@article{NordmeyerKrausZiehmetal.2023,
  author    = {Nordmeyer, Sarah and Kraus, Milena and Ziehm, Matthias and Kirchner, Marieluise and Schafstedde, Marie and Kelm, Marcus and Niquet, Sylvia and Stephen, Mariet Mathew and Baczko, Istvan and Knosalla, Christoph and Schapranow, Matthieu-Patrick and Dittmar, Gunnar and Gotthardt, Michael and Falcke, Martin and Regitz-Zagrosek, Vera and Kuehne, Titus and Mertins, Philipp},
  title     = {Disease- and sex-specific differences in patients with heart valve disease},
  series = {Life Science Alliance},
  volume    = {6},
  journal   = {Life Science Alliance},
  number    = {3},
  publisher = {EMBO Press},
  address   = {Heidelberg},
  issn      = {2575-1077},
  doi       = {10.26508/lsa.202201411},
  pages     = {18},
  year      = {2023},
  abstract  = {Pressure overload in patients with aortic valve stenosis and volume overload in mitral valve regurgitation trigger specific forms of cardiac remodeling; however, little is known about similarities and differences in myocardial proteome regulation. We performed proteome profiling of 75 human left ventricular myocardial biopsies (aortic stenosis = 41, mitral regurgitation = 17, and controls = 17) using high-resolution tandem mass spectrometry next to clinical and hemodynamic parameter acquisition. In patients of both disease groups, proteins related to ECM and cytoskeleton were more abundant, whereas those related to energy metabolism and proteostasis were less abundant compared with controls. In addition, disease group-specific and sex-specific differences have been observed. Male patients with aortic stenosis showed more proteins related to fibrosis and less to energy metabolism, whereas female patients showed strong reduction in proteostasis-related proteins. Clinical imaging was in line with proteomic findings, showing elevation of fibrosis in both patient groups and sex differences. Disease-and sex-specific proteomic profiles provide insight into cardiac remodeling in patients with heart valve disease and might help improve the understanding of molecular mechanisms and the development of individualized treatment strategies.},
  language  = {en}
}
@article{TalebRohrerBergneretal.2022,
  author    = {Taleb, Aiham and Rohrer, Csaba and Bergner, Benjamin and De Leon, Guilherme and Rodrigues, Jonas Almeida and Schwendicke, Falk and Lippert, Christoph and Krois, Joachim},
  title     = {Self-supervised learning methods for label-efficient dental caries classification},
  series = {Diagnostics : open access journal},
  volume    = {12},
  journal   = {Diagnostics : open access journal},
  number    = {5},
  publisher = {MDPI},
  address   = {Basel},
  issn      = {2075-4418},
  doi       = {10.3390/diagnostics12051237},
  pages     = {15},
  year      = {2022},
  abstract  = {High annotation costs are a substantial bottleneck in applying deep learning architectures to clinically relevant use cases, substantiating the need for algorithms to learn from unlabeled data. In this work, we propose employing self-supervised methods. To that end, we trained with three self-supervised algorithms on a large corpus of unlabeled dental images, which contained 38K bitewing radiographs (BWRs). We then applied the learned neural network representations on tooth-level dental caries classification, for which we utilized labels extracted from electronic health records (EHRs). Finally, a holdout test-set was established, which consisted of 343 BWRs and was annotated by three dental professionals and approved by a senior dentist. This test-set was used to evaluate the fine-tuned caries classification models. Our experimental results demonstrate the obtained gains by pretraining models using self-supervised algorithms. These include improved caries classification performance (6 p.p. increase in sensitivity) and, most importantly, improved label-efficiency. In other words, the resulting models can be fine-tuned using few labels (annotations). Our results show that using as few as 18 annotations can produce >= 45\% sensitivity, which is comparable to human-level diagnostic performance. This study shows that self-supervision can provide gains in medical image analysis, particularly when obtaining labels is costly and expensive.},
  language  = {en}
}
@misc{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 Medical Association},
  address   = {Chicago, Ill.},
  issn      = {2168-6106},
  doi       = {10.1001/jamainternmed.2022.3043},
  pages     = {1005 -- 1006},
  year      = {2022},
  language  = {en}
}
@article{AltenburgGieseWangetal.2022,
  author    = {Altenburg, Tom and Giese, Sven Hans-Joachim and Wang, Shengbo and Muth, Thilo and Renard, Bernhard Y.},
  title     = {Ad hoc learning of peptide fragmentation from mass spectra enables an interpretable detection of phosphorylated and cross-linked peptides},
  series = {Nature machine intelligence},
  volume    = {4},
  journal   = {Nature machine intelligence},
  number    = {4},
  publisher = {Springer Nature Publishing},
  address   = {London},
  issn      = {2522-5839},
  doi       = {10.1038/s42256-022-00467-7},
  pages     = {378 -- 388},
  year      = {2022},
  abstract  = {Fragmentation of peptides leaves characteristic patterns in mass spectrometry data, which can be used to identify protein sequences, but this method is challenging for mutated or modified sequences for which limited information exist. Altenburg et al. use an ad hoc learning approach to learn relevant patterns directly from unannotated fragmentation spectra. Mass spectrometry-based proteomics provides a holistic snapshot of the entire protein set of living cells on a molecular level. Currently, only a few deep learning approaches exist that involve peptide fragmentation spectra, which represent partial sequence information of proteins. Commonly, these approaches lack the ability to characterize less studied or even unknown patterns in spectra because of their use of explicit domain knowledge. Here, to elevate unrestricted learning from spectra, we introduce 'ad hoc learning of fragmentation' (AHLF), a deep learning model that is end-to-end trained on 19.2 million spectra from several phosphoproteomic datasets. AHLF is interpretable, and we show that peak-level feature importance values and pairwise interactions between peaks are in line with corresponding peptide fragments. We demonstrate our approach by detecting post-translational modifications, specifically protein phosphorylation based on only the fragmentation spectrum without a database search. AHLF increases the area under the receiver operating characteristic curve (AUC) by an average of 9.4\% on recent phosphoproteomic data compared with the current state of the art on this task. Furthermore, use of AHLF in rescoring search results increases the number of phosphopeptide identifications by a margin of up to 15.1\% at a constant false discovery rate. To show the broad applicability of AHLF, we use transfer learning to also detect cross-linked peptides, as used in protein structure analysis, with an AUC of up to 94\%.},
  language  = {en}
}
@article{GevayRablBressetal.2022,
  author    = {G{\´e}vay, G{\´a}bor E. and Rabl, Tilmann and Breß, Sebastian and Madai-Tahy, Lor{\´a}nd and Quian{\´e}-Ruiz, Jorge-Arnulfo and Markl, Volker},
  title     = {Imperative or functional control flow handling},
  series = {SIGMOD record / Association for Computing Machinery, Special Interest Group on Management of Data},
  volume    = {51},
  journal   = {SIGMOD record / Association for Computing Machinery, Special Interest Group on Management of Data},
  number    = {1},
  publisher = {Association for Computing Machinery},
  address   = {New York},
  issn      = {0163-5808},
  doi       = {10.1145/3542700.3542715},
  pages     = {60 -- 67},
  year      = {2022},
  abstract  = {Modern data analysis tasks often involve control flow statements, such as the iterations in PageRank and K-means. To achieve scalability, developers usually implement these tasks in distributed dataflow systems, such as Spark and Flink. Designers of such systems have to choose between providing imperative or functional control flow constructs to users. Imperative constructs are easier to use, but functional constructs are easier to compile to an efficient dataflow job. We propose Mitos, a system where control flow is both easy to use and efficient. Mitos relies on an intermediate representation based on the static single assignment form. This allows us to abstract away from specific control flow constructs and treat any imperative control flow uniformly both when building the dataflow job and when coordinating the distributed execution.},
  language  = {en}
}
@misc{KonigorskiWernickeSlosareketal.2022,
  author    = {Konigorski, Stefan and Wernicke, Sarah and Slosarek, Tamara and Zenner, Alexander M. and Strelow, Nils and Ruether, Darius F. and Henschel, Florian and Manaswini, Manisha and Pottb{\"a}cker, Fabian and Edelman, Jonathan A. and Owoyele, Babajide and Danieletto, Matteo and Golden, Eddye and Zweig, Micol and Nadkarni, Girish N. and B{\"o}ttinger, Erwin},
  title     = {StudyU: a platform for designing and conducting innovative digital N-of-1 trials},
  series = {Journal of medical internet research},
  volume    = {24},
  journal   = {Journal of medical internet research},
  number    = {7},
  publisher = {Healthcare World},
  address   = {Richmond, Va.},
  issn      = {1439-4456},
  doi       = {10.2196/35884},
  pages     = {12},
  year      = {2022},
  abstract  = {N-of-1 trials are the gold standard study design to evaluate individual treatment effects and derive personalized treatment strategies. Digital tools have the potential to initiate a new era of N-of-1 trials in terms of scale and scope, but fully functional platforms are not yet available. Here, we present the open source StudyU platform, which includes the StudyU Designer and StudyU app. With the StudyU Designer, scientists are given a collaborative web application to digitally specify, publish, and conduct N-of-1 trials. The StudyU app is a smartphone app with innovative user-centric elements for participants to partake in trials published through the StudyU Designer to assess the effects of different interventions on their health. Thereby, the StudyU platform allows clinicians and researchers worldwide to easily design and conduct digital N-of-1 trials in a safe manner. We envision that StudyU can change the landscape of personalized treatments both for patients and healthy individuals, democratize and personalize evidence generation for self-optimization and medicine, and can be integrated in clinical practice.},
  language  = {en}
}
@misc{DellepianeVaidJaladankietal.2021,
  author    = {Dellepiane, Sergio and Vaid, Akhil and Jaladanki, Suraj K. and Coca, Steven and Fayad, Zahi A. and Charney, Alexander W. and B{\"o}ttinger, Erwin and He, John Cijiang and Glicksberg, Benjamin S. and Chan, Lili and Nadkarni, Girish},
  title     = {Acute kidney injury in patients hospitalized with COVID-19 in New York City},
  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    = {5},
  issn      = {2590-0595},
  doi       = {10.25932/publishup-58541},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-585415},
  pages     = {5},
  year      = {2021},
  language  = {en}
}
@article{LangenhanJaegerBaumetal.2022,
  author    = {Langenhan, Jennifer and Jaeger, Carsten and Baum, Katharina and Simon, Mareike and Lisec, Jan},
  title     = {A flexible tool to correct superimposed mass isotopologue distributions in GC-APCI-MS flux experiments},
  series = {Metabolites},
  volume    = {12},
  journal   = {Metabolites},
  number    = {5},
  publisher = {MDPI},
  address   = {Basel},
  issn      = {2218-1989},
  doi       = {10.3390/metabo12050408},
  pages     = {10},
  year      = {2022},
  abstract  = {The investigation of metabolic fluxes and metabolite distributions within cells by means of tracer molecules is a valuable tool to unravel the complexity of biological systems. Technological advances in mass spectrometry (MS) technology such as atmospheric pressure chemical ionization (APCI) coupled with high resolution (HR), not only allows for highly sensitive analyses but also broadens the usefulness of tracer-based experiments, as interesting signals can be annotated de novo when not yet present in a compound library. However, several effects in the APCI ion source, i.e., fragmentation and rearrangement, lead to superimposed mass isotopologue distributions (MID) within the mass spectra, which need to be corrected during data evaluation as they will impair enrichment calculation otherwise. Here, we present and evaluate a novel software tool to automatically perform such corrections. We discuss the different effects, explain the implemented algorithm, and show its application on several experimental datasets. This adjustable tool is available as an R package from CRAN.},
  language  = {en}
}
@article{SinnGieseStuiveretal.2022,
  author    = {Sinn, Ludwig R. and Giese, Sven Hans-Joachim and Stuiver, Marchel and Rappsilber, Juri},
  title     = {Leveraging parameter dependencies in high-field asymmetric waveform ion-mobility spectrometry and size exclusion chromatography for proteome-wide cross-linking mass spectrometry},
  series = {Analytical chemistry : the authoritative voice of the analytical community},
  volume    = {94},
  journal   = {Analytical chemistry : the authoritative voice of the analytical community},
  number    = {11},
  publisher = {American Chemical Society},
  address   = {Columbus, Ohio},
  issn      = {0003-2700},
  doi       = {10.1021/acs.analchem.1c04373},
  pages     = {4627 -- 4634},
  year      = {2022},
  abstract  = {Ion-mobility spectrometry shows great promise to tackle analytically challenging research questions by adding another separation dimension to liquid chromatography-mass spectrometry. The understanding of how analyte properties influence ion mobility has increased through recent studies, but no clear rationale for the design of customized experimental settings has emerged. Here, we leverage machine learning to deepen our understanding of field asymmetric waveform ion-mobility spectrometry for the analysis of cross-linked peptides. Knowing that predominantly m/z and then the size and charge state of an analyte influence the separation, we found ideal compensation voltages correlating with the size exclusion chromatography fraction number. The effect of this relationship on the analytical depth can be substantial as exploiting it allowed us to almost double unique residue pair detections in a proteome-wide cross-linking experiment. Other applications involving liquid- and gas-phase separation may also benefit from considering such parameter dependencies.},
  language  = {en}
}
@article{GevayRablBressetal.2022,
  author    = {Gevay, Gabor E. and Rabl, Tilmann and Bress, Sebastian and Maclai-Tahy, Lorand and Quiane-Ruiz, Jorge-Arnulfo and Markl, Volker},
  title     = {Imperative or Functional Control Flow Handling: Why not the Best of Both Worlds?},
  series = {SIGMOD record},
  volume    = {51},
  journal   = {SIGMOD record},
  number    = {1},
  publisher = {Association for Computing Machinery},
  address   = {New York},
  issn      = {0163-5808},
  doi       = {10.1109/ICDE51399.2021.00127},
  pages     = {60 -- 67},
  year      = {2022},
  abstract  = {Modern data analysis tasks often involve control flow statements, such as the iterations in PageRank and K-means. To achieve scalability, developers usually implement these tasks in distributed dataflow systems, such as Spark and Flink. Designers of such systems have to choose between providing imperative or functional control flow constructs to users. Imperative constructs are easier to use, but functional constructs are easier to compile to an efficient dataflow job. We propose Mitos, a system where control flow is both easy to use and efficient. Mitos relies on an intermediate representation based on the static single assignment form. This allows us to abstract away from specific control flow constructs and treat any imperative control flow uniformly both when building the dataflow job and when coordinating the distributed execution.},
  language  = {en}
}
@article{VerweijNeyThompson2022,
  author    = {Verweij, Marco and Ney, Steven and Thompson, Michael},
  title     = {Cultural Theory's contributions to climate science},
  series = {European journal for philosophy of science},
  volume    = {12},
  journal   = {European journal for philosophy of science},
  number    = {2},
  publisher = {Springer},
  address   = {Dordrecht},
  issn      = {1879-4912},
  doi       = {10.1007/s13194-022-00464-y},
  pages     = {13},
  year      = {2022},
  abstract  = {In his article, 'Social constructionism and climate science denial', Hansson claims to present empirical evidence that the cultural theory developed by Dame Mary Douglas, Aaron Wildavsky and ourselves (among others) leads to (climate) science denial. In this reply, we show that there is no validity to these claims. First, we show that Hansson's empirical evidence that cultural theory has led to climate science denial falls apart under closer inspection. Contrary to Hansson's claims, cultural theory has made significant contributions to understanding and addressing climate change. Second, we discuss various features of Douglas' cultural theory that differentiate it from other constructivist approaches and make it compatible with the scientific method. Thus, we also demonstrate that cultural theory cannot be accused of epistemic relativism.},
  language  = {en}
}
@article{Boissier2021,
  author    = {Boissier, Martin},
  title     = {Robust and budget-constrained encoding configurations for in-memory database systems},
  series = {Proceedings of the VLDB Endowment},
  volume    = {15},
  journal   = {Proceedings of the VLDB Endowment},
  number    = {4},
  publisher = {Association for Computing Machinery (ACM)},
  address   = {[New York]},
  issn      = {2150-8097},
  doi       = {10.14778/3503585.3503588},
  pages     = {780 -- 793},
  year      = {2021},
  abstract  = {Data encoding has been applied to database systems for decades as it mitigates bandwidth bottlenecks and reduces storage requirements. But even in the presence of these advantages, most in-memory database systems use data encoding only conservatively as the negative impact on runtime performance can be severe. Real-world systems with large parts being infrequently accessed and cost efficiency constraints in cloud environments require solutions that automatically and efficiently select encoding techniques, including heavy-weight compression. In this paper, we introduce workload-driven approaches to automaticaly determine memory budget-constrained encoding configurations using greedy heuristics and linear programming. We show for TPC-H, TPC-DS, and the Join Order Benchmark that optimized encoding configurations can reduce the main memory footprint significantly without a loss in runtime performance over state-of-the-art dictionary encoding. To yield robust selections, we extend the linear programming-based approach to incorporate query runtime constraints and mitigate unexpected performance regressions.},
  language  = {en}
}
@article{BjoerkHoelzleBoer2021,
  author    = {Bj{\"o}rk, Jennie and H{\"o}lzle, Katharina and Boer, Harry},
  title     = {'What will we learn from the current crisis?'},
  series = {Creativity and innovation management},
  volume    = {30},
  journal   = {Creativity and innovation management},
  number    = {2},
  publisher = {Wiley-Blackwell},
  address   = {Oxford [u.a.]},
  issn      = {0963-1690},
  doi       = {10.1111/caim.12442},
  pages     = {231 -- 232},
  year      = {2021},
  language  = {en}
}
@article{BonifatiMiorNaumannetal.2022,
  author    = {Bonifati, Angela and Mior, Michael J. and Naumann, Felix and Noack, Nele Sina},
  title     = {How inclusive are we?},
  series = {SIGMOD record / Association for Computing Machinery, Special Interest Group on Management of Data},
  volume    = {50},
  journal   = {SIGMOD record / Association for Computing Machinery, Special Interest Group on Management of Data},
  number    = {4},
  publisher = {Association for Computing Machinery},
  address   = {New York},
  issn      = {0163-5808},
  doi       = {10.1145/3516431.3516438},
  pages     = {30 -- 35},
  year      = {2022},
  abstract  = {ACM SIGMOD, VLDB and other database organizations have committed to fostering an inclusive and diverse community, as do many other scientific organizations. Recently, different measures have been taken to advance these goals, especially for underrepresented groups. One possible measure is double-blind reviewing, which aims to hide gender, ethnicity, and other properties of the authors. <br /> We report the preliminary results of a gender diversity analysis of publications of the database community across several peer-reviewed venues, and also compare women's authorship percentages in both single-blind and double-blind venues along the years. We also obtained a cross comparison of the obtained results in data management with other relevant areas in Computer Science.},
  language  = {en}
}
@article{ReimannBuchheimSemmoetal.2022,
  author    = {Reimann, Max and Buchheim, Benito and Semmo, Amir and D{\"o}llner, J{\"u}rgen and Trapp, Matthias},
  title     = {Controlling strokes in fast neural style transfer using content transforms},
  series = {The Visual Computer},
  volume    = {38},
  journal   = {The Visual Computer},
  number    = {12},
  publisher = {Springer},
  address   = {New York},
  issn      = {0178-2789},
  doi       = {10.1007/s00371-022-02518-x},
  pages     = {4019 -- 4033},
  year      = {2022},
  abstract  = {Fast style transfer methods have recently gained popularity in art-related applications as they make a generalized real-time stylization of images practicable. However, they are mostly limited to one-shot stylizations concerning the interactive adjustment of style elements. In particular, the expressive control over stroke sizes or stroke orientations remains an open challenge. To this end, we propose a novel stroke-adjustable fast style transfer network that enables simultaneous control over the stroke size and intensity, and allows a wider range of expressive editing than current approaches by utilizing the scale-variance of convolutional neural networks. Furthermore, we introduce a network-agnostic approach for style-element editing by applying reversible input transformations that can adjust strokes in the stylized output. At this, stroke orientations can be adjusted, and warping-based effects can be applied to stylistic elements, such as swirls or waves. To demonstrate the real-world applicability of our approach, we present StyleTune, a mobile app for interactive editing of neural style transfers at multiple levels of control. Our app allows stroke adjustments on a global and local level. It furthermore implements an on-device patch-based upsampling step that enables users to achieve results with high output fidelity and resolutions of more than 20 megapixels. Our approach allows users to art-direct their creations and achieve results that are not possible with current style transfer applications.},
