@phdthesis{Zuo2017,
  author    = {Zuo, Zhe},
  title     = {From unstructured to structured: Context-based named entity mining from text},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-412576},
  school      = {Universit{\"a}t Potsdam},
  pages     = {vii, 112},
  year      = {2017},
  abstract  = {With recent advances in the area of information extraction, automatically extracting structured information from a vast amount of unstructured textual data becomes an important task, which is infeasible for humans to capture all information manually. Named entities (e.g., persons, organizations, and locations), which are crucial components in texts, are usually the subjects of structured information from textual documents. Therefore, the task of named entity mining receives much attention. It consists of three major subtasks, which are named entity recognition, named entity linking, and relation extraction. These three tasks build up an entire pipeline of a named entity mining system, where each of them has its challenges and can be employed for further applications. As a fundamental task in the natural language processing domain, studies on named entity recognition have a long history, and many existing approaches produce reliable results. The task is aiming to extract mentions of named entities in text and identify their types. Named entity linking recently received much attention with the development of knowledge bases that contain rich information about entities. The goal is to disambiguate mentions of named entities and to link them to the corresponding entries in a knowledge base. Relation extraction, as the final step of named entity mining, is a highly challenging task, which is to extract semantic relations between named entities, e.g., the ownership relation between two companies. In this thesis, we review the state-of-the-art of named entity mining domain in detail, including valuable features, techniques, evaluation methodologies, and so on. Furthermore, we present two of our approaches that focus on the named entity linking and relation extraction tasks separately. To solve the named entity linking task, we propose the entity linking technique, BEL, which operates on a textual range of relevant terms and aggregates decisions from an ensemble of simple classifiers. Each of the classifiers operates on a randomly sampled subset of the above range. In extensive experiments on hand-labeled and benchmark datasets, our approach outperformed state-of-the-art entity linking techniques, both in terms of quality and efficiency. For the task of relation extraction, we focus on extracting a specific group of difficult relation types, business relations between companies. These relations can be used to gain valuable insight into the interactions between companies and perform complex analytics, such as predicting risk or valuating companies. Our semi-supervised strategy can extract business relations between companies based on only a few user-provided seed company pairs. By doing so, we also provide a solution for the problem of determining the direction of asymmetric relations, such as the ownership_of relation. We improve the reliability of the extraction process by using a holistic pattern identification method, which classifies the generated extraction patterns. Our experiments show that we can accurately and reliably extract new entity pairs occurring in the target relation by using as few as five labeled seed pairs.},
  language  = {en}
}
@article{ZieglerPfitznerSchulzetal.2022,
  author    = {Ziegler, Joceline and Pfitzner, Bjarne and Schulz, Heinrich and Saalbach, Axel and Arnrich, Bert},
  title     = {Defending against Reconstruction Attacks through Differentially Private Federated Learning for Classification of Heterogeneous Chest X-ray Data},
  series = {Sensors},
  volume    = {22},
  journal   = {Sensors},
  edition   = {14},
  publisher = {MDPI},
  address   = {Basel, Schweiz},
  issn      = {1424-8220},
  doi       = {10.3390/s22145195},
  pages     = {25},
  year      = {2022},
