isolated environment prevents direct access to external entities and data, and the non-continual runtime based entirely on atomic transactions impedes the monitoring and detection of events. In this paper we provide an in-depth examination of the semantics of deferred choice, and transfer them to environments such as the blockchain. We introduce and compare several oracle architectures able to satisfy certain requirements, and show that they can be implemented using state-of-the-art blockchain technology.}, language = {en} }