  language  = {en}
}
@article{BorchertMockTomczaketal.2021,
  author    = {Borchert, Florian and Mock, Andreas and Tomczak, Aurelie and H{\"u}gel, Jonas and Alkarkoukly, Samer and Knurr, Alexander and Volckmar, Anna-Lena and Stenzinger, Albrecht and Schirmacher, Peter and Debus, J{\"u}rgen and J{\"a}ger, Dirk and Longerich, Thomas and Fr{\"o}hling, Stefan and Eils, Roland and Bougatf, Nina and Sax, Ulrich and Schapranow, Matthieu-Patrick},
  title     = {Correction to: Knowledge bases and software support for variant interpretation in precision oncology},
  series = {Briefings in bioinformatics},
  volume    = {22},
  journal   = {Briefings in bioinformatics},
  number    = {6},
  publisher = {Oxford Univ. Press},
  address   = {Oxford},
  issn      = {1467-5463},
  doi       = {10.1093/bib/bbab246},
  pages     = {1},
  year      = {2021},
  language  = {en}
}
@article{BorchertMockTomczaketal.2021,
  author    = {Borchert, Florian and Mock, Andreas and Tomczak, Aurelie and H{\"u}gel, Jonas and Alkarkoukly, Samer and Knurr, Alexander and Volckmar, Anna-Lena and Stenzinger, Albrecht and Schirmacher, Peter and Debus, J{\"u}rgen and J{\"a}ger, Dirk and Longerich, Thomas and Fr{\"o}hling, Stefan and Eils, Roland and Bougatf, Nina and Sax, Ulrich and Schapranow, Matthieu-Patrick},
  title     = {Knowledge bases and software support for variant interpretation in precision oncology},
  series = {Briefings in bioinformatics},
  volume    = {22},
  journal   = {Briefings in bioinformatics},
  number    = {6},
  publisher = {Oxford Univ. Press},
  address   = {Oxford},
  issn      = {1467-5463},
  doi       = {10.1093/bib/bbab134},
  pages     = {17},
  year      = {2021},
  abstract  = {Precision oncology is a rapidly evolving interdisciplinary medical specialty. Comprehensive cancer panels are becoming increasingly available at pathology departments worldwide, creating the urgent need for scalable cancer variant annotation and molecularly informed treatment recommendations. A wealth of mainly academia-driven knowledge bases calls for software tools supporting the multi-step diagnostic process. We derive a comprehensive list of knowledge bases relevant for variant interpretation by a review of existing literature followed by a survey among medical experts from university hospitals in Germany. In addition, we review cancer variant interpretation tools, which integrate multiple knowledge bases. We categorize the knowledge bases along the diagnostic process in precision oncology and analyze programmatic access options as well as the integration of knowledge bases into software tools. The most commonly used knowledge bases provide good programmatic access options and have been integrated into a range of software tools. For the wider set of knowledge bases, access options vary across different parts of the diagnostic process. Programmatic access is limited for information regarding clinical classifications of variants and for therapy recommendations. The main issue for databases used for biological classification of pathogenic variants and pathway context information is the lack of standardized interfaces. There is no single cancer variant interpretation tool that integrates all identified knowledge bases. Specialized tools are available and need to be further developed for different steps in the diagnostic process.},
  language  = {en}
}
@article{PrillWalterKrolikowskaetal.2021,
  author    = {Prill, Robert and Walter, Marina and Kr{\´o}likowska, Aleksandra and Becker, Roland},
  title     = {A systematic review of diagnostic accuracy and clinical applications of wearable movement sensors for knee joint rehabilitation},
  series = {Sensors},
  volume    = {21},
  journal   = {Sensors},
  number    = {24},
  publisher = {MDPI},
  address   = {Basel},
  issn      = {1424-8220},
  doi       = {10.3390/s21248221},
  pages     = {14},
  year      = {2021},
  abstract  = {In clinical practice, only a few reliable measurement instruments are available for monitoring knee joint rehabilitation. Advances to replace motion capturing with sensor data measurement have been made in the last years. Thus, a systematic review of the literature was performed, focusing on the implementation, diagnostic accuracy, and facilitators and barriers of integrating wearable sensor technology in clinical practices based on a Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) statement. For critical appraisal, the COSMIN Risk of Bias tool for reliability and measurement of error was used. PUBMED, Prospero, Cochrane database, and EMBASE were searched for eligible studies. Six studies reporting reliability aspects in using wearable sensor technology at any point after knee surgery in humans were included. All studies reported excellent results with high reliability coefficients, high limits of agreement, or a few detectable errors. They used different or partly inappropriate methods for estimating reliability or missed reporting essential information. Therefore, a moderate risk of bias must be considered. Further quality criterion studies in clinical settings are needed to synthesize the evidence for providing transparent recommendations for the clinical use of wearable movement sensors in knee joint rehabilitation.},
  language  = {en}
}
@article{ChanJaladankiSomanietal.2021,
  author    = {Chan, Lili and Jaladanki, Suraj K. and Somani, Sulaiman and Paranjpe, Ishan and Kumar, Arvind and Zhao, Shan and Kaufman, Lewis and Leisman, Staci and Sharma, Shuchita and He, John Cijiang and Murphy, Barbara and Fayad, Zahi A. and Levin, Matthew A. and B{\"o}ttinger, Erwin and Charney, Alexander W. and Glicksberg, Benjamin and Coca, Steven G. and Nadkarni, Girish N.},
  title     = {Outcomes of patients on maintenance dialysis hospitalized with COVID-19},
  series = {Clinical journal of the American Society of Nephrology : CJASN},
  volume    = {16},
  journal   = {Clinical journal of the American Society of Nephrology : CJASN},
  number    = {3},
  publisher = {American Society of Nephrology},
  address   = {Washington},
  organization    = {Mount Sinai Covid I},
  issn      = {1555-9041},
  doi       = {10.2215/CJN.12360720},
  pages     = {452 -- 455},
  year      = {2021},
  language  = {en}
}
@article{DattaSachsFreitasdaCruzetal.2021,
  author    = {Datta, Suparno and Sachs, Jan Philipp and Freitas da Cruz, Harry and Martensen, Tom and Bode, Philipp and Morassi Sasso, Ariane and Glicksberg, Benjamin S. and B{\"o}ttinger, Erwin},
  title     = {FIBER},
  series = {JAMIA open},
  volume    = {4},
  journal   = {JAMIA open},
  number    = {3},
  publisher = {Oxford Univ. Press},
  address   = {Oxford},
  issn      = {2574-2531},
  doi       = {10.1093/jamiaopen/ooab048},
  pages     = {10},
  year      = {2021},
  abstract  = {Objectives: The development of clinical predictive models hinges upon the availability of comprehensive clinical data. Tapping into such resources requires considerable effort from clinicians, data scientists, and engineers. Specifically, these efforts are focused on data extraction and preprocessing steps required prior to modeling, including complex database queries. A handful of software libraries exist that can reduce this complexity by building upon data standards. However, a gap remains concerning electronic health records (EHRs) stored in star schema clinical data warehouses, an approach often adopted in practice. In this article, we introduce the FlexIBle EHR Retrieval (FIBER) tool: a Python library built on top of a star schema (i2b2) clinical data warehouse that enables flexible generation of modeling-ready cohorts as data frames. Materials and Methods: FIBER was developed on top of a large-scale star schema EHR database which contains data from 8 million patients and over 120 million encounters. To illustrate FIBER's capabilities, we present its application by building a heart surgery patient cohort with subsequent prediction of acute kidney injury (AKI) with various machine learning models. Results: Using FIBER, we were able to build the heart surgery cohort (n = 12 061), identify the patients that developed AKI (n = 1005), and automatically extract relevant features (n = 774). Finally, we trained machine learning models that achieved area under the curve values of up to 0.77 for this exemplary use case. Conclusion: FIBER is an open-source Python library developed for extracting information from star schema clinical data warehouses and reduces time-to-modeling, helping to streamline the clinical modeling process.},
  language  = {en}
}
@article{DeFreitasJohnsonGoldenetal.2021,
  author    = {De Freitas, Jessica K. and Johnson, Kipp W. and Golden, Eddye and Nadkarni, Girish N. and Dudley, Joel T. and B{\"o}ttinger, Erwin and Glicksberg, Benjamin S. and Miotto, Riccardo},
  title     = {Phe2vec},
  series = {Patterns},
  volume    = {2},
  journal   = {Patterns},
  number    = {9},
  publisher = {Elsevier},
  address   = {Amsterdam},
  issn      = {2666-3899},
  doi       = {10.1016/j.patter.2021.100337},
  pages     = {9},
  year      = {2021},
  abstract  = {Robust phenotyping of patients from electronic health records (EHRs) at scale is a challenge in clinical informatics. Here, we introduce Phe2vec, an automated framework for disease phenotyping from EHRs based on unsupervised learning and assess its effectiveness against standard rule-based algorithms from Phenotype KnowledgeBase (PheKB). Phe2vec is based on pre-computing embeddings of medical concepts and patients' clinical history. Disease phenotypes are then derived from a seed concept and its neighbors in the embedding space. Patients are linked to a disease if their embedded representation is close to the disease phenotype. Comparing Phe2vec and PheKB cohorts head-to-head using chart review, Phe2vec performed on par or better in nine out of ten diseases. Differently from other approaches, it can scale to any condition and was validated against widely adopted expert-based standards. Phe2vec aims to optimize clinical informatics research by augmenting current frameworks to characterize patients by condition and derive reliable disease cohorts.},
  language  = {en}
}
@article{AdnanSrsicVenticichetal.2020,
  author    = {Adnan, Hassan Sami and Srsic, Amanda and Venticich, Pete Milos and Townend, David M.R.},
  title     = {Using AI for mental health analysis and prediction in school surveys},
  series = {European journal of public health},
  volume    = {30},
  journal   = {European journal of public health},
  publisher = {Oxford Univ. Press},
  address   = {Oxford [u.a.]},
  issn      = {1101-1262},
  doi       = {10.1093/eurpub/ckaa165.336},
  pages     = {V125 -- V125},
  year      = {2020},
  abstract  = {Background: Childhood and adolescence are critical stages of life for mental health and well-being. Schools are a key setting for mental health promotion and illness prevention. One in five children and adolescents have a mental disorder, about half of mental disorders beginning before the age of 14. Beneficial and explainable artificial intelligence can replace current paper- based and online approaches to school mental health surveys. This can enhance data acquisition, interoperability, data driven analysis, trust and compliance. This paper presents a model for using chatbots for non-obtrusive data collection and supervised machine learning models for data analysis; and discusses ethical considerations pertaining to the use of these models. Methods: For data acquisition, the proposed model uses chatbots which interact with students. The conversation log acts as the source of raw data for the machine learning. Pre-processing of the data is automated by filtering for keywords and phrases. Existing survey results, obtained through current paper-based data collection methods, are evaluated by domain experts (health professionals). These can be used to create a test dataset to validate the machine learning models. Supervised learning can then be deployed to classify specific behaviour and mental health patterns. Results: We present a model that can be used to improve upon current paper-based data collection and manual data analysis methods. An open-source GitHub repository contains necessary tools and components of this model. Privacy is respected through rigorous observance of confidentiality and data protection requirements. Critical reflection on these ethics and law aspects is included in the project. Conclusions: This model strengthens mental health surveillance in schools. The same tools and components could be applied to other public health data. Future extensions of this model could also incorporate unsupervised learning to find clusters and patterns of unknown effects.},
  language  = {en}
}
@article{ChanChaudharySahaetal.2021,
  author    = {Chan, Lili and Chaudhary, Kumardeep and Saha, Aparna and Chauhan, Kinsuk and Vaid, Akhil and Zhao, Shan and Paranjpe, Ishan and Somani, Sulaiman and Richter, Felix and Miotto, Riccardo and Lala, Anuradha and Kia, Arash and Timsina, Prem and Li, Li and Freeman, Robert and Chen, Rong and Narula, Jagat and Just, Allan C. and Horowitz, Carol and Fayad, Zahi and Cordon-Cardo, Carlos and Schadt, Eric and Levin, Matthew A. and Reich, David L. and Fuster, Valentin and Murphy, Barbara and He, John C. and Charney, Alexander W. and B{\"o}ttinger, Erwin and Glicksberg, Benjamin and Coca, Steven G. and Nadkarni, Girish N.},
  title     = {AKI in hospitalized patients with COVID-19},
  series = {Journal of the American Society of Nephrology : JASN},
  volume    = {32},
  journal   = {Journal of the American Society of Nephrology : JASN},
  number    = {1},
  publisher = {American Society of Nephrology},
  address   = {Washington},
  organization    = {Mt Sinai COVID Informatics Ct},
  issn      = {1046-6673},
  doi       = {10.1681/ASN.2020050615},
  pages     = {151 -- 160},
  year      = {2021},
  abstract  = {Background: Early reports indicate that AKI is common among patients with coronavirus disease 2019 (COVID-19) and associatedwith worse outcomes. However, AKI among hospitalized patients with COVID19 in the United States is not well described. Methods: This retrospective, observational study involved a review of data from electronic health records of patients aged >= 18 years with laboratory-confirmed COVID-19 admitted to the Mount Sinai Health System from February 27 to May 30, 2020. We describe the frequency of AKI and dialysis requirement, AKI recovery, and adjusted odds ratios (aORs) with mortality. Results: Of 3993 hospitalized patients with COVID-19, AKI occurred in 1835 (46\%) patients; 347 (19\%) of the patientswith AKI required dialysis. The proportionswith stages 1, 2, or 3 AKIwere 39\%, 19\%, and 42\%, respectively. A total of 976 (24\%) patients were admitted to intensive care, and 745 (76\%) experienced AKI. Of the 435 patients with AKI and urine studies, 84\% had proteinuria, 81\% had hematuria, and 60\% had leukocyturia. Independent predictors of severe AKI were CKD, men, and higher serum potassium at admission. In-hospital mortality was 50\% among patients with AKI versus 8\% among those without AKI (aOR, 9.2; 95\% confidence interval, 7.5 to 11.3). Of survivors with AKI who were discharged, 35\% had not recovered to baseline kidney function by the time of discharge. An additional 28 of 77 (36\%) patients who had not recovered kidney function at discharge did so on posthospital follow-up. Conclusions: AKI is common among patients hospitalized with COVID-19 and is associated with high mortality. Of all patients with AKI, only 30\% survived with recovery of kidney function by the time of discharge.},
  language  = {en}
}
@article{OliveiraCiabatiLouresdosSantosHsiouSchmaltzetal.2021,
  author    = {Oliveira-Ciabati, Livia and Loures dos Santos, Luciane and Hsiou Schmaltz, Annie and Sasso, Ariane Morassi and Castro, Margaret de and Souza, Jo{\~a}o Paulo},
  title     = {Scientific sexism},
  series = {Revista de sa{\´u}de p{\´u}blica : publication of the Faculdade de Sa{\´u}de P{\´u}blica da Universidade de S{\~a}o Paulo = Journal of public health},
  volume    = {55},
  journal   = {Revista de sa{\´u}de p{\´u}blica : publication of the Faculdade de Sa{\´u}de P{\´u}blica da Universidade de S{\~a}o Paulo = Journal of public health},
  publisher = {Faculdade de Sa{\´u}de P{\´u}blica da Universidade de S{\~a}o Paulo},
  address   = {S{\~a}o Paulo},
  issn      = {1518-8787},
  doi       = {10.11606/s1518-8787.2021055002939},
  pages     = {12},
  year      = {2021},
  abstract  = {OBJECTIVE: To investigate gender inequity in the scientific production of the University of Sao Paulo. METHODS: Members of the University of Sao Paulo faculty are the study population. The Web of Science repository was the source of the publication metrics. We selected the measures: total publications and citations, average of citations per year and item, H-index, and history of citations between 1950 and 2019. We used the name of the faculty member as a proxy to the gender identity. We use descriptive statistics to characterize the metrics. We evaluated the scissors effect by selecting faculty members with a high H-index. The historical series of citations was projected until 2100. We carry out analyses for the general population and working time subgroups: less than 10 years, 10 to 20 years, and 20 years or more. RESULTS: Of the 8,325 faculty members, we included 3,067 (36.8\%). Among those included, 1,893 (61.7\%) were male and 1,174 (38.28\%) female. The male gender presented higher values in the publication metrics (average of articles: M = 67.0 versus F = 49.7; average of citations/year: M = 53.9 versus F = 35.9), and H-index (M = 14.5 versus F = 12.4). Among the 100 individuals with the highest H-index (>= 37), 83\% are male. The male curve grows faster in the historical series of citations, opening a difference between the groups whose separation is confirmed by the projection. DISCUSSION: Scientific production at the Universidade de Sao Paulo is subject to a gender bias. Two-thirds of the faculty are male, and hiring over the past few decades perpetuates this pattern. The large majority of high impact faculty members are male. CONCLUSION: Our analysis suggests that the Universidade de Sao Paulo will not overcome gender inequality in scientific production without substantive affirmative action. Development does not happen by chance but through choices that are affirmative, decisive, and long-term oriented.},
  language  = {en}
}
@article{LongdeMeloHeetal.2020,
  author    = {Long, Xiang and de Melo, Gerard and He, Dongliang and Li, Fu and Chi, Zhizhen and Wen, Shilei and Gan, Chuang},
  title     = {Purely attention based local feature integration for video classification},
  series = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  volume    = {44},
  journal   = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  number    = {4},
  publisher = {Inst. of Electr. and Electronics Engineers},
  address   = {Los Alamitos},
  issn      = {0162-8828},
  doi       = {10.1109/TPAMI.2020.3029554},
  pages     = {2140 -- 2154},
  year      = {2020},
  abstract  = {Recently, substantial research effort has focused on how to apply CNNs or RNNs to better capture temporal patterns in videos, so as to improve the accuracy of video classification. In this paper, we investigate the potential of a purely attention based local feature integration. Accounting for the characteristics of such features in video classification, we first propose Basic Attention Clusters (BAC), which concatenates the output of multiple attention units applied in parallel, and introduce a shifting operation to capture more diverse signals. Experiments show that BAC can achieve excellent results on multiple datasets. However, BAC treats all feature channels as an indivisible whole, which is suboptimal for achieving a finer-grained local feature integration over the channel dimension. Additionally, it treats the entire local feature sequence as an unordered set, thus ignoring the sequential relationships. To improve over BAC, we further propose the channel pyramid attention schema by splitting features into sub-features at multiple scales for coarse-to-fine sub-feature interaction modeling, and propose the temporal pyramid attention schema by dividing the feature sequences into ordered sub-sequences of multiple lengths to account for the sequential order. Our final model pyramidxpyramid attention clusters (PPAC) combines both channel pyramid attention and temporal pyramid attention to focus on the most important sub-features, while also preserving the temporal information of the video. We demonstrate the effectiveness of PPAC on seven real-world video classification datasets. Our model achieves competitive results across all of these, showing that our proposed framework can consistently outperform the existing local feature integration methods across a range of different scenarios.},
  language  = {en}
}
@article{HaarmannHolfterPufahletal.2021,
  author    = {Haarmann, Stephan and Holfter, Adrian and Pufahl, Luise and Weske, Mathias},
  title     = {Formal framework for checking compliance of data-driven case management},
  series = {Journal on data semantics : JoDS},
  volume    = {10},
  journal   = {Journal on data semantics : JoDS},
  number    = {1-2},
  publisher = {Springer},
  address   = {Heidelberg},
  issn      = {1861-2032},
  doi       = {10.1007/s13740-021-00120-3},
  pages     = {143 -- 163},
  year      = {2021},
  abstract  = {Business processes are often specified in descriptive or normative models. Both types of models should adhere to internal and external regulations, such as company guidelines or laws. Employing compliance checking techniques, it is possible to verify process models against rules. While traditionally compliance checking focuses on well-structured processes, we address case management scenarios. In case management, knowledge workers drive multi-variant and adaptive processes. Our contribution is based on the fragment-based case management approach, which splits a process into a set of fragments. The fragments are synchronized through shared data but can, otherwise, be dynamically instantiated and executed. We formalize case models using Petri nets. We demonstrate the formalization for design-time and run-time compliance checking and present a proof-of-concept implementation. The application of the implemented compliance checking approach to a use case exemplifies its effectiveness while designing a case model. The empirical evaluation on a set of case models for measuring the performance of the approach shows that rules can often be checked in less than a second.},
  language  = {en}
}
@article{DoerrKoetzing2022,
  author    = {Doerr, Benjamin and K{\"o}tzing, Timo},
  title     = {Lower bounds from fitness levels made easy},
  series = {Algorithmica},
  journal   = {Algorithmica},
  publisher = {Springer},
  address   = {New York},
  issn      = {0178-4617},
  doi       = {10.1007/s00453-022-00952-w},
  pages     = {29},
  year      = {2022},