  abstract  = {Privacy regulations and the physical distribution of heterogeneous data are often primary concerns for the development of deep learning models in a medical context. This paper evaluates the feasibility of differentially private federated learning for chest X-ray classification as a defense against data privacy attacks. To the best of our knowledge, we are the first to directly compare the impact of differentially private training on two different neural network architectures, DenseNet121 and ResNet50. Extending the federated learning environments previously analyzed in terms of privacy, we simulated a heterogeneous and imbalanced federated setting by distributing images from the public CheXpert and Mendeley chest X-ray datasets unevenly among 36 clients. Both non-private baseline models achieved an area under the receiver operating characteristic curve (AUC) of 0.940.94 on the binary classification task of detecting the presence of a medical finding. We demonstrate that both model architectures are vulnerable to privacy violation by applying image reconstruction attacks to local model updates from individual clients. The attack was particularly successful during later training stages. To mitigate the risk of a privacy breach, we integrated R{\´e}nyi differential privacy with a Gaussian noise mechanism into local model training. We evaluate model performance and attack vulnerability for privacy budgets ε∈{1,3,6,10}�∈{1,3,6,10}. The DenseNet121 achieved the best utility-privacy trade-off with an AUC of 0.940.94 for ε=6�=6. Model performance deteriorated slightly for individual clients compared to the non-private baseline. The ResNet50 only reached an AUC of 0.760.76 in the same privacy setting. Its performance was inferior to that of the DenseNet121 for all considered privacy constraints, suggesting that the DenseNet121 architecture is more robust to differentially private training.},
  language  = {en}
}
@misc{ZieglerPfitznerSchulzetal.2022,
  author    = {Ziegler, Joceline and Pfitzner, Bjarne and Schulz, Heinrich and Saalbach, Axel and Arnrich, Bert},
  title     = {Defending against Reconstruction Attacks through Differentially Private Federated Learning for Classification of Heterogeneous Chest X-ray Data},
  series = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t},
  journal   = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t},
  number    = {14},
  doi       = {10.25932/publishup-58132},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-581322},
  pages     = {25},
  year      = {2022},
  abstract  = {Privacy regulations and the physical distribution of heterogeneous data are often primary concerns for the development of deep learning models in a medical context. This paper evaluates the feasibility of differentially private federated learning for chest X-ray classification as a defense against data privacy attacks. To the best of our knowledge, we are the first to directly compare the impact of differentially private training on two different neural network architectures, DenseNet121 and ResNet50. Extending the federated learning environments previously analyzed in terms of privacy, we simulated a heterogeneous and imbalanced federated setting by distributing images from the public CheXpert and Mendeley chest X-ray datasets unevenly among 36 clients. Both non-private baseline models achieved an area under the receiver operating characteristic curve (AUC) of 0.940.94 on the binary classification task of detecting the presence of a medical finding. We demonstrate that both model architectures are vulnerable to privacy violation by applying image reconstruction attacks to local model updates from individual clients. The attack was particularly successful during later training stages. To mitigate the risk of a privacy breach, we integrated R{\´e}nyi differential privacy with a Gaussian noise mechanism into local model training. We evaluate model performance and attack vulnerability for privacy budgets ε∈{1,3,6,10}�∈{1,3,6,10}. The DenseNet121 achieved the best utility-privacy trade-off with an AUC of 0.940.94 for ε=6�=6. Model performance deteriorated slightly for individual clients compared to the non-private baseline. The ResNet50 only reached an AUC of 0.760.76 in the same privacy setting. Its performance was inferior to that of the DenseNet121 for all considered privacy constraints, suggesting that the DenseNet121 architecture is more robust to differentially private training.},
  language  = {en}
}
@phdthesis{Zieger2017,
  author    = {Zieger, Tobias},
  title     = {Self-adaptive data quality},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-410573},
  school      = {Universit{\"a}t Potsdam},
  pages     = {vii, 125},
  year      = {2017},