  abstract  = {One of the first and easy to use techniques for proving run time bounds for evolutionary algorithms is the so-called method of fitness levels by Wegener. It uses a partition of the search space into a sequence of levels which are traversed by the algorithm in increasing order, possibly skipping levels. An easy, but often strong upper bound for the run time can then be derived by adding the reciprocals of the probabilities to leave the levels (or upper bounds for these). Unfortunately, a similarly effective method for proving lower bounds has not yet been established. The strongest such method, proposed by Sudholt (2013), requires a careful choice of the viscosity parameters gamma(i), j, 0 <= i < j <= n. In this paper we present two new variants of the method, one for upper and one for lower bounds. Besides the level leaving probabilities, they only rely on the probabilities that levels are visited at all. We show that these can be computed or estimated without greater difficulties and apply our method to reprove the following known results in an easy and natural way. (i) The precise run time of the (1+1) EA on LEADINGONES. (ii) A lower bound for the run time of the (1+1) EA on ONEMAX, tight apart from an O(n) term. (iii) A lower bound for the run time of the (1+1) EA on long k-paths (which differs slightly from the previous result due to a small error in the latter). We also prove a tighter lower bound for the run time of the (1+1) EA on jump functions by showing that, regardless of the jump size, only with probability O(2(-n)) the algorithm can avoid to jump over the valley of low fitness.},
  language  = {en}
}
@article{BlaesiusFreibergerFriedrichetal.2022,
  author    = {Bl{\"a}sius, Thomas and Freiberger, Cedric and Friedrich, Tobias and Katzmann, Maximilian and Montenegro-Retana, Felix and Thieffry, Marianne},
  title     = {Efficient Shortest Paths in Scale-Free Networks with Underlying Hyperbolic Geometry},
  series = {ACM Transactions on Algorithms},
  volume    = {18},
  journal   = {ACM Transactions on Algorithms},
  number    = {2},
  publisher = {Association for Computing Machinery},
  address   = {New York},
  issn      = {1549-6325},
  doi       = {10.1145/3516483},
  pages     = {1 -- 32},
  year      = {2022},
  abstract  = {A standard approach to accelerating shortest path algorithms on networks is the bidirectional search, which explores the graph from the start and the destination, simultaneously. In practice this strategy performs particularly well on scale-free real-world networks. Such networks typically have a heterogeneous degree distribution (e.g., a power-law distribution) and high clustering (i.e., vertices with a common neighbor are likely to be connected themselves). These two properties can be obtained by assuming an underlying hyperbolic geometry. <br /> To explain the observed behavior of the bidirectional search, we analyze its running time on hyperbolic random graphs and prove that it is (O) over tilde (n(2-1/alpha) + n(1/(2 alpha)) + delta(max)) with high probability, where alpha is an element of (1/2, 1) controls the power-law exponent of the degree distribution, and dmax is the maximum degree. This bound is sublinear, improving the obvious worst-case linear bound. Although our analysis depends on the underlying geometry, the algorithm itself is oblivious to it.},
  language  = {en}
}
@article{DoerrKrejca2021,
  author    = {Doerr, Benjamin and Krejca, Martin Stefan},
  title     = {A simplified run time analysis of the univariate marginal distribution algorithm on LeadingOnes},
  series = {Theoretical computer science},
  volume    = {851},
  journal   = {Theoretical computer science},
  publisher = {Elsevier},
  address   = {Amsterdam},
  issn      = {0304-3975},
  doi       = {10.1016/j.tcs.2020.11.028},
  pages     = {121 -- 128},
  year      = {2021},
  abstract  = {With elementary means, we prove a stronger run time guarantee for the univariate marginal distribution algorithm (UMDA) optimizing the LEADINGONES benchmark function in the desirable regime with low genetic drift. If the population size is at least quasilinear, then, with high probability, the UMDA samples the optimum in a number of iterations that is linear in the problem size divided by the logarithm of the UMDA's selection rate. This improves over the previous guarantee, obtained by Dang and Lehre (2015) via the deep level-based population method, both in terms of the run time and by demonstrating further run time gains from small selection rates. Under similar assumptions, we prove a lower bound that matches our upper bound up to constant factors.},
  language  = {en}
}
@article{BanoMichaelRumpeetal.2022,
  author    = {Bano, Dorina and Michael, Judith and Rumpe, Bernhard and Varga, Simon and Weske, Mathias},
  title     = {Process-aware digital twin cockpit synthesis from event logs},
  series = {Journal of computer languages},
  volume    = {70},
  journal   = {Journal of computer languages},
  publisher = {Elsevier},
  address   = {Amsterdam [u.a.]},
  issn      = {2590-1184},
  doi       = {10.1016/j.cola.2022.101121},
  pages     = {19},
  year      = {2022},
  abstract  = {The engineering of digital twins and their user interaction parts with explicated processes, namely processaware digital twin cockpits (PADTCs), is challenging due to the complexity of the systems and the need for information from different disciplines within the engineering process. Therefore, it is interesting to investigate how to facilitate their engineering by using already existing data, namely event logs, and reducing the number of manual steps for their engineering. Current research lacks systematic, automated approaches to derive process-aware digital twin cockpits even though some helpful techniques already exist in the areas of process mining and software engineering. Within this paper, we present a low-code development approach that reduces the amount of hand-written code needed and uses process mining techniques to derive PADTCs. We describe what models could be derived from event log data, which generative steps are needed for the engineering of PADTCs, and how process mining could be incorporated into the resulting application. This process is evaluated using the MIMIC III dataset for the creation of a PADTC prototype for an automated hospital transportation system. This approach can be used for early prototyping of PADTCs as it needs no hand-written code in the first place, but it still allows for the iterative evolvement of the application. This empowers domain experts to create their PADTC prototypes.},
  language  = {en}
}
@article{BlaesiusFriedrichSchirneck2021,
  author    = {Blaesius, Thomas and Friedrich, Tobias and Schirneck, Friedrich Martin},
  title     = {The complexity of dependency detection and discovery in relational databases},
  series = {Theoretical computer science},
  volume    = {900},
  journal   = {Theoretical computer science},
  publisher = {Elsevier},
  address   = {Amsterdam},
  issn      = {0304-3975},
  doi       = {10.1016/j.tcs.2021.11.020},
  pages     = {79 -- 96},
  year      = {2021},
  abstract  = {Multi-column dependencies in relational databases come associated with two different computational tasks. The detection problem is to decide whether a dependency of a certain type and size holds in a given database, the discovery problem asks to enumerate all valid dependencies of that type. We settle the complexity of both of these problems for unique column combinations (UCCs), functional dependencies (FDs), and inclusion dependencies (INDs). We show that the detection of UCCs and FDs is W[2]-complete when parameterized by the solution size. The discovery of inclusion-wise minimal UCCs is proven to be equivalent under parsimonious reductions to the transversal hypergraph problem of enumerating the minimal hitting sets of a hypergraph. The discovery of FDs is equivalent to the simultaneous enumeration of the hitting sets of multiple input hypergraphs. We further identify the detection of INDs as one of the first natural W[3]-complete problems. The discovery of maximal INDs is shown to be equivalent to enumerating the maximal satisfying assignments of antimonotone, 3-normalized Boolean formulas.},
  language  = {en}
}
@article{AndreeIhdeWeskeetal.2022,
  author    = {Andree, Kerstin and Ihde, Sven and Weske, Mathias and Pufahl, Luise},
  title     = {An exception handling framework for case management},
  series = {Software and Systems Modeling},
  volume    = {21},
  journal   = {Software and Systems Modeling},
  number    = {3},
  publisher = {Springer},
  address   = {Heidelberg},
  issn      = {1619-1366},
  doi       = {10.1007/s10270-022-00993-3},
  pages     = {939 -- 962},
  year      = {2022},
  abstract  = {In order to achieve their business goals, organizations heavily rely on the operational excellence of their business processes. In traditional scenarios, business processes are usually well-structured, clearly specifying when and how certain tasks have to be executed. Flexible and knowledge-intensive processes are gathering momentum, where a knowledge worker drives the execution of a process case and determines the exact process path at runtime. In the case of an exception, the knowledge worker decides on an appropriate handling. While there is initial work on exception handling in well-structured business processes, exceptions in case management have not been sufficiently researched. This paper proposes an exception handling framework for stage-oriented case management languages, namely Guard Stage Milestone Model, Case Management Model and Notation, and Fragment-based Case Management. The effectiveness of the framework is evaluated with two real-world use cases showing that it covers all relevant exceptions and proposed handling strategies.},
  language  = {en}
}
@article{KossmannPapenbrockNaumann2021,
  author    = {Koßmann, Jan and Papenbrock, Thorsten and Naumann, Felix},
  title     = {Data dependencies for query optimization},
  series = {The VLDB journal : the international journal on very large data bases / publ. on behalf of the VLDB Endowment},
  volume    = {31},
  journal   = {The VLDB journal : the international journal on very large data bases / publ. on behalf of the VLDB Endowment},
  number    = {1},
  publisher = {Springer},
  address   = {Berlin ; Heidelberg ; New York},
  issn      = {1066-8888},
  doi       = {10.1007/s00778-021-00676-3},
  pages     = {1 -- 22},
  year      = {2021},
  abstract  = {Effective query optimization is a core feature of any database management system. While most query optimization techniques make use of simple metadata, such as cardinalities and other basic statistics, other optimization techniques are based on more advanced metadata including data dependencies, such as functional, uniqueness, order, or inclusion dependencies. This survey provides an overview, intuitive descriptions, and classifications of query optimization and execution strategies that are enabled by data dependencies. We consider the most popular types of data dependencies and focus on optimization strategies that target the optimization of relational database queries. The survey supports database vendors to identify optimization opportunities as well as DBMS researchers to find related work and open research questions.},
  language  = {en}
}
@article{RoostapourNeumannNeumannetal.2022,
  author    = {Roostapour, Vahid and Neumann, Aneta and Neumann, Frank and Friedrich, Tobias},
  title     = {Pareto optimization for subset selection with dynamic cost constraints},
  series = {Artificial intelligence},
  volume    = {302},
  journal   = {Artificial intelligence},
  publisher = {Elsevier},
  address   = {Amsterdam},
  issn      = {0004-3702},
  doi       = {10.1016/j.artint.2021.103597},
  pages     = {17},
  year      = {2022},
  abstract  = {We consider the subset selection problem for function f with constraint bound B that changes over time. Within the area of submodular optimization, various greedy approaches are commonly used. For dynamic environments we observe that the adaptive variants of these greedy approaches are not able to maintain their approximation quality. Investigating the recently introduced POMC Pareto optimization approach, we show that this algorithm efficiently computes a phi=(alpha(f)/2)(1 - 1/e(alpha)f)-approximation, where alpha(f) is the submodularity ratio of f, for each possible constraint bound b <= B. Furthermore, we show that POMC is able to adapt its set of solutions quickly in the case that B increases. Our experimental investigations for the influence maximization in social networks show the advantage of POMC over generalized greedy algorithms. We also consider EAMC, a new evolutionary algorithm with polynomial expected time guarantee to maintain phi approximation ratio, and NSGA-II with two different population sizes as advanced multi-objective optimization algorithm, to demonstrate their challenges in optimizing the maximum coverage problem. Our empirical analysis shows that, within the same number of evaluations, POMC is able to perform as good as NSGA-II under linear constraint, while EAMC performs significantly worse than all considered algorithms in most cases.},
  language  = {en}
}
@article{CsehFleiner2020,
  author    = {Cseh, {\´A}gnes and Fleiner, Tamas},
  title     = {The complexity of cake cutting with unequal shares},
  series = {ACM transactions on algorithms : TALG},
  volume    = {16},
  journal   = {ACM transactions on algorithms : TALG},
  number    = {3},
  publisher = {Association for Computing Machinery},
  address   = {New York},
  issn      = {1549-6325},
  doi       = {10.1145/3380742},
  pages     = {21},
  year      = {2020},
  abstract  = {An unceasing problem of our prevailing society is the fair division of goods. The problem of proportional cake cutting focuses on dividing a heterogeneous and divisible resource, the cake, among n players who value pieces according to their own measure function. The goal is to assign each player a not necessarily connected part of the cake that the player evaluates at least as much as her proportional share. <br /> In this article, we investigate the problem of proportional division with unequal shares, where each player is entitled to receive a predetermined portion of the cake. Our main contribution is threefold. First we present a protocol for integer demands, which delivers a proportional solution in fewer queries than all known protocols. By giving a matching lower bound, we then show that our protocol is asymptotically the fastest possible. Finally, we turn to irrational demands and solve the proportional cake cutting problem by reducing it to the same problem with integer demands only. All results remain valid in a highly general cake cutting model, which can be of independent interest.},
  language  = {en}
}
@article{HehnMendezUebernickeletal.2019,
  author    = {Hehn, Jennifer and Mendez, Daniel and Uebernickel, Falk and Brenner, Walter and Broy, Manfred},
  title     = {On integrating design thinking for human-centered requirements engineering},
  series = {IEEE software},
  volume    = {37},
  journal   = {IEEE software},
  number    = {2},
  publisher = {Inst. of Electr. and Electronics Engineers},
  address   = {Los Alamitos},
  issn      = {0740-7459},
  doi       = {10.1109/MS.2019.2957715},
  pages     = {25 -- 31},
  year      = {2019},
  abstract  = {We elaborate on the possibilities and needs to integrate design thinking into requirements engineering, drawing from our research and project experiences. We suggest three approaches for tailoring and integrating design thinking and requirements engineering with complementary synergies and point at open challenges for research and practice.},
  language  = {en}
}
@article{LambersOrejas2021,
  author    = {Lambers, Leen and Orejas, Fernando},
  title     = {Transformation rules with nested application conditions},
  series = {Theoretical computer science},
  volume    = {884},
  journal   = {Theoretical computer science},
  publisher = {Elsevier},
  address   = {Amsterdam},
  issn      = {0304-3975},
  doi       = {10.1016/j.tcs.2021.07.023},
  pages     = {44 -- 67},
  year      = {2021},
  abstract  = {Recently, initial conflicts were introduced in the framework of M-adhesive categories as an important optimization of critical pairs. In particular, they represent a proper subset such that each conflict is represented in a minimal context by a unique initial one. The theory of critical pairs has been extended in the framework of M-adhesive categories to rules with nested application conditions (ACs), restricting the applicability of a rule and generalizing the well-known negative application conditions. A notion of initial conflicts for rules with ACs does not exist yet. In this paper, on the one hand, we extend the theory of initial conflicts in the framework of M-adhesive categories to transformation rules with ACs. They represent a proper subset again of critical pairs for rules with ACs, and represent each conflict in a minimal context uniquely. They are moreover symbolic because we can show that in general no finite and complete set of conflicts for rules with ACs exists. On the other hand, we show that critical pairs are minimally M-complete, whereas initial conflicts are minimally complete. Finally, we introduce important special cases of rules with ACs for which we can obtain finite, minimally (M-)complete sets of conflicts.},
  language  = {en}
}
@article{WeinsteinCehMeineletal.2022,
  author    = {Weinstein, Theresa Julia and Ceh, Simon Majed and Meinel, Christoph and Benedek, Mathias},
  title     = {What's creative about sentences?},
  series = {Creativity Research Journal},
  volume    = {34},
  journal   = {Creativity Research Journal},
  number    = {4},
  publisher = {Routledge, Taylor \& Francis Group},
  address   = {Abingdon},
  issn      = {1040-0419},
  doi       = {10.1080/10400419.2022.2124777},
  pages     = {419 -- 430},
  year      = {2022},
  abstract  = {Evaluating creativity of verbal responses or texts is a challenging task due to psychometric issues associated with subjective ratings and the peculiarities of textual data. We explore an approach to objectively assess the creativity of responses in a sentence generation task to 1) better understand what language-related aspects are valued by human raters and 2) further advance the developments toward automating creativity evaluations. Over the course of two prior studies, participants generated 989 four-word sentences based on a four-letter prompt with the instruction to be creative. We developed an algorithm that scores each sentence on eight different metrics including 1) general word infrequency, 2) word combination infrequency, 3) context-specific word uniqueness, 4) syntax uniqueness, 5) rhyme, 6) phonetic similarity, and similarity of 7) sequence spelling and 8) semantic meaning to the cue. The text metrics were then used to explain the averaged creativity ratings of eight human raters. We found six metrics to be significantly correlated with the human ratings, explaining a total of 16\% of their variance. We conclude that the creative impression of sentences is partly driven by different aspects of novelty in word choice and syntax, as well as rhythm and sound, which are amenable to objective assessment.},
  language  = {en}
}
@article{DoerrKoetzingLagodzinskietal.2020,
  author    = {Doerr, Benjamin and K{\"o}tzing, Timo and Lagodzinski, Gregor J. A. and Lengler, Johannes},
  title     = {The impact of lexicographic parsimony pressure for ORDER/MAJORITY on the run time},
  series = {Theoretical computer science : the journal of the EATCS},
  volume    = {816},
  journal   = {Theoretical computer science : the journal of the EATCS},
  publisher = {Elsevier},
  address   = {Amsterdam [u.a.]},
  issn      = {0304-3975},
  doi       = {10.1016/j.tcs.2020.01.011},
  pages     = {144 -- 168},
  year      = {2020},
  abstract  = {While many optimization problems work with a fixed number of decision variables and thus a fixed-length representation of possible solutions, genetic programming (GP) works on variable-length representations. A naturally occurring problem is that of bloat, that is, the unnecessary growth of solution lengths, which may slow down the optimization process. So far, the mathematical runtime analysis could not deal well with bloat and required explicit assumptions limiting bloat. In this paper, we provide the first mathematical runtime analysis of a GP algorithm that does not require any assumptions on the bloat. Previous performance guarantees were only proven conditionally for runs in which no strong bloat occurs. Together with improved analyses for the case with bloat restrictions our results show that such assumptions on the bloat are not necessary and that the algorithm is efficient without explicit bloat control mechanism. More specifically, we analyzed the performance of the (1 + 1) GP on the two benchmark functions ORDER and MAJORITY. When using lexicographic parsimony pressure as bloat control, we show a tight runtime estimate of O(T-init + nlogn) iterations both for ORDER and MAJORITY. For the case without bloat control, the bounds O(T-init logT(i)(nit) + n(logn)(3)) and Omega(T-init + nlogn) (and Omega(T-init log T-init) for n = 1) hold for MAJORITY(1).},
  language  = {en}
}
@article{OosthoekDoerr2021,
  author    = {Oosthoek, Kris and D{\"o}rr, Christian},
  title     = {Cyber security threats to bitcoin exchanges},
  series = {IEEE transactions on network and service management : a publication of the IEEE},
  volume    = {18},
  journal   = {IEEE transactions on network and service management : a publication of the IEEE},
  number    = {2},
  publisher = {IEEE},
  address   = {New York},
  issn      = {1932-4537},
  doi       = {10.1109/TNSM.2020.3046145},
  pages     = {1616 -- 1628},
  year      = {2021},
  abstract  = {Bitcoin is gaining traction as an alternative store of value. Its market capitalization transcends all other cryptocurrencies in the market. But its high monetary value also makes it an attractive target to cyber criminal actors. Hacking campaigns usually target an ecosystem's weakest points. In Bitcoin, the exchange platforms are one of them. Each exchange breach is a threat not only to direct victims, but to the credibility of Bitcoin's entire ecosystem. Based on an extensive analysis of 36 breaches of Bitcoin exchanges, we show the attack patterns used to exploit Bitcoin exchange platforms using an industry standard for reporting intelligence on cyber security breaches. Based on this we are able to provide an overview of the most common attack vectors, showing that all except three hacks were possible due to relatively lax security. We show that while the security regimen of Bitcoin exchanges is subpar compared to other financial service providers, the use of stolen credentials, which does not require any hacking, is decreasing. We also show that the amount of BTC taken during a breach is decreasing, as well as the exchanges that terminate after being breached. Furthermore we show that overall security posture has improved, but still has major flaws. To discover adversarial methods post-breach, we have analyzed two cases of BTC laundering. Through this analysis we provide insight into how exchange platforms with lax cyber security even further increase the intermediary risk introduced by them into the Bitcoin ecosystem.},
  language  = {en}
}
@article{VaidChanChaudharyetal.2021,
  author    = {Vaid, Akhil and Chan, Lili and Chaudhary, Kumardeep and Jaladanki, Suraj K. and Paranjpe, Ishan and Russak, Adam J. and Kia, Arash and Timsina, Prem and Levin, Matthew A. and He, John Cijiang and B{\"o}ttinger, Erwin and Charney, Alexander W. and Fayad, Zahi A. and Coca, Steven G. and Glicksberg, Benjamin S. and Nadkarni, Girish N.},
  title     = {Predictive approaches for acute dialysis requirement and death in COVID-19},
  series = {Clinical journal of the American Society of Nephrology : CJASN},
  volume    = {16},
  journal   = {Clinical journal of the American Society of Nephrology : CJASN},
  number    = {8},
  publisher = {American Society of Nephrology},
  address   = {Washington},
  organization    = {MSCIC},
  issn      = {1555-9041},
  doi       = {10.2215/CJN.17311120},
  pages     = {1158 -- 1168},
  year      = {2021},
  abstract  = {Background and objectives AKI treated with dialysis initiation is a common complication of coronavirus disease 2019 (COVID-19) among hospitalized patients. However, dialysis supplies and personnel are often limited. Design, setting, participants, \& measurements Using data from adult patients hospitalized with COVID-19 from five hospitals from theMount Sinai Health System who were admitted between March 10 and December 26, 2020, we developed and validated several models (logistic regression, Least Absolute Shrinkage and Selection Operator (LASSO), random forest, and eXtreme GradientBoosting [XGBoost; with and without imputation]) for predicting treatment with dialysis or death at various time horizons (1, 3, 5, and 7 days) after hospital admission. Patients admitted to theMount Sinai Hospital were used for internal validation, whereas the other hospitals formed part of the external validation cohort. Features included demographics, comorbidities, and laboratory and vital signs within 12 hours of hospital admission. Results A total of 6093 patients (2442 in training and 3651 in external validation) were included in the final cohort. Of the different modeling approaches used, XGBoost without imputation had the highest area under the receiver operating characteristic (AUROC) curve on internal validation (range of 0.93-0.98) and area under the precisionrecall curve (AUPRC; range of 0.78-0.82) for all time points. XGBoost without imputation also had the highest test parameters on external validation (AUROC range of 0.85-0.87, and AUPRC range of 0.27-0.54) across all time windows. XGBoost without imputation outperformed all models with higher precision and recall (mean difference in AUROC of 0.04; mean difference in AUPRC of 0.15). Features of creatinine, BUN, and red cell distribution width were major drivers of the model's prediction. Conclusions An XGBoost model without imputation for prediction of a composite outcome of either death or dialysis in patients positive for COVID-19 had the best performance, as compared with standard and other machine learning models.},
  language  = {en}
}
@article{VaidSomaniRussaketal.2020,
  author    = {Vaid, Akhil and Somani, Sulaiman and Russak, Adam J. and De Freitas, Jessica K. and Chaudhry, Fayzan F. and Paranjpe, Ishan and Johnson, Kipp W. and Lee, Samuel J. and Miotto, Riccardo and Richter, Felix and Zhao, Shan and Beckmann, Noam D. and Naik, Nidhi and Kia, Arash and Timsina, Prem and Lala, Anuradha and Paranjpe, Manish and Golden, Eddye and Danieletto, Matteo and Singh, Manbir and Meyer, Dara and O'Reilly, Paul F. and Huckins, Laura and Kovatch, Patricia and Finkelstein, Joseph and Freeman, Robert M. and Argulian, Edgar and Kasarskis, Andrew and Percha, Bethany and Aberg, Judith A. and Bagiella, Emilia and Horowitz, Carol R. and Murphy, Barbara and Nestler, Eric J. and Schadt, Eric E. and Cho, Judy H. and Cordon-Cardo, Carlos and Fuster, Valentin and Charney, Dennis S. and Reich, David L. and B{\"o}ttinger, Erwin and Levin, Matthew A. and Narula, Jagat and Fayad, Zahi A. and Just, Allan C. and Charney, Alexander W. and Nadkarni, Girish N. and Glicksberg, Benjamin S.},
  title     = {Machine learning to predict mortality and critical events in a cohort of patients with COVID-19 in New York City: model development and validation},
  series = {Journal of medical internet research : international scientific journal for medical research, information and communication on the internet ; JMIR},
  volume    = {22},
  journal   = {Journal of medical internet research : international scientific journal for medical research, information and communication on the internet ; JMIR},
  number    = {11},
  publisher = {Healthcare World},
  address   = {Richmond, Va.},
  issn      = {1439-4456},
  doi       = {10.2196/24018},
  pages     = {19},
  year      = {2020},
  abstract  = {Background: COVID-19 has infected millions of people worldwide and is responsible for several hundred thousand fatalities. The COVID-19 pandemic has necessitated thoughtful resource allocation and early identification of high-risk patients. However, effective methods to meet these needs are lacking. Objective: The aims of this study were to analyze the electronic health records (EHRs) of patients who tested positive for COVID-19 and were admitted to hospitals in the Mount Sinai Health System in New York City; to develop machine learning models for making predictions about the hospital course of the patients over clinically meaningful time horizons based on patient characteristics at admission; and to assess the performance of these models at multiple hospitals and time points. Methods: We used Extreme Gradient Boosting (XGBoost) and baseline comparator models to predict in-hospital mortality and critical events at time windows of 3, 5, 7, and 10 days from admission. Our study population included harmonized EHR data from five hospitals in New York City for 4098 COVID-19-positive patients admitted from March 15 to May 22, 2020. The models were first trained on patients from a single hospital (n=1514) before or on May 1, externally validated on patients from four other hospitals (n=2201) before or on May 1, and prospectively validated on all patients after May 1 (n=383). Finally, we established model interpretability to identify and rank variables that drive model predictions. Results: Upon cross-validation, the XGBoost classifier outperformed baseline models, with an area under the receiver operating characteristic curve (AUC-ROC) for mortality of 0.89 at 3 days, 0.85 at 5 and 7 days, and 0.84 at 10 days. XGBoost also performed well for critical event prediction, with an AUC-ROC of 0.80 at 3 days, 0.79 at 5 days, 0.80 at 7 days, and 0.81 at 10 days. In external validation, XGBoost achieved an AUC-ROC of 0.88 at 3 days, 0.86 at 5 days, 0.86 at 7 days, and 0.84 at 10 days for mortality prediction. Similarly, the unimputed XGBoost model achieved an AUC-ROC of 0.78 at 3 days, 0.79 at 5 days, 0.80 at 7 days, and 0.81 at 10 days. Trends in performance on prospective validation sets were similar. At 7 days, acute kidney injury on admission, elevated LDH, tachypnea, and hyperglycemia were the strongest drivers of critical event prediction, while higher age, anion gap, and C-reactive protein were the strongest drivers of mortality prediction. Conclusions: We externally and prospectively trained and validated machine learning models for mortality and critical events for patients with COVID-19 at different time horizons. These models identified at-risk patients and uncovered underlying relationships that predicted outcomes.},
  language  = {en}
}
@article{CsehHeeger2020,
  author    = {Cseh, Agnes and Heeger, Klaus},
  title     = {The stable marriage problem with ties and restricted edges},
  series = {Discrete optimization},
  volume    = {36},
  journal   = {Discrete optimization},
  publisher = {Elsevier},
  address   = {Amsterdam},
  issn      = {1572-5286},
  doi       = {10.1016/j.disopt.2020.100571},
  pages     = {11},
  year      = {2020},
  abstract  = {In the stable marriage problem, a set of men and a set of women are given, each of whom has a strictly ordered preference list over the acceptable agents in the opposite class. A matching is called stable if it is not blocked by any pair of agents, who mutually prefer each other to their respective partner. Ties in the preferences allow for three different definitions for a stable matching: weak, strong and super-stability. Besides this, acceptable pairs in the instance can be restricted in their ability of blocking a matching or being part of it, which again generates three categories of restrictions on acceptable pairs. Forced pairs must be in a stable matching, forbidden pairs must not appear in it, and lastly, free pairs cannot block any matching. Our computational complexity study targets the existence of a stable solution for each of the three stability definitions, in the presence of each of the three types of restricted pairs. We solve all cases that were still open. As a byproduct, we also derive that the maximum size weakly stable matching problem is hard even in very dense graphs, which may be of independent interest.},
  language  = {en}
}
@article{CaruccioDeufemiaNaumannetal.2021,
  author    = {Caruccio, Loredana and Deufemia, Vincenzo and Naumann, Felix and Polese, Giuseppe},
  title     = {Discovering relaxed functional dependencies based on multi-attribute dominance},
  series = {IEEE transactions on knowledge and data engineering},
  volume    = {33},
  journal   = {IEEE transactions on knowledge and data engineering},
  number    = {9},
  publisher = {Institute of Electrical and Electronics Engineers},
  address   = {New York, NY},
  issn      = {1041-4347},
  doi       = {10.1109/TKDE.2020.2967722},
  pages     = {3212 -- 3228},
  year      = {2021},
  abstract  = {With the advent of big data and data lakes, data are often integrated from multiple sources. Such integrated data are often of poor quality, due to inconsistencies, errors, and so forth. One way to check the quality of data is to infer functional dependencies (fds). However, in many modern applications it might be necessary to extract properties and relationships that are not captured through fds, due to the necessity to admit exceptions, or to consider similarity rather than equality of data values. Relaxed fds (rfds) have been introduced to meet these needs, but their discovery from data adds further complexity to an already complex problem, also due to the necessity of specifying similarity and validity thresholds. We propose Domino, a new discovery algorithm for rfds that exploits the concept of dominance in order to derive similarity thresholds of attribute values while inferring rfds. An experimental evaluation on real datasets demonstrates the discovery performance and the effectiveness of the proposed algorithm.},
  language  = {en}
}
@article{QuinzanGoebelWagneretal.2021,
  author    = {Quinzan, Francesco and G{\"o}bel, Andreas and Wagner, Markus and Friedrich, Tobias},
  title     = {Evolutionary algorithms and submodular functions},
  series = {Natural computing : an innovative journal bridging biosciences and computer sciences ; an international journal},
  volume    = {20},
  journal   = {Natural computing : an innovative journal bridging biosciences and computer sciences ; an international journal},
  number    = {3},
  publisher = {Springer Science + Business Media B.V.},
  address   = {Dordrecht},
  issn      = {1572-9796},
  doi       = {10.1007/s11047-021-09841-7},
  pages     = {561 -- 575},
  year      = {2021},
  abstract  = {A core operator of evolutionary algorithms (EAs) is the mutation. Recently, much attention has been devoted to the study of mutation operators with dynamic and non-uniform mutation rates. Following up on this area of work, we propose a new mutation operator and analyze its performance on the (1 + 1) Evolutionary Algorithm (EA). Our analyses show that this mutation operator competes with pre-existing ones, when used by the (1 + 1) EA on classes of problems for which results on the other mutation operators are available. We show that the (1 + 1) EA using our mutation operator finds a (1/3)-approximation ratio on any non-negative submodular function in polynomial time. We also consider the problem of maximizing a symmetric submodular function under a single matroid constraint and show that the (1 + 1) EA using our operator finds a (1/3)-approximation within polynomial time. This performance matches that of combinatorial local search algorithms specifically designed to solve these problems and outperforms them with constant probability. Finally, we evaluate the performance of the (1 + 1) EA using our operator experimentally by considering two applications: (a) the maximum directed cut problem on real-world graphs of different origins, with up to 6.6 million vertices and 56 million edges and (b) the symmetric mutual information problem using a four month period air pollution data set. In comparison with uniform mutation and a recently proposed dynamic scheme, our operator comes out on top on these instances.},
  language  = {en}
}
@article{Henkenjohann2021,
  author    = {Henkenjohann, Richard},
  title     = {Role of individual motivations and privacy concerns in the adoption of German electronic patient record apps},
  series = {International journal of environmental research and public health : IJERPH / Molecular Diversity Preservation International},
  volume    = {18},
  journal   = {International journal of environmental research and public health : IJERPH / Molecular Diversity Preservation International},
  number    = {18},
  publisher = {MDPI},
  address   = {Basel},
  issn      = {1660-4601},
  doi       = {10.3390/ijerph18189553},
  pages     = {31},
  year      = {2021},
  abstract  = {Germany's electronic patient record ("ePA") launched in 2021 with several attempts and years of delay. The development of such a large-scale project is a complex task, and so is its adoption. Individual attitudes towards an electronic health record are crucial, as individuals can reject opting-in to it and making any national efforts unachievable. Although the integration of an electronic health record serves potential benefits, it also constitutes risks for an individual's privacy. With a mixed-methods study design, this work provides evidence that different types of motivations and contextual privacy antecedents affect usage intentions towards the ePA. Most significantly, individual motivations stemming from feelings of volition or external mandates positively affect ePA adoption, although internal incentives are more powerful.},
  language  = {en}
}
@article{ShekharReimannMayeretal.2021,
  author    = {Shekhar, Sumit and Reimann, Max and Mayer, Maximilian and Semmo, Amir and Pasewaldt, Sebastian and D{\"o}llner, J{\"u}rgen and Trapp, Matthias},
  title     = {Interactive photo editing on smartphones via intrinsic decomposition},
  series = {Computer graphics forum : journal of the European Association for Computer Graphics},
  volume    = {40},
  journal   = {Computer graphics forum : journal of the European Association for Computer Graphics},
  publisher = {Blackwell},
  address   = {Oxford},
  issn      = {0167-7055},
  doi       = {10.1111/cgf.142650},
  pages     = {497 -- 510},
  year      = {2021},
  abstract  = {Intrinsic decomposition refers to the problem of estimating scene characteristics, such as albedo and shading, when one view or multiple views of a scene are provided. The inverse problem setting, where multiple unknowns are solved given a single known pixel-value, is highly under-constrained. When provided with correlating image and depth data, intrinsic scene decomposition can be facilitated using depth-based priors, which nowadays is easy to acquire with high-end smartphones by utilizing their depth sensors. In this work, we present a system for intrinsic decomposition of RGB-D images on smartphones and the algorithmic as well as design choices therein. Unlike state-of-the-art methods that assume only diffuse reflectance, we consider both diffuse and specular pixels. For this purpose, we present a novel specularity extraction algorithm based on a multi-scale intensity decomposition and chroma inpainting. At this, the diffuse component is further decomposed into albedo and shading components. We use an inertial proximal algorithm for non-convex optimization (iPiano) to ensure albedo sparsity. Our GPU-based visual processing is implemented on iOS via the Metal API and enables interactive performance on an iPhone 11 Pro. Further, a qualitative evaluation shows that we are able to obtain high-quality outputs. Furthermore, our proposed approach for specularity removal outperforms state-of-the-art approaches for real-world images, while our albedo and shading layer decomposition is faster than the prior work at a comparable output quality. Manifold applications such as recoloring, retexturing, relighting, appearance editing, and stylization are shown, each using the intrinsic layers obtained with our method and/or the corresponding depth data.},
  language  = {en}
}
@article{SchneiderLambersOrejas2021,
  author    = {Schneider, Sven and Lambers, Leen and Orejas, Fernando},
  title     = {A logic-based incremental approach to graph repair featuring delta preservation},
  series = {International journal on software tools for technology transfer : STTT},
  volume    = {23},
  journal   = {International journal on software tools for technology transfer : STTT},
  number    = {3},
  publisher = {Springer},
  address   = {Berlin ; Heidelberg},
  issn      = {1433-2779},
  doi       = {10.1007/s10009-020-00584-x},
  pages     = {369 -- 410},
  year      = {2021},
  abstract  = {We introduce a logic-based incremental approach to graph repair, generating a sound and complete (upon termination) overview of least-changing graph repairs from which a user may select a graph repair based on non-formalized further requirements. This incremental approach features delta preservation as it allows to restrict the generation of graph repairs to delta-preserving graph repairs, which do not revert the additions and deletions of the most recent consistency-violating graph update. We specify consistency of graphs using the logic of nested graph conditions, which is equivalent to first-order logic on graphs. Technically, the incremental approach encodes if and how the graph under repair satisfies a graph condition using the novel data structure of satisfaction trees, which are adapted incrementally according to the graph updates applied. In addition to the incremental approach, we also present two state-based graph repair algorithms, which restore consistency of a graph independent of the most recent graph update and which generate additional graph repairs using a global perspective on the graph under repair. We evaluate the developed algorithms using our prototypical implementation in the tool AutoGraph and illustrate our incremental approach using a case study from the graph database domain.},
  language  = {en}
}
@article{OlamoyegunRaimiAlaetal.2020,
  author    = {Olamoyegun, Michael Adeyemi and Raimi, Taiwo Hassan and Ala, Oluwabukola Ayodele and Fadare, Joseph Olusesan},
  title     = {Mobile phone ownership and willingness to receive mHealth services among patients with diabetes mellitus in South-West, Nigeria},
  series = {Pan African medical journal : PAMJ},
  volume    = {37},
  journal   = {Pan African medical journal : PAMJ},
  publisher = {African Field Epidemiology Network (AFENET)},
  address   = {Kampala, Uganda},
  issn      = {1937-8688},
  doi       = {10.11604/pamj.2020.37.29.25174},
  pages     = {13},
  year      = {2020},
  abstract  = {Introduction: mobile phone technology is increasingly used to overcome traditional barriers to limiting access to diabetes care. This study evaluated mobile phone ownership and willingness to receive and pay for mobile phone-based diabetic services among people with diabetes in South-West, Nigeria. Methods: two hundred and fifty nine patients with diabetes were consecutively recruited from three tertiary health institutions in South-West, Nigeria. Questionnaire was used to evaluate mobile phone ownership, willingness to receive and pay for mobile phone-based diabetic health care services via voice call and text messaging. Results: 97.3\% owned a mobile phone, with 38.9\% and 61.1\% owning smartphone and basic phone respectively. Males were significantly more willing to receive mobile-phone-based health services than females (81.1\% vs 68.1\%, p=0.025), likewise married compared to unmarried [77.4\% vs 57.1\%, p=0.0361. Voice calls (41.3\%) and text messages (32.4\%), were the most preferred modes of receiving diabetes-related health education with social media (3.1\%) and email (1.5\%) least. Almost three-quarter of participants (72.6\%) who owned mobile phone, were willing to receive mobile phone-based diabetes health services. The educational status of patients (adjusted OR [AORJ: 1.7(95\% CI: 1.6 to 2.11), glucometers possession (ACM: 2.0 [95\% CI: 1.9 to 2.1) and type of mobile phone owned (AOR: 2.9 [95\% CI: 2.8 to 5.0]) were significantly associated with the willingness to receive mobile phone-based diabetic services. Conclusion: the majority of study participants owned mobile phones and would be willing to receive and pay for diabetes-related healthcare delivery services provided the cost is minimal and affordable.},
  language  = {en}
}
@article{SigelSwartzGoldenetal.2020,
  author    = {Sigel, Keith Magnus and Swartz, Talia H. and Golden, Eddye and Paranjpe, Ishan and Somani, Sulaiman and Richter, Felix and De Freitas, Jessica K. and Miotto, Riccardo and Zhao, Shan and Polak, Paz and Mutetwa, Tinaye and Factor, Stephanie and Mehandru, Saurabh and Mullen, Michael and Cossarini, Francesca and B{\"o}ttinger, Erwin and Fayad, Zahi and Merad, Miriam and Gnjatic, Sacha and Aberg, Judith and Charney, Alexander and Nadkarni, Girish and Glicksberg, Benjamin S.},
  title     = {Coronavirus 2019 and people living with human immunodeficiency virus},
  series = {Clinical infectious diseases : electronic edition},
  volume    = {71},
  journal   = {Clinical infectious diseases : electronic edition},
  number    = {11},
  publisher = {Oxford Univ. Press},
  address   = {Cary, NC},
  issn      = {1058-4838},
  doi       = {10.1093/cid/ciaa880},
  pages     = {2933 -- 2938},
  year      = {2020},