  abstract  = {Carrying out business processes successfully is closely linked to the quality of the data inventory in an organization. Lacks in data quality lead to problems: Incorrect address data prevents (timely) shipments to customers. Erroneous orders lead to returns and thus to unnecessary effort. Wrong pricing forces companies to miss out on revenues or to impair customer satisfaction. If orders or customer records cannot be retrieved, complaint management takes longer. Due to erroneous inventories, too few or too much supplies might be reordered. A special problem with data quality and the reason for many of the issues mentioned above are duplicates in databases. Duplicates are different representations of same real-world objects in a dataset. However, these representations differ from each other and are for that reason hard to match by a computer. Moreover, the number of required comparisons to find those duplicates grows with the square of the dataset size. To cleanse the data, these duplicates must be detected and removed. Duplicate detection is a very laborious process. To achieve satisfactory results, appropriate software must be created and configured (similarity measures, partitioning keys, thresholds, etc.). Both requires much manual effort and experience. This thesis addresses automation of parameter selection for duplicate detection and presents several novel approaches that eliminate the need for human experience in parts of the duplicate detection process. A pre-processing step is introduced that analyzes the datasets in question and classifies their attributes semantically. Not only do these annotations help understanding the respective datasets, but they also facilitate subsequent steps, for example, by selecting appropriate similarity measures or normalizing the data upfront. This approach works without schema information. Following that, we show a partitioning technique that strongly reduces the number of pair comparisons for the duplicate detection process. The approach automatically finds particularly suitable partitioning keys that simultaneously allow for effective and efficient duplicate retrieval. By means of a user study, we demonstrate that this technique finds partitioning keys that outperform expert suggestions and additionally does not need manual configuration. Furthermore, this approach can be applied independently of the attribute types. To measure the success of a duplicate detection process and to execute the described partitioning approach, a gold standard is required that provides information about the actual duplicates in a training dataset. This thesis presents a technique that uses existing duplicate detection results and crowdsourcing to create a near gold standard that can be used for the purposes above. Another part of the thesis describes and evaluates strategies how to reduce these crowdsourcing costs and to achieve a consensus with less effort.},
  language  = {en}
}
@misc{ZhouFischerTuncaetal.2020,
  author    = {Zhou, Lin and Fischer, Eric and Tunca, Can and Brahms, Clemens Markus and Ersoy, Cem and Granacher, Urs and Arnrich, Bert},
  title     = {How We Found Our IMU},
  series = {Postprints der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t},
  journal   = {Postprints der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t},
  number    = {2},
  doi       = {10.25932/publishup-48162},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-481628},
  pages     = {31},
  year      = {2020},
  abstract  = {Inertial measurement units (IMUs) are commonly used for localization or movement tracking in pervasive healthcare-related studies, and gait analysis is one of the most often studied topics using IMUs. The increasing variety of commercially available IMU devices offers convenience by combining the sensor modalities and simplifies the data collection procedures. However, selecting the most suitable IMU device for a certain use case is increasingly challenging. In this study, guidelines for IMU selection are proposed. In particular, seven IMUs were compared in terms of their specifications, data collection procedures, and raw data quality. Data collected from the IMUs were then analyzed by a gait analysis algorithm. The difference in accuracy of the calculated gait parameters between the IMUs could be used to retrace the issues in raw data, such as acceleration range or sensor calibration. Based on our algorithm, we were able to identify the best-suited IMUs for our needs. This study provides an overview of how to select the IMUs based on the area of study with concrete examples, and gives insights into the features of seven commercial IMUs using real data.},