  abstract  = {Background: There are limited data regarding the clinical impact of coronavirus disease 2019 (COVID-19) on people living with human immunodeficiency virus (PLWH). In this study, we compared outcomes for PLWH with COVID-19 to a matched comparison group. Methods: We identified 88 PLWH hospitalized with laboratory-confirmed COVID-19 in our hospital system in New York City between 12 March and 23 April 2020. We collected data on baseline clinical characteristics, laboratory values, HIV status, treatment, and outcomes from this group and matched comparators (1 PLWH to up to 5 patients by age, sex, race/ethnicity, and calendar week of infection). We compared clinical characteristics and outcomes (death, mechanical ventilation, hospital discharge) for these groups, as well as cumulative incidence of death by HIV status. Results: Patients did not differ significantly by HIV status by age, sex, or race/ethnicity due to the matching algorithm. PLWH hospitalized with COVID-19 had high proportions of HIV virologic control on antiretroviral therapy. PLWH had greater proportions of smoking (P < .001) and comorbid illness than uninfected comparators. There was no difference in COVID-19 severity on admission by HIV status (P = .15). Poor outcomes for hospitalized PLWH were frequent but similar to proportions in comparators; 18\% required mechanical ventilation and 21\% died during follow-up (compared with 23\% and 20\%, respectively). There was similar cumulative incidence of death over time by HIV status (P = .94). Conclusions: We found no differences in adverse outcomes associated with HIV infection for hospitalized COVID-19 patients compared with a demographically similar patient group.},
  language  = {en}
}
@article{DoerrKrejca2020,
  author    = {Doerr, Benjamin and Krejca, Martin S.},
  title     = {Significance-based estimation-of-distribution algorithms},
  series = {IEEE transactions on evolutionary computation},
  volume    = {24},
  journal   = {IEEE transactions on evolutionary computation},
  number    = {6},
  publisher = {Institute of Electrical and Electronics Engineers},
  address   = {New York, NY},
  issn      = {1089-778X},
  doi       = {10.1109/TEVC.2019.2956633},
  pages     = {1025 -- 1034},
  year      = {2020},
  abstract  = {Estimation-of-distribution algorithms (EDAs) are randomized search heuristics that create a probabilistic model of the solution space, which is updated iteratively, based on the quality of the solutions sampled according to the model. As previous works show, this iteration-based perspective can lead to erratic updates of the model, in particular, to bit-frequencies approaching a random boundary value. In order to overcome this problem, we propose a new EDA based on the classic compact genetic algorithm (cGA) that takes into account a longer history of samples and updates its model only with respect to information which it classifies as statistically significant. We prove that this significance-based cGA (sig-cGA) optimizes the commonly regarded benchmark functions OneMax (OM), LeadingOnes, and BinVal all in quasilinear time, a result shown for no other EDA or evolutionary algorithm so far. For the recently proposed stable compact genetic algorithm-an EDA that tries to prevent erratic model updates by imposing a bias to the uniformly distributed model-we prove that it optimizes OM only in a time exponential in its hypothetical population size. Similarly, we show that the convex search algorithm cannot optimize OM in polynomial time.},
  language  = {en}
}
@article{ThamsenBeilharzVinhThuyTranetal.2020,
  author    = {Thamsen, Lauritz and Beilharz, Jossekin Jakob and Vinh Thuy Tran, and Nedelkoski, Sasho and Kao, Odej},
  title     = {Mary, Hugo, and Hugo*},
  series = {Concurrency and computation : practice \& experience},
  volume    = {33},
  journal   = {Concurrency and computation : practice \& experience},
  number    = {18},
  publisher = {Wiley},
  address   = {Hoboken},
  issn      = {1532-0626},
  doi       = {10.1002/cpe.5823},
  pages     = {12},
  year      = {2020},
  abstract  = {Distributed data-parallel processing systems like MapReduce, Spark, and Flink are popular for analyzing large datasets using cluster resources. Resource management systems like YARN or Mesos in turn allow multiple data-parallel processing jobs to share cluster resources in temporary containers. Often, the containers do not isolate resource usage to achieve high degrees of overall resource utilization despite overprovisioning and the often fluctuating utilization of specific jobs. However, some combinations of jobs utilize resources better and interfere less with each other when running on the same shared nodes than others. This article presents an approach for improving the resource utilization and job throughput when scheduling recurring distributed data-parallel processing jobs in shared clusters. The approach is based on reinforcement learning and a measure of co-location goodness to have cluster schedulers learn over time which jobs are best executed together on shared resources. We evaluated this approach over the last years with three prototype schedulers that build on each other: Mary, Hugo, and Hugo*. For the evaluation we used exemplary Flink and Spark jobs from different application domains and clusters of commodity nodes managed by YARN. The results of these experiments show that our approach can increase resource utilization and job throughput significantly.},
  language  = {en}
}
@misc{OosthoekDoerr2020,
  author    = {Oosthoek, Kris and Doerr, Christian},
  title     = {Cyber threat intelligence: A product without a process?},
  series = {International journal of intelligence and counterintelligence},
  volume    = {34},
  journal   = {International journal of intelligence and counterintelligence},
  number    = {2},
  publisher = {Taylor \& Francis},
  address   = {London},
  issn      = {0885-0607},
  doi       = {10.1080/08850607.2020.1780062},
  pages     = {300 -- 315},
  year      = {2020},
  language  = {en}
}
@article{BirnickBlaesiusFriedrichetal.2020,
  author    = {Birnick, Johann and Bl{\"a}sius, Thomas and Friedrich, Tobias and Naumann, Felix and Papenbrock, Thorsten and Schirneck, Friedrich Martin},
  title     = {Hitting set enumeration with partial information for unique column combination discovery},
  series = {Proceedings of the VLDB Endowment},
  volume    = {13},
  journal   = {Proceedings of the VLDB Endowment},
  number    = {11},
  publisher = {Association for Computing Machinery},
  address   = {[New York, NY]},
  issn      = {2150-8097},
  doi       = {10.14778/3407790.3407824},
  pages     = {2270 -- 2283},
  year      = {2020},
  abstract  = {Unique column combinations (UCCs) are a fundamental concept in relational databases. They identify entities in the data and support various data management activities. Still, UCCs are usually not explicitly defined and need to be discovered. State-of-the-art data profiling algorithms are able to efficiently discover UCCs in moderately sized datasets, but they tend to fail on large and, in particular, on wide datasets due to run time and memory limitations. <br /> In this paper, we introduce HPIValid, a novel UCC discovery algorithm that implements a faster and more resource-saving search strategy. HPIValid models the metadata discovery as a hitting set enumeration problem in hypergraphs. In this way, it combines efficient discovery techniques from data profiling research with the most recent theoretical insights into enumeration algorithms. Our evaluation shows that HPIValid is not only orders of magnitude faster than related work, it also has a much smaller memory footprint.},
  language  = {en}
}
@article{LewkowiczWohlbrandtBoettinger2022,
  author    = {Lewkowicz, Daniel and Wohlbrandt, Attila M. and B{\"o}ttinger, Erwin},
  title     = {Digital therapeutic care apps with decision-support interventions for people with low back pain in Germany},
  series = {JMIR mhealth and uhealth},
  volume    = {10},
  journal   = {JMIR mhealth and uhealth},
  number    = {2},
  publisher = {JMIR Publications},
  address   = {Toronto},
  issn      = {2291-5222},
  doi       = {10.2196/35042},
  pages     = {17},
  year      = {2022},
  abstract  = {Background: Digital therapeutic care apps provide a new effective and scalable approach for people with nonspecific low back pain (LBP). Digital therapeutic care apps are also driven by personalized decision-support interventions that support the user in self-managing LBP, and may induce prolonged behavior change to reduce the frequency and intensity of pain episodes. However, these therapeutic apps are associated with high attrition rates, and the initial prescription cost is higher than that of face-to-face physiotherapy. In Germany, digital therapeutic care apps are now being reimbursed by statutory health insurance; however, price targets and cost-driving factors for the formation of the reimbursement rate remain unexplored. Objective: The aim of this study was to evaluate the cost-effectiveness of a digital therapeutic care app compared to treatment as usual (TAU) in Germany. We further aimed to explore under which circumstances the reimbursement rate could be modified to consider value-based pricing. Methods: We developed a state-transition Markov model based on a best-practice analysis of prior LBP-related decision-analytic models, and evaluated the cost utility of a digital therapeutic care app compared to TAU in Germany. Based on a 3-year time horizon, we simulated the incremental cost and quality-adjusted life years (QALYs) for people with nonacute LBP from the societal perspective. In the deterministic sensitivity and scenario analyses, we focused on diverging attrition rates and app cost to assess our model's robustness and conditions for changing the reimbursement rate. All costs are reported in Euro (euro1=US \$1.12). Results: Our base case results indicated that the digital therapeutic care strategy led to an incremental cost of euro121.59, but also generated 0.0221 additional QALYs compared to the TAU strategy, with an estimated incremental cost-effectiveness ratio (ICER) of euro5486 per QALY. The sensitivity analysis revealed that the reimbursement rate and the capability of digital therapeutic care to prevent reoccurring LBP episodes have a significant impact on the ICER. At the same time, the other parameters remained unaffected and thus supported the robustness of our model. In the scenario analysis, the different model time horizons and attrition rates strongly influenced the economic outcome. Reducing the cost of the app to euro99 per 3 months or decreasing the app's attrition rate resulted in digital therapeutic care being significantly less costly with more generated QALYs, and is thus considered to be the dominant strategy over TAU. Conclusions: The current reimbursement rate for a digital therapeutic care app in the statutory health insurance can be considered a cost-effective measure compared to TAU. The app's attrition rate and effect on the patient's prolonged behavior change essentially influence the settlement of an appropriate reimbursement rate. Future value-based pricing targets should focus on additional outcome parameters besides pain intensity and functional disability by including attrition rates and the app's long-term effect on quality of life.},
  language  = {en}
}
@article{KulahciogluMelo2020,
  author    = {Kulahcioglu, Tugba and Melo, Gerard de},
  title     = {Affect-aware word clouds},
  series = {ACM transactions on interactive intelligent systems},
  volume    = {10},
  journal   = {ACM transactions on interactive intelligent systems},
  number    = {4},
  publisher = {Association for Computing Machinery},
  address   = {New York, NY},
  issn      = {2160-6455},
  doi       = {10.1145/3370928},
  pages     = {25},
  year      = {2020},
  abstract  = {Word clouds are widely used for non-analytic purposes, such as introducing a topic to students, or creating a gift with personally meaningful text. Surveys show that users prefer tools that yield word clouds with a stronger emotional impact. Fonts and color palettes are powerful typographical signals that may determine this impact. Typically, these signals are assigned randomly, or expected to be chosen by the users. We present an affect-aware font and color palette selection methodology that aims to facilitate more informed choices. We infer associations of fonts with a set of eight affects, and evaluate the resulting data in a series of user studies both on individual words as well as in word clouds. Relying on a recent study to procure affective color palettes, we carry out a similar user study to understand the impact of color choices on word clouds. Our findings suggest that both fonts and color palettes are powerful tools contributing to the affects evoked by a word cloud. The experiments further confirm that the novel datasets we propose are successful in enabling this. We also find that, for the majority of the affects, both signals need to be congruent to create a stronger impact. Based on this data, we implement a prototype that allows users to specify a desired affect and recommends congruent fonts and color palettes for the word.},
  language  = {en}
}
@article{KrejcaWitt2020,
  author    = {Krejca, Martin S. and Witt, Carsten},
  title     = {Lower bounds on the run time of the Univariate Marginal Distribution Algorithm on OneMax},
  series = {Theoretical computer science : the journal of the EATCS},
  volume    = {832},
  journal   = {Theoretical computer science : the journal of the EATCS},
  publisher = {Elsevier},
  address   = {Amsterdam [u.a.]},
  issn      = {0304-3975},
  doi       = {10.1016/j.tcs.2018.06.004},
  pages     = {143 -- 165},
  year      = {2020},
  abstract  = {The Univariate Marginal Distribution Algorithm (UMDA) - a popular estimation-of-distribution algorithm - is studied from a run time perspective. On the classical OneMax benchmark function on bit strings of length n, a lower bound of Omega(lambda + mu root n + n logn), where mu and lambda are algorithm-specific parameters, on its expected run time is proved. This is the first direct lower bound on the run time of UMDA. It is stronger than the bounds that follow from general black-box complexity theory and is matched by the run time of many evolutionary algorithms. The results are obtained through advanced analyses of the stochastic change of the frequencies of bit values maintained by the algorithm, including carefully designed potential functions. These techniques may prove useful in advancing the field of run time analysis for estimation-of-distribution algorithms in general.},
  language  = {en}
}
@article{BohnKundisch2020,
  author    = {Bohn, Nicolai and Kundisch, Dennis},
  title     = {What are we talking about when we talk about technology pivots?},
  series = {Information \& management},
  volume    = {57},
  journal   = {Information \& management},
  number    = {6},
  publisher = {Elsevier},
  address   = {Amsterdam},
  issn      = {0378-7206},
  doi       = {10.1016/j.im.2020.103319},
  pages     = {20},
  year      = {2020},
  abstract  = {Technology pivots were designed to help digital startups make adjustments to the technology underpinning their products and services. While academia and the media make liberal use of the term "technology pivot," they rarely align themselves to Ries' foundational conceptualization. Recent research suggests that a more granulated conceptualization of technology pivots is required. To scientifically derive a comprehensive conceptualization, we conduct a Delphi study with a panel of 38 experts drawn from academia and practice to explore their understanding of "technology pivots." Our study thus makes an important contribution to advance the seminal work by Ries on technology pivots.},
  language  = {en}
}
@article{LambersWeber2020,
  author    = {Lambers, Leen and Weber, Jens},
  title     = {Preface to the special issue on the 11th International Conference on Graph Transformation},
  series = {Journal of Logical and Algebraic Methods in Programming},
  volume    = {112},
  journal   = {Journal of Logical and Algebraic Methods in Programming},
  publisher = {Elsevier},
  address   = {Amsterdam},
  issn      = {2352-2208},
  doi       = {10.1016/j.jlamp.2020.100525},
  pages     = {2},
  year      = {2020},
  abstract  = {This special issue contains extended versions of four selected papers from the 11th International Conference on Graph Transformation (ICGT 2018). The articles cover a tool for computing core graphs via SAT/SMT solvers (graph language definition), graph transformation through graph surfing in reaction systems (a new graph transformation formalism), the essence and initiality of conflicts in M-adhesive transformation systems, and a calculus of concurrent graph-rewriting processes (theory on conflicts and parallel independence).},
  language  = {en}
}
@article{CopeBaukmannKlingeretal.2021,
  author    = {Cope, Justin L. and Baukmann, Hannes A. and Klinger, J{\"o}rn E. and Ravarani, Charles N. J. and B{\"o}ttinger, Erwin and Konigorski, Stefan and Schmidt, Marco F.},
  title     = {Interaction-based feature selection algorithm outperforms polygenic risk score in predicting Parkinson's Disease status},
  series = {Frontiers in genetics},
  volume    = {12},
  journal   = {Frontiers in genetics},
  publisher = {Frontiers Media},
  address   = {Lausanne},
  issn      = {1664-8021},
  doi       = {10.3389/fgene.2021.744557},
  pages     = {9},
  year      = {2021},
  abstract  = {Polygenic risk scores (PRS) aggregating results from genome-wide association studies are the state of the art in the prediction of susceptibility to complex traits or diseases, yet their predictive performance is limited for various reasons, not least of which is their failure to incorporate the effects of gene-gene interactions. Novel machine learning algorithms that use large amounts of data promise to find gene-gene interactions in order to build models with better predictive performance than PRS. Here, we present a data preprocessing step by using data-mining of contextual information to reduce the number of features, enabling machine learning algorithms to identify gene-gene interactions. We applied our approach to the Parkinson's Progression Markers Initiative (PPMI) dataset, an observational clinical study of 471 genotyped subjects (368 cases and 152 controls). With an AUC of 0.85 (95\% CI = [0.72; 0.96]), the interaction-based prediction model outperforms the PRS (AUC of 0.58 (95\% CI = [0.42; 0.81])). Furthermore, feature importance analysis of the model provided insights into the mechanism of Parkinson's disease. For instance, the model revealed an interaction of previously described drug target candidate genes TMEM175 and GAPDHP25. These results demonstrate that interaction-based machine learning models can improve genetic prediction models and might provide an answer to the missing heritability problem.},
  language  = {en}
}
@article{SiddiqiDoerrStrydis2020,
  author    = {Siddiqi, Muhammad Ali and D{\"o}rr, Christian and Strydis, Christos},
  title     = {IMDfence},
  series = {IEEE access},
  volume    = {8},
  journal   = {IEEE access},
  publisher = {Institute of Electrical and Electronics Engineers},
  address   = {Piscataway},
  issn      = {2169-3536},
  doi       = {10.1109/ACCESS.2020.3015686},
  pages     = {147948 -- 147964},
  year      = {2020},
  abstract  = {Over the past decade, focus on the security and privacy aspects of implantable medical devices (IMDs) has intensified, driven by the multitude of cybersecurity vulnerabilities found in various existing devices. However, due to their strict computational, energy and physical constraints, conventional security protocols are not directly applicable to IMDs. Custom-tailored schemes have been proposed instead which, however, fail to cover the full spectrum of security features that modern IMDs and their ecosystems so critically require. In this paper we propose IMDfence, a security protocol for IMD ecosystems that provides a comprehensive yet practical security portfolio, which includes availability, non-repudiation, access control, entity authentication, remote monitoring and system scalability. The protocol also allows emergency access that results in the graceful degradation of offered services without compromising security and patient safety. The performance of the security protocol as well as its feasibility and impact on modern IMDs are extensively analyzed and evaluated. We find that IMDfence achieves the above security requirements at a mere less than 7\% increase in total IMD energy consumption, and less than 14 ms and 9 kB increase in system delay and memory footprint, respectively.},
  language  = {en}
}
@article{DellepianeVaidJaladankietal.2021,
  author    = {Dellepiane, Sergio and Vaid, Akhil and Jaladanki, Suraj K. and Coca, Steven and Fayad, Zahi A. and Charney, Alexander W. and B{\"o}ttinger, Erwin and He, John Cijiang and Glicksberg, Benjamin S. and Chan, Lili and Nadkarni, Girish},
  title     = {Acute kidney injury in patients hospitalized with COVID-19 in New York City},
  series = {Kidney medicine},
  volume    = {3},
  journal   = {Kidney medicine},
  number    = {5},
  publisher = {Elsevier},
  address   = {Amsterdam},
  issn      = {2590-0595},
  doi       = {10.1016/j.xkme.2021.06.008},
  pages     = {877 -- 879},
  year      = {2021},
  language  = {en}
}
@article{KoetzingLagodzinskiLengleretal.2020,
  author    = {K{\"o}tzing, Timo and Lagodzinski, Gregor J. A. and Lengler, Johannes and Melnichenko, Anna},
  title     = {Destructiveness of lexicographic parsimony pressure and alleviation by a concatenation crossover in genetic programming},
  series = {Theoretical computer science},
  volume    = {816},
  journal   = {Theoretical computer science},
  publisher = {Elsevier},
  address   = {Amsterdam},
  issn      = {0304-3975},
  doi       = {10.1016/j.tcs.2019.11.036},
  pages     = {96 -- 113},
  year      = {2020},
  abstract  = {For theoretical analyses there are two specifics distinguishing GP from many other areas of evolutionary computation: the variable size representations, in particular yielding a possible bloat (i.e. the growth of individuals with redundant parts); and also the role and the realization of crossover, which is particularly central in GP due to the tree-based representation. Whereas some theoretical work on GP has studied the effects of bloat, crossover had surprisingly little share in this work. <br /> We analyze a simple crossover operator in combination with randomized local search, where a preference for small solutions minimizes bloat (lexicographic parsimony pressure); we denote the resulting algorithm Concatenation Crossover GP. We consider three variants of the well-studied MAJORITY test function, adding large plateaus in different ways to the fitness landscape and thus giving a test bed for analyzing the interplay of variation operators and bloat control mechanisms in a setting with local optima. We show that the Concatenation Crossover GP can efficiently optimize these test functions, while local search cannot be efficient for all three variants independent of employing bloat control. (C) 2019 Elsevier B.V. All rights reserved.},
  language  = {en}
}
@article{HackerKrestelGrundmannetal.2020,
  author    = {Hacker, Philipp and Krestel, Ralf and Grundmann, Stefan and Naumann, Felix},
  title     = {Explainable AI under contract and tort law},
  series = {Artificial intelligence and law},
  volume    = {28},
  journal   = {Artificial intelligence and law},
  number    = {4},
  publisher = {Springer},
  address   = {Dordrecht},
  issn      = {0924-8463},
  doi       = {10.1007/s10506-020-09260-6},
  pages     = {415 -- 439},
  year      = {2020},