  language  = {en}
}
@article{ZhouFischerTuncaetal.2020,
  author    = {Zhou, Lin and Fischer, Eric and Tunca, Can and Brahms, Clemens Markus and Ersoy, Cem and Granacher, Urs and Arnrich, Bert},
  title     = {How We Found Our IMU},
  series = {Sensors},
  volume    = {20},
  journal   = {Sensors},
  number    = {15},
  publisher = {MDPI},
  address   = {Basel},
  issn      = {1424-8220},
  doi       = {10.3390/s20154090},
  pages     = {29},
  year      = {2020},
  abstract  = {Inertial measurement units (IMUs) are commonly used for localization or movement tracking in pervasive healthcare-related studies, and gait analysis is one of the most often studied topics using IMUs. The increasing variety of commercially available IMU devices offers convenience by combining the sensor modalities and simplifies the data collection procedures. However, selecting the most suitable IMU device for a certain use case is increasingly challenging. In this study, guidelines for IMU selection are proposed. In particular, seven IMUs were compared in terms of their specifications, data collection procedures, and raw data quality. Data collected from the IMUs were then analyzed by a gait analysis algorithm. The difference in accuracy of the calculated gait parameters between the IMUs could be used to retrace the issues in raw data, such as acceleration range or sensor calibration. Based on our algorithm, we were able to identify the best-suited IMUs for our needs. This study provides an overview of how to select the IMUs based on the area of study with concrete examples, and gives insights into the features of seven commercial IMUs using real data.},
  language  = {en}
}
@book{ZhangPlauthEberhardtetal.2020,
  author    = {Zhang, Shuhao and Plauth, Max and Eberhardt, Felix and Polze, Andreas and Lehmann, Jens and Sejdiu, Gezim and Jabeen, Hajira and Servadei, Lorenzo and M{\"o}stl, Christian and B{\"a}r, Florian and Netzeband, Andr{\´e} and Schmidt, Rainer and Knigge, Marlene and Hecht, Sonja and Prifti, Loina and Krcmar, Helmut and Sapegin, Andrey and Jaeger, David and Cheng, Feng and Meinel, Christoph and Friedrich, Tobias and Rothenberger, Ralf and Sutton, Andrew M. and Sidorova, Julia A. and Lundberg, Lars and Rosander, Oliver and Sk{\"o}ld, Lars and Di Varano, Igor and van der Walt, Est{\´e}e and Eloff, Jan H. P. and Fabian, Benjamin and Baumann, Annika and Ermakova, Tatiana and Kelkel, Stefan and Choudhary, Yash and Cooray, Thilini and Rodr{\´i}guez, Jorge and Medina-P{\´e}rez, Miguel Angel and Trejo, Luis A. and Barrera-Animas, Ari Yair and Monroy-Borja, Ra{\´u}l and L{\´o}pez-Cuevas, Armando and Ram{\´i}rez-M{\´a}rquez, Jos{\´e} Emmanuel and Grohmann, Maria and Niederleithinger, Ernst and Podapati, Sasidhar and Schmidt, Christopher and Huegle, Johannes and de Oliveira, Roberto C. L. and Soares, F{\´a}bio Mendes and van Hoorn, Andr{\´e} and Neumer, Tamas and Willnecker, Felix and Wilhelm, Mathias and Kuster, Bernhard},
  title     = {HPI Future SOC Lab - Proceedings 2017},
  number    = {130},
  editor    = {Meinel, Christoph and Polze, Andreas and Beins, Karsten and Strotmann, Rolf and Seibold, Ulrich and R{\"o}dszus, Kurt and M{\"u}ller, J{\"u}rgen},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-475-3},
  issn      = {1613-5652},
  doi       = {10.25932/publishup-43310},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-433100},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {ix, 235},
  year      = {2020},
  abstract  = {The "HPI Future SOC Lab" is a cooperation of the Hasso Plattner Institute (HPI) and industry partners. Its mission is to enable and promote exchange and interaction between the research community and the industry partners. The HPI Future SOC Lab provides researchers with free of charge access to a complete infrastructure of state of the art hard and software. This infrastructure includes components, which might be too expensive for an ordinary research environment, such as servers with up to 64 cores and 2 TB main memory. The offerings address researchers particularly from but not limited to the areas of computer science and business information systems. Main areas of research include cloud computing, parallelization, and In-Memory technologies. This technical report presents results of research projects executed in 2017. Selected projects have presented their results on April 25th and November 15th 2017 at the Future SOC Lab Day events.},