  abstract  = {This paper shows that the law, in subtle ways, may set hitherto unrecognized incentives for the adoption of explainable machine learning applications. In doing so, we make two novel contributions. First, on the legal side, we show that to avoid liability, professional actors, such as doctors and managers, may soon be legally compelled to use explainable ML models. We argue that the importance of explainability reaches far beyond data protection law, and crucially influences questions of contractual and tort liability for the use of ML models. To this effect, we conduct two legal case studies, in medical and corporate merger applications of ML. As a second contribution, we discuss the (legally required) trade-off between accuracy and explainability and demonstrate the effect in a technical case study in the context of spam classification.},
  language  = {en}
}
@article{KaitouaRablMarkl2020,
  author    = {Kaitoua, Abdulrahman and Rabl, Tilmann and Markl, Volker},
  title     = {A distributed data exchange engine for polystores},
  series = {Information technology : methods and applications of informatics and information technology},
  volume    = {62},
  journal   = {Information technology : methods and applications of informatics and information technology},
  number    = {3-4},
  publisher = {De Gruyter},
  address   = {Berlin},
  issn      = {1611-2776},
  doi       = {10.1515/itit-2019-0037},
  pages     = {145 -- 156},
  year      = {2020},
  abstract  = {There is an increasing interest in fusing data from heterogeneous sources. Combining data sources increases the utility of existing datasets, generating new information and creating services of higher quality. A central issue in working with heterogeneous sources is data migration: In order to share and process data in different engines, resource intensive and complex movements and transformations between computing engines, services, and stores are necessary. Muses is a distributed, high-performance data migration engine that is able to interconnect distributed data stores by forwarding, transforming, repartitioning, or broadcasting data among distributed engines' instances in a resource-, cost-, and performance-adaptive manner. As such, it performs seamless information sharing across all participating resources in a standard, modular manner. We show an overall improvement of 30 \% for pipelining jobs across multiple engines, even when we count the overhead of Muses in the execution time. This performance gain implies that Muses can be used to optimise large pipelines that leverage multiple engines.},
  language  = {en}
}
@article{IsailovićStojanovicTrappetal.2020,
  author    = {Isailović, Dušan and Stojanovic, Vladeta and Trapp, Matthias and Richter, Rico and Hajdin, Rade and D{\"o}llner, J{\"u}rgen Roland Friedrich},
  title     = {Bridge damage},
  series = {Automation in construction : an international research journal},
  volume    = {112},
  journal   = {Automation in construction : an international research journal},
  publisher = {Elsevier},
  address   = {Amsterdam},
  issn      = {0926-5805},
  doi       = {10.1016/j.autcon.2020.103088},
  pages     = {22},
  year      = {2020},
  abstract  = {Building Information Modeling (BIM) representations of bridges enriched by inspection data will add tremendous value to future Bridge Management Systems (BMSs). This paper presents an approach for point cloud-based detection of spalling damage, as well as integrating damage components into a BIM via semantic enrichment of an as-built Industry Foundation Classes (IFC) model. An approach for generating the as-built BIM, geometric reconstruction of detected damage point clusters and semantic-enrichment of the corresponding IFC model is presented. Multiview-classification is used and evaluated for the detection of spalling damage features. The semantic enrichment of as-built IFC models is based on injecting classified and reconstructed damage clusters back into the as-built IFC, thus generating an accurate as-is IFC model compliant to the BMS inspection requirements.},
  language  = {en}
}
@article{PfitznerSteckhanArnrich2021,
  author    = {Pfitzner, Bjarne and Steckhan, Nico and Arnrich, Bert},
  title     = {Federated learning in a medical context},
  series = {ACM transactions on internet technology : TOIT / Association for Computing},
  volume    = {21},
  journal   = {ACM transactions on internet technology : TOIT / Association for Computing},
  number    = {2},
  publisher = {Association for Computing Machinery},
  address   = {New York},
  issn      = {1533-5399},
  doi       = {10.1145/3412357},
  pages     = {1 -- 31},
  year      = {2021},
  abstract  = {Data privacy is a very important issue. Especially in fields like medicine, it is paramount to abide by the existing privacy regulations to preserve patients' anonymity. However, data is required for research and training machine learning models that could help gain insight into complex correlations or personalised treatments that may otherwise stay undiscovered. Those models generally scale with the amount of data available, but the current situation often prohibits building large databases across sites. So it would be beneficial to be able to combine similar or related data from different sites all over the world while still preserving data privacy. Federated learning has been proposed as a solution for this, because it relies on the sharing of machine learning models, instead of the raw data itself. That means private data never leaves the site or device it was collected on. Federated learning is an emerging research area, and many domains have been identified for the application of those methods. This systematic literature review provides an extensive look at the concept of and research into federated learning and its applicability for confidential healthcare datasets.},
  language  = {en}
}
@article{RezaeiNaeppiLippertetal.2020,
  author    = {Rezaei, Mina and N{\"a}ppi, Janne J. and Lippert, Christoph and Meinel, Christoph and Yoshida, Hiroyuki},
  title     = {Generative multi-adversarial network for striking the right balance in abdominal image segmentation},
  series = {International journal of computer assisted radiology and surgery},
  volume    = {15},
  journal   = {International journal of computer assisted radiology and surgery},
  number    = {11},
  publisher = {Springer},
  address   = {Berlin},
  issn      = {1861-6410},
  doi       = {10.1007/s11548-020-02254-4},
  pages     = {1847 -- 1858},
  year      = {2020},
  abstract  = {Purpose: The identification of abnormalities that are relatively rare within otherwise normal anatomy is a major challenge for deep learning in the semantic segmentation of medical images. The small number of samples of the minority classes in the training data makes the learning of optimal classification challenging, while the more frequently occurring samples of the majority class hamper the generalization of the classification boundary between infrequently occurring target objects and classes. In this paper, we developed a novel generative multi-adversarial network, called Ensemble-GAN, for mitigating this class imbalance problem in the semantic segmentation of abdominal images. Method: The Ensemble-GAN framework is composed of a single-generator and a multi-discriminator variant for handling the class imbalance problem to provide a better generalization than existing approaches. The ensemble model aggregates the estimates of multiple models by training from different initializations and losses from various subsets of the training data. The single generator network analyzes the input image as a condition to predict a corresponding semantic segmentation image by use of feedback from the ensemble of discriminator networks. To evaluate the framework, we trained our framework on two public datasets, with different imbalance ratios and imaging modalities: the Chaos 2019 and the LiTS 2017. Result: In terms of the F1 score, the accuracies of the semantic segmentation of healthy spleen, liver, and left and right kidneys were 0.93, 0.96, 0.90 and 0.94, respectively. The overall F1 scores for simultaneous segmentation of the lesions and liver were 0.83 and 0.94, respectively. Conclusion: The proposed Ensemble-GAN framework demonstrated outstanding performance in the semantic segmentation of medical images in comparison with other approaches on popular abdominal imaging benchmarks. The Ensemble-GAN has the potential to segment abdominal images more accurately than human experts.},
  language  = {en}
}
@article{GhahremaniGieseVogel2020,
  author    = {Ghahremani, Sona and Giese, Holger and Vogel, Thomas},
  title     = {Improving scalability and reward of utility-driven self-healing for large dynamic architectures},
  series = {ACM transactions on autonomous and adaptive systems},
  volume    = {14},
  journal   = {ACM transactions on autonomous and adaptive systems},
  number    = {3},
  publisher = {Association for Computing Machinery},
  address   = {New York},
  issn      = {1556-4665},
  doi       = {10.1145/3380965},
  pages     = {41},
  year      = {2020},
  abstract  = {Self-adaptation can be realized in various ways. Rule-based approaches prescribe the adaptation to be executed if the system or environment satisfies certain conditions. They result in scalable solutions but often with merely satisfying adaptation decisions. In contrast, utility-driven approaches determine optimal decisions by using an often costly optimization, which typically does not scale for large problems. We propose a rule-based and utility-driven adaptation scheme that achieves the benefits of both directions such that the adaptation decisions are optimal, whereas the computation scales by avoiding an expensive optimization. We use this adaptation scheme for architecture-based self-healing of large software systems. For this purpose, we define the utility for large dynamic architectures of such systems based on patterns that define issues the self-healing must address. Moreover, we use pattern-based adaptation rules to resolve these issues. Using a pattern-based scheme to define the utility and adaptation rules allows us to compute the impact of each rule application on the overall utility and to realize an incremental and efficient utility-driven self-healing. In addition to formally analyzing the computational effort and optimality of the proposed scheme, we thoroughly demonstrate its scalability and optimality in terms of reward in comparative experiments with a static rule-based approach as a baseline and a utility-driven approach using a constraint solver. These experiments are based on different failure profiles derived from real-world failure logs. We also investigate the impact of different failure profile characteristics on the scalability and reward to evaluate the robustness of the different approaches.},
  language  = {en}
}
@article{RoseHoelzleBjoerk2020,
  author    = {Rose, Robert and H{\"o}lzle, Katharina and Bj{\"o}rk, Jennie},
  title     = {More than a quarter century of creativity and innovation management},
  series = {Creativity and innovation management},
  volume    = {29},
  journal   = {Creativity and innovation management},
  number    = {1},
  publisher = {Wiley-Blackwell},
  address   = {Oxford},
  issn      = {0963-1690},
  doi       = {10.1111/caim.12361},
  pages     = {5 -- 20},
  year      = {2020},
  abstract  = {When this journal was founded in 1992 by Tudor Rickards and Susan Moger, there was no academic outlet available that addressed issues at the intersection of creativity and innovation. From zero to 1,163 records, from the new kid on the block to one of the leading journals in creativity and innovation management has been quite a journey, and we would like to reflect on the past 28 years and the intellectual and conceptual structure of Creativity and Innovation Management (CIM). Specifically, we highlight milestones and influential articles, identify how key journal characteristics evolved, outline the (co-)authorship structure, and finally, map the thematic landscape of CIM by means of a text-mining analysis. This study represents the first systematic and comprehensive assessment of the journal's published body of knowledge and helps to understand the journal's influence on the creativity and innovation management community. We conclude by discussing future topics and paths of the journal as well as limitations of our approach.},
  language  = {en}
}
@article{DraisbachChristenNaumann2019,
  author    = {Draisbach, Uwe and Christen, Peter and Naumann, Felix},
  title     = {Transforming pairwise duplicates to entity clusters for high-quality duplicate detection},
  series = {ACM Journal of Data and Information Quality},
  volume    = {12},
  journal   = {ACM Journal of Data and Information Quality},
  number    = {1},
  publisher = {Association for Computing Machinery},
  address   = {New York},
  issn      = {1936-1955},
  doi       = {10.1145/3352591},
  pages     = {1 -- 30},
  year      = {2019},
  abstract  = {Duplicate detection algorithms produce clusters of database records, each cluster representing a single real-world entity. As most of these algorithms use pairwise comparisons, the resulting (transitive) clusters can be inconsistent: Not all records within a cluster are sufficiently similar to be classified as duplicate. Thus, one of many subsequent clustering algorithms can further improve the result. <br /> We explain in detail, compare, and evaluate many of these algorithms and introduce three new clustering algorithms in the specific context of duplicate detection. Two of our three new algorithms use the structure of the input graph to create consistent clusters. Our third algorithm, and many other clustering algorithms, focus on the edge weights, instead. For evaluation, in contrast to related work, we experiment on true real-world datasets, and in addition examine in great detail various pair-selection strategies used in practice. While no overall winner emerges, we are able to identify best approaches for different situations. In scenarios with larger clusters, our proposed algorithm, Extended Maximum Clique Clustering (EMCC), and Markov Clustering show the best results. EMCC especially outperforms Markov Clustering regarding the precision of the results and additionally has the advantage that it can also be used in scenarios where edge weights are not available.},
  language  = {en}
}
@article{BiloLenzner2019,
  author    = {Bil{\`o}, Davide and Lenzner, Pascal},
  title     = {On the tree conjecture for the network creation game},
  series = {Theory of computing systems},
  volume    = {64},
  journal   = {Theory of computing systems},
  number    = {3},
  publisher = {Springer},
  address   = {New York},
  issn      = {1432-4350},
  doi       = {10.1007/s00224-019-09945-9},
  pages     = {422 -- 443},
  year      = {2019},
  abstract  = {Selfish Network Creation focuses on modeling real world networks from a game-theoretic point of view. One of the classic models by Fabrikant et al. (2003) is the network creation game, where agents correspond to nodes in a network which buy incident edges for the price of alpha per edge to minimize their total distance to all other nodes. The model is well-studied but still has intriguing open problems. The most famous conjectures state that the price of anarchy is constant for all alpha and that for alpha >= n all equilibrium networks are trees. We introduce a novel technique for analyzing stable networks for high edge-price alpha and employ it to improve on the best known bound for the latter conjecture. In particular we show that for alpha > 4n - 13 all equilibrium networks must be trees, which implies a constant price of anarchy for this range of alpha. Moreover, we also improve the constant upper bound on the price of anarchy for equilibrium trees.},
  language  = {en}
}
@article{KastiusSchlosser2022,
  author    = {Kastius, Alexander and Schlosser, Rainer},
  title     = {Dynamic pricing under competition using reinforcement learning},
  series = {Journal of revenue and pricing management},
  volume    = {21},
  journal   = {Journal of revenue and pricing management},
  number    = {1},
  publisher = {Springer Nature Switzerland AG},
  address   = {Cham},
  issn      = {1476-6930},
  doi       = {10.1057/s41272-021-00285-3},
  pages     = {50 -- 63},
  year      = {2022},
  abstract  = {Dynamic pricing is considered a possibility to gain an advantage over competitors in modern online markets. The past advancements in Reinforcement Learning (RL) provided more capable algorithms that can be used to solve pricing problems. In this paper, we study the performance of Deep Q-Networks (DQN) and Soft Actor Critic (SAC) in different market models. We consider tractable duopoly settings, where optimal solutions derived by dynamic programming techniques can be used for verification, as well as oligopoly settings, which are usually intractable due to the curse of dimensionality. We find that both algorithms provide reasonable results, while SAC performs better than DQN. Moreover, we show that under certain conditions, RL algorithms can be forced into collusion by their competitors without direct communication.},
  language  = {en}
}
@article{MattisBeckmannReinetal.2022,
  author    = {Mattis, Toni and Beckmann, Tom and Rein, Patrick and Hirschfeld, Robert},
  title     = {First-class concepts},
  series = {Journal of object technology : JOT / ETH Z{\"u}rich, Department of Computer Science},
  volume    = {21},
  journal   = {Journal of object technology : JOT / ETH Z{\"u}rich, Department of Computer Science},
  number    = {2},
  publisher = {ETH Z{\"u}rich, Department of Computer Science},
  address   = {Z{\"u}rich},
  issn      = {1660-1769},
  doi       = {10.5381/jot.2022.21.2.a6},
  pages     = {1 -- 15},
  year      = {2022},
  abstract  = {Ideally, programs are partitioned into independently maintainable and understandable modules. As a system grows, its architecture gradually loses the capability to accommodate new concepts in a modular way. While refactoring is expensive and not always possible, and the programming language might lack dedicated primary language constructs to express certain cross-cutting concerns, programmers are still able to explain and delineate convoluted concepts through secondary means: code comments, use of whitespace and arrangement of code, documentation, or communicating tacit knowledge. <br /> Secondary constructs are easy to change and provide high flexibility in communicating cross-cutting concerns and other concepts among programmers. However, such secondary constructs usually have no reified representation that can be explored and manipulated as first-class entities through the programming environment. <br /> In this exploratory work, we discuss novel ways to express a wide range of concepts, including cross-cutting concerns, patterns, and lifecycle artifacts independently of the dominant decomposition imposed by an existing architecture. We propose the representation of concepts as first-class objects inside the programming environment that retain the capability to change as easily as code comments. We explore new tools that allow programmers to view, navigate, and change programs based on conceptual perspectives. In a small case study, we demonstrate how such views can be created and how the programming experience changes from draining programmers' attention by stretching it across multiple modules toward focusing it on cohesively presented concepts. Our designs are geared toward facilitating multiple secondary perspectives on a system to co-exist in symbiosis with the original architecture, hence making it easier to explore, understand, and explain complex contexts and narratives that are hard or impossible to express using primary modularity constructs.},
  language  = {en}
}
@article{Doellner2020,
  author    = {D{\"o}llner, J{\"u}rgen Roland Friedrich},
  title     = {Geospatial artificial intelligence},
  series = {Journal of photogrammetry, remote sensing and geoinformation science : PFG : Photogrammetrie, Fernerkundung, Geoinformation},
  volume    = {88},
  journal   = {Journal of photogrammetry, remote sensing and geoinformation science : PFG : Photogrammetrie, Fernerkundung, Geoinformation},
  number    = {1},
  publisher = {Springer International Publishing},
  address   = {Cham},
  issn      = {2512-2789},
  doi       = {10.1007/s41064-020-00102-3},
  pages     = {15 -- 24},
  year      = {2020},
  abstract  = {Artificial intelligence (AI) is changing fundamentally the way how IT solutions are implemented and operated across all application domains, including the geospatial domain. This contribution outlines AI-based techniques for 3D point clouds and geospatial digital twins as generic components of geospatial AI. First, we briefly reflect on the term "AI" and outline technology developments needed to apply AI to IT solutions, seen from a software engineering perspective. Next, we characterize 3D point clouds as key category of geodata and their role for creating the basis for geospatial digital twins; we explain the feasibility of machine learning (ML) and deep learning (DL) approaches for 3D point clouds. In particular, we argue that 3D point clouds can be seen as a corpus with similar properties as natural language corpora and formulate a "Naturalness Hypothesis" for 3D point clouds. In the main part, we introduce a workflow for interpreting 3D point clouds based on ML/DL approaches that derive domain-specific and application-specific semantics for 3D point clouds without having to create explicit spatial 3D models or explicit rule sets. Finally, examples are shown how ML/DL enables us to efficiently build and maintain base data for geospatial digital twins such as virtual 3D city models, indoor models, or building information models.},
  language  = {en}
}
@article{GruenerMuehleMeinel2021,
  author    = {Gr{\"u}ner, Andreas and M{\"u}hle, Alexander and Meinel, Christoph},
  title     = {ATIB},
  series = {IEEE access : practical research, open solutions / Institute of Electrical and Electronics Engineers},
  volume    = {9},
  journal   = {IEEE access : practical research, open solutions / Institute of Electrical and Electronics Engineers},
  publisher = {Institute of Electrical and Electronics Engineers},
  address   = {New York, NY},
  issn      = {2169-3536},
  doi       = {10.1109/ACCESS.2021.3116095},
  pages     = {138553 -- 138570},
  year      = {2021},
  abstract  = {Identity management is a principle component of securing online services. In the advancement of traditional identity management patterns, the identity provider remained a Trusted Third Party (TTP). The service provider and the user need to trust a particular identity provider for correct attributes amongst other demands. This paradigm changed with the invention of blockchain-based Self-Sovereign Identity (SSI) solutions that primarily focus on the users. SSI reduces the functional scope of the identity provider to an attribute provider while enabling attribute aggregation. Besides that, the development of new protocols, disregarding established protocols and a significantly fragmented landscape of SSI solutions pose considerable challenges for an adoption by service providers. We propose an Attribute Trust-enhancing Identity Broker (ATIB) to leverage the potential of SSI for trust-enhancing attribute aggregation. Furthermore, ATIB abstracts from a dedicated SSI solution and offers standard protocols. Therefore, it facilitates the adoption by service providers. Despite the brokered integration approach, we show that ATIB provides a high security posture. Additionally, ATIB does not compromise the ten foundational SSI principles for the users.},
  language  = {en}
}
@article{ChromikKirstenHerdicketal.2022,
  author    = {Chromik, Jonas and Kirsten, Kristina and Herdick, Arne and Kappattanavar, Arpita Mallikarjuna and Arnrich, Bert},
  title     = {SensorHub},
  series = {Sensors},
  volume    = {22},
  journal   = {Sensors},
  number    = {1},
  publisher = {MDPI},
  address   = {Basel},
  issn      = {1424-8220},
  doi       = {10.3390/s22010408},
  pages     = {18},
  year      = {2022},
  abstract  = {Observational studies are an important tool for determining whether the findings from controlled experiments can be transferred into scenarios that are closer to subjects' real-life circumstances. A rigorous approach to observational studies involves collecting data from different sensors to comprehensively capture the situation of the subject. However, this leads to technical difficulties especially if the sensors are from different manufacturers, as multiple data collection tools have to run simultaneously. We present SensorHub, a system that can collect data from various wearable devices from different manufacturers, such as inertial measurement units, portable electrocardiographs, portable electroencephalographs, portable photoplethysmographs, and sensors for electrodermal activity. Additionally, our tool offers the possibility to include ecological momentary assessments (EMAs) in studies. Hence, SensorHub enables multimodal sensor data collection under real-world conditions and allows direct user feedback to be collected through questionnaires, enabling studies at home. In a first study with 11 participants, we successfully used SensorHub to record multiple signals with different devices and collected additional information with the help of EMAs. In addition, we evaluated SensorHub's technical capabilities in several trials with up to 21 participants recording simultaneously using multiple sensors with sampling frequencies as high as 1000 Hz. We could show that although there is a theoretical limitation to the transmissible data rate, in practice this limitation is not an issue and data loss is rare. We conclude that with modern communication protocols and with the increasingly powerful smartphones and wearables, a system like our SensorHub establishes an interoperability framework to adequately combine consumer-grade sensing hardware which enables observational studies in real life.},
  language  = {en}
}
@article{Schlosser2020,
  author    = {Schlosser, Rainer},
  title     = {Risk-sensitive control of Markov decision processes},
  series = {Computers \& operations research : and their applications to problems of world concern},
  volume    = {123},
  journal   = {Computers \& operations research : and their applications to problems of world concern},
  publisher = {Elsevier},
  address   = {Oxford},
  issn      = {0305-0548},
  doi       = {10.1016/j.cor.2020.104997},
  pages     = {14},
  year      = {2020},
  abstract  = {In many revenue management applications risk-averse decision-making is crucial. In dynamic settings, however, it is challenging to find the right balance between maximizing expected rewards and minimizing various kinds of risk. In existing approaches utility functions, chance constraints, or (conditional) value at risk considerations are used to influence the distribution of rewards in a preferred way. Nevertheless, common techniques are not flexible enough and typically numerically complex. In our model, we exploit the fact that a distribution is characterized by its mean and higher moments. We present a multi-valued dynamic programming heuristic to compute risk-sensitive feedback policies that are able to directly control the moments of future rewards. Our approach is based on recursive formulations of higher moments and does not require an extension of the state space. Finally, we propose a self-tuning algorithm, which allows to identify feedback policies that approximate predetermined (risk-sensitive) target distributions. We illustrate the effectiveness and the flexibility of our approach for different dynamic pricing scenarios. (C) 2020 Elsevier Ltd. All rights reserved.},
  language  = {en}
}
@article{KoumarelasJiangNaumann2020,
  author    = {Koumarelas, Ioannis and Jiang, Lan and Naumann, Felix},
  title     = {Data preparation for duplicate detection},
  series = {Journal of data and information quality : (JDIQ)},
  volume    = {12},
  journal   = {Journal of data and information quality : (JDIQ)},
  number    = {3},
  publisher = {Association for Computing Machinery},
  address   = {New York},
  issn      = {1936-1955},
  doi       = {10.1145/3377878},
  pages     = {24},
  year      = {2020},
  abstract  = {Data errors represent a major issue in most application workflows. Before any important task can take place, a certain data quality has to be guaranteed by eliminating a number of different errors that may appear in data. Typically, most of these errors are fixed with data preparation methods, such as whitespace removal. However, the particular error of duplicate records, where multiple records refer to the same entity, is usually eliminated independently with specialized techniques. Our work is the first to bring these two areas together by applying data preparation operations under a systematic approach prior to performing duplicate detection. <br /> Our process workflow can be summarized as follows: It begins with the user providing as input a sample of the gold standard, the actual dataset, and optionally some constraints to domain-specific data preparations, such as address normalization. The preparation selection operates in two consecutive phases. First, to vastly reduce the search space of ineffective data preparations, decisions are made based on the improvement or worsening of pair similarities. Second, using the remaining data preparations an iterative leave-one-out classification process removes preparations one by one and determines the redundant preparations based on the achieved area under the precision-recall curve (AUC-PR). Using this workflow, we manage to improve the results of duplicate detection up to 19\% in AUC-PR.},
  language  = {en}
}
@article{DreselerBoissierRabletal.2020,
  author    = {Dreseler, Markus and Boissier, Martin and Rabl, Tilmann and Uflacker, Matthias},
  title     = {Quantifying TPC-H choke points and their optimizations},
  series = {Proceedings of the VLDB Endowment},
  volume    = {13},
  journal   = {Proceedings of the VLDB Endowment},
  number    = {8},
  publisher = {Association for Computing Machinery},
  address   = {New York},
  issn      = {2150-8097},
  doi       = {10.14778/3389133.3389138},
  pages     = {1206 -- 1220},
  year      = {2020},
  abstract  = {TPC-H continues to be the most widely used benchmark for relational OLAP systems. It poses a number of challenges, also known as "choke points", which database systems have to solve in order to achieve good benchmark results. Examples include joins across multiple tables, correlated subqueries, and correlations within the TPC-H data set. Knowing the impact of such optimizations helps in developing optimizers as well as in interpreting TPC-H results across database systems. This paper provides a systematic analysis of choke points and their optimizations. It complements previous work on TPC-H choke points by providing a quantitative discussion of their relevance. It focuses on eleven choke points where the optimizations are beneficial independently of the database system. Of these, the flattening of subqueries and the placement of predicates have the biggest impact. Three queries (Q2, Q17, and Q21) are strongly ifluenced by the choice of an efficient query plan; three others (Q1, Q13, and Q18) are less influenced by plan optimizations and more dependent on an efficient execution engine.},
  language  = {en}
}
@article{CaselFernauGaspersetal.2020,
  author    = {Casel, Katrin and Fernau, Henning and Gaspers, Serge and Gras, Benjamin and Schmid, Markus L.},
  title     = {On the complexity of the smallest grammar problem over fixed alphabets},
  series = {Theory of computing systems},
  volume    = {65},
  journal   = {Theory of computing systems},
  number    = {2},
  publisher = {Springer},
  address   = {New York},
  issn      = {1432-4350},
  doi       = {10.1007/s00224-020-10013-w},
  pages     = {344 -- 409},
  year      = {2020},
  abstract  = {In the smallest grammar problem, we are given a word w and we want to compute a preferably small context-free grammar G for the singleton language {w} (where the size of a grammar is the sum of the sizes of its rules, and the size of a rule is measured by the length of its right side). It is known that, for unbounded alphabets, the decision variant of this problem is NP-hard and the optimisation variant does not allow a polynomial-time approximation scheme, unless P = NP. We settle the long-standing open problem whether these hardness results also hold for the more realistic case of a constant-size alphabet. More precisely, it is shown that the smallest grammar problem remains NP-complete (and its optimisation version is APX-hard), even if the alphabet is fixed and has size of at least 17. The corresponding reduction is robust in the sense that it also works for an alternative size-measure of grammars that is commonly used in the literature (i. e., a size measure also taking the number of rules into account), and it also allows to conclude that even computing the number of rules required by a smallest grammar is a hard problem. On the other hand, if the number of nonterminals (or, equivalently, the number of rules) is bounded by a constant, then the smallest grammar problem can be solved in polynomial time, which is shown by encoding it as a problem on graphs with interval structure. However, treating the number of rules as a parameter (in terms of parameterised complexity) yields W[1]-hardness. Furthermore, we present an O(3(vertical bar w vertical bar)) exact exponential-time algorithm, based on dynamic programming. These three main questions are also investigated for 1-level grammars, i. e., grammars for which only the start rule contains nonterminals on the right side; thus, investigating the impact of the "hierarchical depth" of grammars on the complexity of the smallest grammar problem. In this regard, we obtain for 1-level grammars similar, but slightly stronger results.},
  language  = {en}
}
@article{KossmannHalfpapJankriftetal.2020,
  author    = {Kossmann, Jan and Halfpap, Stefan and Jankrift, Marcel and Schlosser, Rainer},
  title     = {Magic mirror in my hand, which is the best in the land?},
  series = {Proceedings of the VLDB Endowment},
  volume    = {13},
  journal   = {Proceedings of the VLDB Endowment},
  number    = {11},
  publisher = {Association for Computing Machinery},
  address   = {New York},
  issn      = {2150-8097},
  doi       = {10.14778/3407790.3407832},
  pages     = {2382 -- 2395},
  year      = {2020},
  abstract  = {Indexes are essential for the efficient processing of database workloads. Proposed solutions for the relevant and challenging index selection problem range from metadata-based simple heuristics, over sophisticated multi-step algorithms, to approaches that yield optimal results. The main challenges are (i) to accurately determine the effect of an index on the workload cost while considering the interaction of indexes and (ii) a large number of possible combinations resulting from workloads containing many queries and massive schemata with possibly thousands of attributes. <br /> In this work, we describe and analyze eight index selection algorithms that are based on different concepts and compare them along different dimensions, such as solution quality, runtime, multi-column support, solution granularity, and complexity. In particular, we analyze the solutions of the algorithms for the challenging analytical Join Order, TPC-H, and TPC-DS benchmarks. Afterward, we assess strengths and weaknesses, infer insights for index selection in general and each approach individually, before we give recommendations on when to use which approach.},
  language  = {en}
}
@article{KoumarelasPapenbrockNaumann2020,
  author    = {Koumarelas, Ioannis and Papenbrock, Thorsten and Naumann, Felix},
  title     = {MDedup},
  series = {Proceedings of the VLDB Endowment},
  volume    = {13},
  journal   = {Proceedings of the VLDB Endowment},
  number    = {5},
  publisher = {Association for Computing Machinery},
  address   = {New York},
  issn      = {2150-8097},
  doi       = {10.14778/3377369.3377379},
  pages     = {712 -- 725},
  year      = {2020},
  abstract  = {Duplicate detection is an integral part of data cleaning and serves to identify multiple representations of same real-world entities in (relational) datasets. Existing duplicate detection approaches are effective, but they are also hard to parameterize or require a lot of pre-labeled training data. Both parameterization and pre-labeling are at least domain-specific if not dataset-specific, which is a problem if a new dataset needs to be cleaned. For this reason, we propose a novel, rule-based and fully automatic duplicate detection approach that is based on matching dependencies (MDs). Our system uses automatically discovered MDs, various dataset features, and known gold standards to train a model that selects MDs as duplicate detection rules. Once trained, the model can select useful MDs for duplicate detection on any new dataset. To increase the generally low recall of MD-based data cleaning approaches, we propose an additional boosting step. Our experiments show that this approach reaches up to 94\% F-measure and 100\% precision on our evaluation datasets, which are good numbers considering that the system does not require domain or target data-specific configuration.},
  language  = {en}
}
@article{SchirmerPapenbrockKoumarelasetal.2020,
  author    = {Schirmer, Philipp and Papenbrock, Thorsten and Koumarelas, Ioannis and Naumann, Felix},
  title     = {Efficient discovery of matching dependencies},
  series = {ACM transactions on database systems : TODS},
  volume    = {45},
  journal   = {ACM transactions on database systems : TODS},
  number    = {3},
  publisher = {Association for Computing Machinery},
  address   = {New York},
  issn      = {0362-5915},
  doi       = {10.1145/3392778},
  pages     = {33},
  year      = {2020},
  abstract  = {Matching dependencies (MDs) are data profiling results that are often used for data integration, data cleaning, and entity matching. They are a generalization of functional dependencies (FDs) matching similar rather than same elements. As their discovery is very difficult, existing profiling algorithms find either only small subsets of all MDs or their scope is limited to only small datasets. We focus on the efficient discovery of all interesting MDs in real-world datasets. For this purpose, we propose HyMD, a novel MD discovery algorithm that finds all minimal, non-trivial MDs within given similarity boundaries. The algorithm extracts the exact similarity thresholds for the individual MDs from the data instead of using predefined similarity thresholds. For this reason, it is the first approach to solve the MD discovery problem in an exact and truly complete way. If needed, the algorithm can, however, enforce certain properties on the reported MDs, such as disjointness and minimum support, to focus the discovery on such results that are actually required by downstream use cases. HyMD is technically a hybrid approach that combines the two most popular dependency discovery strategies in related work: lattice traversal and inference from record pairs. Despite the additional effort of finding exact similarity thresholds for all MD candidates, the algorithm is still able to efficiently process large datasets, e.g., datasets larger than 3 GB.},
  language  = {en}
}
@article{TorkuraSukmanaChengetal.2020,
  author    = {Torkura, Kennedy A. and Sukmana, Muhammad Ihsan Haikal and Cheng, Feng and Meinel, Christoph},
  title     = {CloudStrike},
  series = {IEEE access : practical research, open solutions},
  volume    = {8},
  journal   = {IEEE access : practical research, open solutions},
  publisher = {Institute of Electrical and Electronics Engineers },
  address   = {Piscataway},
  issn      = {2169-3536},
  doi       = {10.1109/ACCESS.2020.3007338},
  pages     = {123044 -- 123060},
  year      = {2020},
  abstract  = {Most cyber-attacks and data breaches in cloud infrastructure are due to human errors and misconfiguration vulnerabilities. Cloud customer-centric tools are imperative for mitigating these issues, however existing cloud security models are largely unable to tackle these security challenges. Therefore, novel security mechanisms are imperative, we propose Risk-driven Fault Injection (RDFI) techniques to address these challenges. RDFI applies the principles of chaos engineering to cloud security and leverages feedback loops to execute, monitor, analyze and plan security fault injection campaigns, based on a knowledge-base. The knowledge-base consists of fault models designed from secure baselines, cloud security best practices and observations derived during iterative fault injection campaigns. These observations are helpful for identifying vulnerabilities while verifying the correctness of security attributes (integrity, confidentiality and availability). Furthermore, RDFI proactively supports risk analysis and security hardening efforts by sharing security information with security mechanisms. We have designed and implemented the RDFI strategies including various chaos engineering algorithms as a software tool: CloudStrike. Several evaluations have been conducted with CloudStrike against infrastructure deployed on two major public cloud infrastructure: Amazon Web Services and Google Cloud Platform. The time performance linearly increases, proportional to increasing attack rates. Also, the analysis of vulnerabilities detected via security fault injection has been used to harden the security of cloud resources to demonstrate the effectiveness of the security information provided by CloudStrike. Therefore, we opine that our approaches are suitable for overcoming contemporary cloud security issues.},
  language  = {en}
}
@article{AdnanMatthewsHackletal.2020,
  author    = {Adnan, Hassan Sami and Matthews, Sam and Hackl, M. and Das, P. P. and Manaswini, Manisha and Gadamsetti, S. and Filali, Maroua and Owoyele, Babajide and Santuber, Joaqu{\´i}n and Edelman, Jonathan},
  title     = {Human centered AI design for clinical monitoring and data management},
  series = {European journal of public health : official journal of the European Health Association},
  volume    = {30},
  journal   = {European journal of public health : official journal of the European Health Association},
  number    = {5},
  publisher = {Oxford Univ. Press},
  address   = {Oxford},
  issn      = {1101-1262},
  doi       = {10.1093/eurpub/ckaa165.225},
  pages     = {V86 -- V86},
  year      = {2020},
  abstract  = {In clinical settings, significant resources are spent on data collection and monitoring patients' health parameters to improve decision-making and provide better care. With increased digitization, the healthcare sector is shifting towards implementing digital technologies for data management and in administration. New technologies offer better treatment opportunities and streamline clinical workflow, but the complexity can cause ineffectiveness, frustration, and errors. To address this, we believe digital solutions alone are not sufficient. Therefore, we take a human-centred design approach for AI development, and apply systems engineering methods to identify system leverage points. We demonstrate how automation enables monitoring clinical parameters, using existing non-intrusive sensor technology, resulting in more resources toward patient care. Furthermore, we provide a framework on digitization of clinical data for integration with data management.},
  language  = {en}
}
@article{ChujfiLaRocheMeinel2017,
  author    = {Chujfi-La-Roche, Salim and Meinel, Christoph},
  title     = {Matching cognitively sympathetic individual styles to develop collective intelligence in digital communities},
  series = {AI \& society : the journal of human-centred systems and machine intelligence},
  volume    = {35},
  journal   = {AI \& society : the journal of human-centred systems and machine intelligence},
  number    = {1},
  publisher = {Springer},
  address   = {New York},
  issn      = {0951-5666},
  doi       = {10.1007/s00146-017-0780-x},
  pages     = {5 -- 15},
  year      = {2017},
  abstract  = {Creation, collection and retention of knowledge in digital communities is an activity that currently requires being explicitly targeted as a secure method of keeping intellectual capital growing in the digital era. In particular, we consider it relevant to analyze and evaluate the empathetic cognitive personalities and behaviors that individuals now have with the change from face-to-face communication (F2F) to computer-mediated communication (CMC) online. This document proposes a cyber-humanistic approach to enhance the traditional SECI knowledge management model. A cognitive perception is added to its cyclical process following design thinking interaction, exemplary for improvement of the method in which knowledge is continuously created, converted and shared. In building a cognitive-centered model, we specifically focus on the effective identification and response to cognitive stimulation of individuals, as they are the intellectual generators and multiplicators of knowledge in the online environment. Our target is to identify how geographically distributed-digital-organizations should align the individual's cognitive abilities to promote iteration and improve interaction as a reliable stimulant of collective intelligence. The new model focuses on analyzing the four different stages of knowledge processing, where individuals with sympathetic cognitive personalities can significantly boost knowledge creation in a virtual social system. For organizations, this means that multidisciplinary individuals can maximize their extensive potential, by externalizing their knowledge in the correct stage of the knowledge creation process, and by collaborating with their appropriate sympathetically cognitive remote peers.},
  language  = {en}
}
@article{Perscheid2021,
  author    = {Perscheid, Cindy},
  title     = {Integrative biomarker detection on high-dimensional gene expression data sets},
  series = {Briefings in bioinformatics},
  volume    = {22},
  journal   = {Briefings in bioinformatics},
  number    = {3},
  publisher = {Oxford Univ. Press},
  address   = {Oxford},