  language  = {en}
}
@misc{ZennerBoettingerKonigorski2022,
  author    = {Zenner, Alexander M. and B{\"o}ttinger, Erwin and Konigorski, Stefan},
  title     = {StudyMe},
  series = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t},
  journal   = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t},
  number    = {18},
  doi       = {10.25932/publishup-58976},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-589763},
  pages     = {15},
  year      = {2022},
  abstract  = {N-of-1 trials are multi-crossover self-experiments that allow individuals to systematically evaluate the effect of interventions on their personal health goals. Although several tools for N-of-1 trials exist, there is a gap in supporting non-experts in conducting their own user-centric trials. In this study, we present StudyMe, an open-source mobile application that is freely available from https://play.google.com/store/apps/details?id=health.studyu.me and offers users flexibility and guidance in configuring every component of their trials. We also present research that informed the development of StudyMe, focusing on trial creation. Through an initial survey with 272 participants, we learned that individuals are interested in a variety of personal health aspects and have unique ideas on how to improve them. In an iterative, user-centered development process with intermediate user tests, we developed StudyMe that features an educational part to communicate N-of-1 trial concepts. A final empirical evaluation of StudyMe showed that all participants were able to create their own trials successfully using StudyMe and the app achieved a very good usability rating. Our findings suggest that StudyMe provides a significant step towards enabling individuals to apply a systematic science-oriented approach to personalize health-related interventions and behavior modifications in their everyday lives.},
  language  = {en}
}
@article{ZennerBoettingerKonigorski2022,
  author    = {Zenner, Alexander M. and B{\"o}ttinger, Erwin and Konigorski, Stefan},
  title     = {StudyMe},
  series = {Trials},
  volume    = {23},
  journal   = {Trials},
  publisher = {BioMed Central},
  address   = {London},
  issn      = {1745-6215},
  doi       = {10.1186/s13063-022-06893-7},
  pages     = {15},
  year      = {2022},
  abstract  = {N-of-1 trials are multi-crossover self-experiments that allow individuals to systematically evaluate the effect of interventions on their personal health goals. Although several tools for N-of-1 trials exist, there is a gap in supporting non-experts in conducting their own user-centric trials. In this study, we present StudyMe, an open-source mobile application that is freely available from https://play.google.com/store/apps/details?id=health.studyu.me and offers users flexibility and guidance in configuring every component of their trials. We also present research that informed the development of StudyMe, focusing on trial creation. Through an initial survey with 272 participants, we learned that individuals are interested in a variety of personal health aspects and have unique ideas on how to improve them. In an iterative, user-centered development process with intermediate user tests, we developed StudyMe that features an educational part to communicate N-of-1 trial concepts. A final empirical evaluation of StudyMe showed that all participants were able to create their own trials successfully using StudyMe and the app achieved a very good usability rating. Our findings suggest that StudyMe provides a significant step towards enabling individuals to apply a systematic science-oriented approach to personalize health-related interventions and behavior modifications in their everyday lives.},
  language  = {en}
}
@article{YousfiHeweltBaueretal.2018,
  author    = {Yousfi, Alaaeddine and Hewelt, Marcin and Bauer, Christine and Weske, Mathias},
  title     = {Toward uBPMN-Based patterns for modeling ubiquitous business processes},
  series = {IEEE Transactions on Industrial Informatics},
  volume    = {14},
  journal   = {IEEE Transactions on Industrial Informatics},
  number    = {8},
  publisher = {Inst. of Electr. and Electronics Engineers},