  issn      = {1467-5463},
  doi       = {10.1093/bib/bbaa151},
  pages     = {18},
  year      = {2021},
  abstract  = {Gene expression data provide the expression levels of tens of thousands of genes from several hundred samples. These data are analyzed to detect biomarkers that can be of prognostic or diagnostic use. Traditionally, biomarker detection for gene expression data is the task of gene selection. The vast number of genes is reduced to a few relevant ones that achieve the best performance for the respective use case. Traditional approaches select genes based on their statistical significance in the data set. This results in issues of robustness, redundancy and true biological relevance of the selected genes. Integrative analyses typically address these shortcomings by integrating multiple data artifacts from the same objects, e.g. gene expression and methylation data. When only gene expression data are available, integrative analyses instead use curated information on biological processes from public knowledge bases. With knowledge bases providing an ever-increasing amount of curated biological knowledge, such prior knowledge approaches become more powerful. This paper provides a thorough overview on the status quo of biomarker detection on gene expression data with prior biological knowledge. We discuss current shortcomings of traditional approaches, review recent external knowledge bases, provide a classification and qualitative comparison of existing prior knowledge approaches and discuss open challenges for this kind of gene selection.},
  language  = {en}
}
@article{HameedNaumann2020,
  author    = {Hameed, Mazhar and Naumann, Felix},
  title     = {Data Preparation},
  series = {SIGMOD record},
  volume    = {49},
  journal   = {SIGMOD record},
  number    = {3},
  publisher = {Association for Computing Machinery},
  address   = {New York},
  issn      = {0163-5808},
  doi       = {10.1145/3444831.3444835},
  pages     = {18 -- 29},
  year      = {2020},
  abstract  = {Raw data are often messy: they follow different encodings, records are not well structured, values do not adhere to patterns, etc. Such data are in general not fit to be ingested by downstream applications, such as data analytics tools, or even by data management systems. The act of obtaining information from raw data relies on some data preparation process. Data preparation is integral to advanced data analysis and data management, not only for data science but for any data-driven applications. Existing data preparation tools are operational and useful, but there is still room for improvement and optimization. With increasing data volume and its messy nature, the demand for prepared data increases day by day. <br /> To cater to this demand, companies and researchers are developing techniques and tools for data preparation. To better understand the available data preparation systems, we have conducted a survey to investigate (1) prominent data preparation tools, (2) distinctive tool features, (3) the need for preliminary data processing even for these tools and, (4) features and abilities that are still lacking. We conclude with an argument in support of automatic and intelligent data preparation beyond traditional and simplistic techniques.},
  language  = {en}
}
@article{GoebelLagodzinskiSeidel2021,
  author    = {G{\"o}bel, Andreas and Lagodzinski, Gregor J. A. and Seidel, Karen},
  title     = {Counting homomorphisms to trees modulo a prime},
  series = {ACM transactions on computation theory : TOCT / Association for Computing Machinery},
  volume    = {13},
  journal   = {ACM transactions on computation theory : TOCT / Association for Computing Machinery},
  number    = {3},
  publisher = {Association for Computing Machinery},
  address   = {New York},
  issn      = {1942-3454},
  doi       = {10.1145/3460958},
  pages     = {1 -- 33},
  year      = {2021},
  abstract  = {Many important graph-theoretic notions can be encoded as counting graph homomorphism problems, such as partition functions in statistical physics, in particular independent sets and colourings. In this article, we study the complexity of \#(p) HOMSTOH, the problem of counting graph homomorphisms from an input graph to a graph H modulo a prime number p. Dyer and Greenhill proved a dichotomy stating that the tractability of non-modular counting graph homomorphisms depends on the structure of the target graph. Many intractable cases in non-modular counting become tractable in modular counting due to the common phenomenon of cancellation. In subsequent studies on counting modulo 2, however, the influence of the structure of H on the tractability was shown to persist, which yields similar dichotomies. <br /> Our main result states that for every tree H and every prime p the problem \#pHOMSTOH is either polynomial time computable or \#P-p-complete. This relates to the conjecture of Faben and Jerrum stating that this dichotomy holds for every graph H when counting modulo 2. In contrast to previous results on modular counting, the tractable cases of \#pHOMSTOH are essentially the same for all values of the modulo when H is a tree. To prove this result, we study the structural properties of a homomorphism. As an important interim result, our study yields a dichotomy for the problem of counting weighted independent sets in a bipartite graph modulo some prime p. These results are the first suggesting that such dichotomies hold not only for the modulo 2 case but also for the modular counting functions of all primes p.},
  language  = {en}
}
@article{VitaglianoJiangNaumann2021,
  author    = {Vitagliano, Gerardo and Jiang, Lan and Naumann, Felix},
  title     = {Detecting layout templates in complex multiregion files},
  series = {Proceedings of the VLDB Endowment},
  volume    = {15},
  journal   = {Proceedings of the VLDB Endowment},
  number    = {3},
  publisher = {Association for Computing Machinery},
  address   = {New York},
  issn      = {2150-8097},
  doi       = {10.14778/3494124.3494145},
  pages     = {646 -- 658},
  year      = {2021},
  abstract  = {Spreadsheets are among the most commonly used file formats for data management, distribution, and analysis. Their widespread employment makes it easy to gather large collections of data, but their flexible canvas-based structure makes automated analysis difficult without heavy preparation. One of the common problems that practitioners face is the presence of multiple, independent regions in a single spreadsheet, possibly separated by repeated empty cells. We define such files as "multiregion" files. In collections of various spreadsheets, we can observe that some share the same layout. We present the Mondrian approach to automatically identify layout templates across multiple files and systematically extract the corresponding regions. Our approach is composed of three phases: first, each file is rendered as an image and inspected for elements that could form regions; then, using a clustering algorithm, the identified elements are grouped to form regions; finally, every file layout is represented as a graph and compared with others to find layout templates. We compare our method to state-of-the-art table recognition algorithms on two corpora of real-world enterprise spreadsheets. Our approach shows the best performances in detecting reliable region boundaries within each file and can correctly identify recurring layouts across files.},
  language  = {en}
}
@article{ChauhanFriedrichRothenberger2020,
  author    = {Chauhan, Ankit and Friedrich, Tobias and Rothenberger, Ralf},
  title     = {Greed is good for deterministic scale-free networks},
  series = {Algorithmica : an international journal in computer science},
  volume    = {82},
  journal   = {Algorithmica : an international journal in computer science},
  number    = {11},
  publisher = {Springer},
  address   = {New York},
  issn      = {0178-4617},
  doi       = {10.1007/s00453-020-00729-z},
  pages     = {3338 -- 3389},
  year      = {2020},
  abstract  = {Large real-world networks typically follow a power-law degree distribution. To study such networks, numerous random graph models have been proposed. However, real-world networks are not drawn at random. Therefore, Brach et al. (27th symposium on discrete algorithms (SODA), pp 1306-1325, 2016) introduced two natural deterministic conditions: (1) a power-law upper bound on the degree distribution (PLB-U) and (2) power-law neighborhoods, that is, the degree distribution of neighbors of each vertex is also upper bounded by a power law (PLB-N). They showed that many real-world networks satisfy both properties and exploit them to design faster algorithms for a number of classical graph problems. We complement their work by showing that some well-studied random graph models exhibit both of the mentioned PLB properties. PLB-U and PLB-N hold with high probability for Chung-Lu Random Graphs and Geometric Inhomogeneous Random Graphs and almost surely for Hyperbolic Random Graphs. As a consequence, all results of Brach et al. also hold with high probability or almost surely for those random graph classes. In the second part we study three classical NP-hard optimization problems on PLB networks. It is known that on general graphs with maximum degree Delta, a greedy algorithm, which chooses nodes in the order of their degree, only achieves a Omega (ln Delta)-approximation forMinimum Vertex Cover and Minimum Dominating Set, and a Omega(Delta)-approximation forMaximum Independent Set. We prove that the PLB-U property with beta>2 suffices for the greedy approach to achieve a constant-factor approximation for all three problems. We also show that these problems are APX-hard even if PLB-U, PLB-N, and an additional power-law lower bound on the degree distribution hold. Hence, a PTAS cannot be expected unless P = NP. Furthermore, we prove that all three problems are in MAX SNP if the PLB-U property holds.},
  language  = {en}
}
@article{BarkowskyGiese2020,
  author    = {Barkowsky, Matthias and Giese, Holger},
  title     = {Hybrid search plan generation for generalized graph pattern matching},
  series = {Journal of logical and algebraic methods in programming},
  volume    = {114},
  journal   = {Journal of logical and algebraic methods in programming},
  publisher = {Elsevier},
  address   = {New York},
  issn      = {2352-2208},
  doi       = {10.1016/j.jlamp.2020.100563},
  pages     = {29},
  year      = {2020},
  abstract  = {In recent years, the increased interest in application areas such as social networks has resulted in a rising popularity of graph-based approaches for storing and processing large amounts of interconnected data. To extract useful information from the growing network structures, efficient querying techniques are required. In this paper, we propose an approach for graph pattern matching that allows a uniform handling of arbitrary constraints over the query vertices. Our technique builds on a previously introduced matching algorithm, which takes concrete host graph information into account to dynamically adapt the employed search plan during query execution. The dynamic algorithm is combined with an existing static approach for search plan generation, resulting in a hybrid technique which we further extend by a more sophisticated handling of filtering effects caused by constraint checks. We evaluate the presented concepts empirically based on an implementation for our graph pattern matching tool, the Story Diagram Interpreter, with queries and data provided by the LDBC Social Network Benchmark. Our results suggest that the hybrid technique may improve search efficiency in several cases, and rarely reduces efficiency.},
  language  = {en}
}
@article{ChromikPirlBeilharzetal.2021,
  author    = {Chromik, Jonas and Pirl, Lukas and Beilharz, Jossekin Jakob and Arnrich, Bert and Polze, Andreas},
  title     = {Certainty in QRS detection with artificial neural networks},
  series = {Biomedical signal processing and control},
  volume    = {68},
  journal   = {Biomedical signal processing and control},
  publisher = {Elsevier},
  address   = {Oxford},
  issn      = {1746-8094},
  doi       = {10.1016/j.bspc.2021.102628},
  pages     = {12},
  year      = {2021},
  abstract  = {Detection of the QRS complex is a long-standing topic in the context of electrocardiography and many algorithms build upon the knowledge of the QRS positions. Although the first solutions to this problem were proposed in the 1970s and 1980s, there is still potential for improvements. Advancements in neural network technology made in recent years also lead to the emergence of enhanced QRS detectors based on artificial neural networks. In this work, we propose a method for assessing the certainty that is in each of the detected QRS complexes, i.e. how confident the QRS detector is that there is, in fact, a QRS complex in the position where it was detected. We further show how this metric can be utilised to distinguish correctly detected QRS complexes from false detections.},
  language  = {en}
}
@article{Schlosser2022,
  author    = {Schlosser, Rainer},
  title     = {Heuristic mean-variance optimization in Markov decision processes using state-dependent risk aversion},
  series = {IMA journal of management mathematics / Institute of Mathematics and Its Applications},
  volume    = {33},
  journal   = {IMA journal of management mathematics / Institute of Mathematics and Its Applications},
  number    = {2},
  publisher = {Oxford Univ. Press},
  address   = {Oxford},
  issn      = {1471-678X},
  doi       = {10.1093/imaman/dpab009},
  pages     = {181 -- 199},
  year      = {2022},
  abstract  = {In dynamic decision problems, it is challenging to find the right balance between maximizing expected rewards and minimizing risks. In this paper, we consider NP-hard mean-variance (MV) optimization problems in Markov decision processes with a finite time horizon. We present a heuristic approach to solve MV problems, which is based on state-dependent risk aversion and efficient dynamic programming techniques. Our approach can also be applied to mean-semivariance (MSV) problems, which particularly focus on the downside risk. We demonstrate the applicability and the effectiveness of our heuristic for dynamic pricing applications. Using reproducible examples, we show that our approach outperforms existing state-of-the-art benchmark models for MV and MSV problems while also providing competitive runtimes. Further, compared to models based on constant risk levels, we find that state-dependent risk aversion allows to more effectively intervene in case sales processes deviate from their planned paths. Our concepts are domain independent, easy to implement and of low computational complexity.},
  language  = {en}
}
@article{Schlosser2020,
  author    = {Schlosser, Rainer},
  title     = {Scalable relaxation techniques to solve stochastic dynamic multi-product pricing problems with substitution effects},
  series = {Journal of revenue and pricing management},
  volume    = {20},
  journal   = {Journal of revenue and pricing management},
  number    = {1},
  publisher = {Palgrave Macmillan},
  address   = {Basingstoke},
  issn      = {1476-6930},
  doi       = {10.1057/s41272-020-00249-z},
  pages     = {54 -- 65},
  year      = {2020},
  abstract  = {In many businesses, firms are selling different types of products, which share mutual substitution effects in demand. To compute effective pricing strategies is challenging as the sales probabilities of each of a firm's products can also be affected by the prices of potential substitutes. In this paper, we analyze stochastic dynamic multi-product pricing models for the sale of perishable goods. To circumvent the limitations of time-consuming optimal solutions for highly complex models, we propose different relaxation techniques, which allow to reduce the size of critical model components, such as the state space, the action space, or the set of potential sales events. Our heuristics are able to decrease the size of those components by forming corresponding clusters and using subsets of representative elements. Using numerical examples, we verify that our heuristics make it possible to dramatically reduce the computation time while still obtaining close-to-optimal expected profits. Further, we show that our heuristics are (i) flexible, (ii) scalable, and (iii) can be arbitrarily combined in a mutually supportive way.},
  language  = {en}
}
@misc{AlibabaieGhasemzadehMeinel2017,
  author    = {Alibabaie, Najmeh and Ghasemzadeh, Mohammad and Meinel, Christoph},
  title     = {A variant of genetic algorithm for non-homogeneous population},
  series = {International Conference Applied Mathematics, Computational Science and Systems Engineering 2016},
  volume    = {9},
  journal   = {International Conference Applied Mathematics, Computational Science and Systems Engineering 2016},
  publisher = {EDP Sciences},
  address   = {Les Ulis},
  issn      = {2271-2097},
  doi       = {10.1051/itmconf/20170902001},
  pages     = {8},
  year      = {2017},
  abstract  = {Selection of initial points, the number of clusters and finding proper clusters centers are still the main challenge in clustering processes. In this paper, we suggest genetic algorithm based method which searches several solution spaces simultaneously. The solution spaces are population groups consisting of elements with similar structure. Elements in a group have the same size, while elements in different groups are of different sizes. The proposed algorithm processes the population in groups of chromosomes with one gene, two genes to k genes. These genes hold corresponding information about the cluster centers. In the proposed method, the crossover and mutation operators can accept parents with different sizes; this can lead to versatility in population and information transfer among sub-populations. We implemented the proposed method and evaluated its performance against some random datasets and the Ruspini dataset as well. The experimental results show that the proposed method could effectively determine the appropriate number of clusters and recognize their centers. Overall this research implies that using heterogeneous population in the genetic algorithm can lead to better results.},
  language  = {en}
}
@misc{LorenzKiekhebenSchnor2017,
  author    = {Lorenz, Claas and Kiekheben, Sebastian and Schnor, Bettina},
  title     = {FaVe: Modeling IPv6 firewalls for fast formal verification},
  series = {International Conference on Networked Systems (NetSys) 2017},
  journal   = {International Conference on Networked Systems (NetSys) 2017},
  publisher = {IEEE},
  address   = {New York},
  doi       = {10.1109/NetSys.2017.7903956},
  pages     = {8},
  year      = {2017},
  abstract  = {As virtualization drives the automation of networking, the validation of security properties becomes more and more challenging eventually ruling out manual inspections. While formal verification in Software Defined Networks is provided by comprehensive tools with high speed reverification capabilities like NetPlumber for instance, the presence of middlebox functionality like firewalls is not considered. Also, they lack the ability to handle dynamic protocol elements like IPv6 extension header chains. In this work, we provide suitable modeling abstractions to enable both - the inclusion of firewalls and dynamic protocol elements. We exemplarily model the Linux ip6tables/netfilter packet filter and also provide abstractions for an application layer gateway. Finally, we present a prototype of our formal verification system FaVe.},
  language  = {en}
}
@misc{GawronChengMeinel2017,
  author    = {Gawron, Marian and Cheng, Feng and Meinel, Christoph},
  title     = {PVD: Passive Vulnerability Detection},
  series = {8th International Conference on Information and Communication Systems (ICICS)},
  journal   = {8th International Conference on Information and Communication Systems (ICICS)},
  publisher = {IEEE},
  address   = {New York},
  isbn      = {978-1-5090-4243-2},
  issn      = {2471-125X},
  doi       = {10.1109/IACS.2017.7921992},
  pages     = {322 -- 327},
  year      = {2017},
  abstract  = {The identification of vulnerabilities relies on detailed information about the target infrastructure. The gathering of the necessary information is a crucial step that requires an intensive scanning or mature expertise and knowledge about the system even though the information was already available in a different context. In this paper we propose a new method to detect vulnerabilities that reuses the existing information and eliminates the necessity of a comprehensive scan of the target system. Since our approach is able to identify vulnerabilities without the additional effort of a scan, we are able to increase the overall performance of the detection. Because of the reuse and the removal of the active testing procedures, our approach could be classified as a passive vulnerability detection. We will explain the approach and illustrate the additional possibility to increase the security awareness of users. Therefore, we applied the approach on an experimental setup and extracted security relevant information from web logs.},
  language  = {en}
}
@misc{MalchowRenzBaueretal.2017,
  author    = {Malchow, Martin and Renz, Jan and Bauer, Matthias and Meinel, Christoph},
  title     = {Embedded smart home},
  series = {11th Annual IEEE International Systems Conference (SysCon)},
  journal   = {11th Annual IEEE International Systems Conference (SysCon)},
  publisher = {IEEE},
  address   = {New York},
  isbn      = {978-1-5090-4623-2},
  issn      = {1944-7620},
  doi       = {10.1109/SYSCON.2017.7934728},
  pages     = {195 -- 200},
  year      = {2017},
  abstract  = {The popularity of MOOCs has increased considerably in the last years. A typical MOOC course consists of video content, self tests after a video and homework, which is normally in multiple choice format. After solving this homeworks for every week of a MOOC, the final exam certificate can be issued when the student has reached a sufficient score. There are also some attempts to include practical tasks, such as programming, in MOOCs for grading. Nevertheless, until now there is no known possibility to teach embedded system programming in a MOOC course where the programming can be done in a remote lab and where grading of the tasks is additionally possible. This embedded programming includes communication over GPIO pins to control LEDs and measure sensor values. We started a MOOC course called "Embedded Smart Home" as a pilot to prove the concept to teach real hardware programming in a MOOC environment under real life MOOC conditions with over 6000 students. Furthermore, also students with real hardware have the possibility to program on their own real hardware and grade their results in the MOOC course. Finally, we evaluate our approach and analyze the student acceptance of this approach to offer a course on embedded programming. We also analyze the hardware usage and working time of students solving tasks to find out if real hardware programming is an advantage and motivating achievement to support students learning success.},
  language  = {en}
}