  address   = {Piscataway},
  issn      = {1551-3203},
  doi       = {10.1109/TII.2017.2777847},
  pages     = {3358 -- 3367},
  year      = {2018},
  abstract  = {Ubiquitous business processes are the new generation of processes that pervade the physical space and interact with their environments using a minimum of human involvement. Although they are now widely deployed in the industry, their deployment is still ad hoc . They are implemented after an arbitrary modeling phase or no modeling phase at all. The absence of a solid modeling phase backing up the implementation generates many loopholes that are stressed in the literature. Here, we tackle the issue of modeling ubiquitous business processes. We propose patterns to represent the recent ubiquitous computing features. These patterns are the outcome of an analysis we conducted in the field of human-computer interaction to examine how the features are actually deployed. The patterns' understandability, ease-of-use, usefulness, and completeness are examined via a user experiment. The results indicate that these four indexes are on the positive track. Hence, the patterns may be the backbone of ubiquitous business process modeling in industrial applications.},
  language  = {en}
}
@article{YousfiBatoulisWeske2019,
  author    = {Yousfi, Alaaeddine and Batoulis, Kimon and Weske, Mathias},
  title     = {Achieving Business Process Improvement via Ubiquitous Decision-Aware Business Processes},
  series = {ACM Transactions on Internet Technology},
  volume    = {19},
  journal   = {ACM Transactions on Internet Technology},
  number    = {1},
  publisher = {Association for Computing Machinery},
  address   = {New York},
  issn      = {1533-5399},
  doi       = {10.1145/3298986},
  pages     = {19},
  year      = {2019},
  abstract  = {Business process improvement is an endless challenge for many organizations. As long as there is a process, it must he improved. Nowadays, improvement initiatives are driven by professionals. This is no longer practical because people cannot perceive the enormous data of current business environments. Here, we introduce ubiquitous decision-aware business processes. They pervade the physical space, analyze the ever-changing environments, and make decisions accordingly. We explain how they can be built and used for improvement. Our approach can be a valuable improvement option to alleviate the workload of participants by helping focus on the crucial rather than the menial tasks.},
  language  = {en}
}
@phdthesis{Yang2019,
  author    = {Yang, Haojin},
  title     = {Deep representation learning for multimedia data analysis},
  school      = {Universit{\"a}t Potsdam},
  pages     = {278},
  year      = {2019},
  language  = {en}
}
@article{WuttkeLiLietal.2019,
  author    = {Wuttke, Matthias and Li, Yong and Li, Man and Sieber, Karsten B. and Feitosa, Mary F. and Gorski, Mathias and Tin, Adrienne and Wang, Lihua and Chu, Audrey Y. and Hoppmann, Anselm and Kirsten, Holger and Giri, Ayush and Chai, Jin-Fang and Sveinbjornsson, Gardar and Tayo, Bamidele O. and Nutile, Teresa and Fuchsberger, Christian and Marten, Jonathan and Cocca, Massimiliano and Ghasemi, Sahar and Xu, Yizhe and Horn, Katrin and Noce, Damia and Van der Most, Peter J. and Sedaghat, Sanaz and Yu, Zhi and Akiyama, Masato and Afaq, Saima and Ahluwalia, Tarunveer Singh and Almgren, Peter and Amin, Najaf and Arnlov, Johan and Bakker, Stephan J. L. and Bansal, Nisha and Baptista, Daniela and Bergmann, Sven and Biggs, Mary L. and Biino, Ginevra and Boehnke, Michael and Boerwinkle, Eric and Boissel, Mathilde and B{\"o}ttinger, Erwin and Boutin, Thibaud S. and Brenner, Hermann and Brumat, Marco and Burkhardt, Ralph and Butterworth, Adam S. and Campana, Eric and Campbell, Archie and Campbell, Harry and Canouil, Mickael and Carroll, Robert J. and Catamo, Eulalia and Chambers, John C. and Chee, Miao-Ling and Chee, Miao-Li and Chen, Xu and Cheng, Ching-Yu and Cheng, Yurong and Christensen, Kaare and Cifkova, Renata and Ciullo, Marina and Concas, Maria Pina and Cook, James P. and Coresh, Josef and Corre, Tanguy and Sala, Cinzia Felicita and Cusi, Daniele and Danesh, John and Daw, E. Warwick and De Borst, Martin H. and De Grandi, Alessandro and De Mutsert, Renee and De Vries, Aiko P. J. and Degenhardt, Frauke and Delgado, Graciela and Demirkan, Ayse and Di Angelantonio, Emanuele and Dittrich, Katalin and Divers, Jasmin and Dorajoo, Rajkumar and Eckardt, Kai-Uwe and Ehret, Georg and Elliott, Paul and Endlich, Karlhans and Evans, Michele K. and Felix, Janine F. and Foo, Valencia Hui Xian and Franco, Oscar H. and Franke, Andre and Freedman, Barry I. and Freitag-Wolf, Sandra and Friedlander, Yechiel and Froguel, Philippe and Gansevoort, Ron T. and Gao, He and Gasparini, Paolo and Gaziano, J. Michael and Giedraitis, Vilmantas and Gieger, Christian and Girotto, Giorgia and Giulianini, Franco and Gogele, Martin and Gordon, Scott D. and Gudbjartsson, Daniel F. and Gudnason, Vilmundur and Haller, Toomas and Hamet, Pavel and Harris, Tamara B. and Hartman, Catharina A. and Hayward, Caroline and Hellwege, Jacklyn N. and Heng, Chew-Kiat and Hicks, Andrew A. and Hofer, Edith and Huang, Wei and Hutri-Kahonen, Nina and Hwang, Shih-Jen and Ikram, M. Arfan and Indridason, Olafur S. and Ingelsson, Erik and Ising, Marcus and Jaddoe, Vincent W. V. and Jakobsdottir, Johanna and Jonas, Jost B. and Joshi, Peter K. and Josyula, Navya Shilpa and Jung, Bettina and Kahonen, Mika and Kamatani, Yoichiro and Kammerer, Candace M. and Kanai, Masahiro and Kastarinen, Mika and Kerr, Shona M. and Khor, Chiea-Chuen and Kiess, Wieland and Kleber, Marcus E. and Koenig, Wolfgang and Kooner, Jaspal S. and Korner, Antje and Kovacs, Peter and Kraja, Aldi T. and Krajcoviechova, Alena and Kramer, Holly and Kramer, Bernhard K. and Kronenberg, Florian and Kubo, Michiaki and Kuhnel, Brigitte and Kuokkanen, Mikko and Kuusisto, Johanna and La Bianca, Martina and Laakso, Markku and Lange, Leslie A. and Langefeld, Carl D. and Lee, Jeannette Jen-Mai and Lehne, Benjamin and Lehtimaki, Terho and Lieb, Wolfgang and Lim, Su-Chi and Lind, Lars and Lindgren, Cecilia M. and Liu, Jun and Liu, Jianjun and Loeffler, Markus and Loos, Ruth J. F. and Lucae, Susanne and Lukas, Mary Ann and Lyytikainen, Leo-Pekka and Magi, Reedik and Magnusson, Patrik K. E. and Mahajan, Anubha and Martin, Nicholas G. and Martins, Jade and Marz, Winfried and Mascalzoni, Deborah and Matsuda, Koichi and Meisinger, Christa and Meitinger, Thomas and Melander, Olle and Metspalu, Andres and Mikaelsdottir, Evgenia K. and Milaneschi, Yuri and Miliku, Kozeta and Mishra, Pashupati P. and Program, V. A. Million Veteran and Mohlke, Karen L. and Mononen, Nina and Montgomery, Grant W. and Mook-Kanamori, Dennis O. and Mychaleckyj, Josyf C. and Nadkarni, Girish N. and Nalls, Mike A. and Nauck, Matthias and Nikus, Kjell and Ning, Boting and Nolte, Ilja M. and Noordam, Raymond and Olafsson, Isleifur and Oldehinkel, Albertine J. and Orho-Melander, Marju and Ouwehand, Willem H. and Padmanabhan, Sandosh and Palmer, Nicholette D. and Palsson, Runolfur and Penninx, Brenda W. J. H. and Perls, Thomas and Perola, Markus and Pirastu, Mario and Pirastu, Nicola and Pistis, Giorgio and Podgornaia, Anna I. and Polasek, Ozren and Ponte, Belen and Porteous, David J. and Poulain, Tanja and Pramstaller, Peter P. and Preuss, Michael H. and Prins, Bram P. and Province, Michael A. and Rabelink, Ton J. and Raffield, Laura M. and Raitakari, Olli T. and Reilly, Dermot F. and Rettig, Rainer and Rheinberger, Myriam and Rice, Kenneth M. and Ridker, Paul M. and Rivadeneira, Fernando and Rizzi, Federica and Roberts, David J. and Robino, Antonietta and Rossing, Peter and Rudan, Igor and Rueedi, Rico and Ruggiero, Daniela and Ryan, Kathleen A. and Saba, Yasaman and Sabanayagam, Charumathi and Salomaa, Veikko and Salvi, Erika and Saum, Kai-Uwe and Schmidt, Helena and Schmidt, Reinhold and Ben Schottker, and Schulz, Christina-Alexandra and Schupf, Nicole and Shaffer, Christian M. and Shi, Yuan and Smith, Albert V. and Smith, Blair H. and Soranzo, Nicole and Spracklen, Cassandra N. and Strauch, Konstantin and Stringham, Heather M. and Stumvoll, Michael and Svensson, Per O. and Szymczak, Silke and Tai, E-Shyong and Tajuddin, Salman M. and Tan, Nicholas Y. Q. and Taylor, Kent D. and Teren, Andrej and Tham, Yih-Chung and Thiery, Joachim and Thio, Chris H. L. and Thomsen, Hauke and Thorleifsson, Gudmar and Toniolo, Daniela and Tonjes, Anke and Tremblay, Johanne and Tzoulaki, Ioanna and Uitterlinden, Andre G. and Vaccargiu, Simona and Van Dam, Rob M. and Van der Harst, Pim and Van Duijn, Cornelia M. and Edward, Digna R. Velez and Verweij, Niek and Vogelezang, Suzanne and Volker, Uwe and Vollenweider, Peter and Waeber, Gerard and Waldenberger, Melanie and Wallentin, Lars and Wang, Ya Xing and Wang, Chaolong and Waterworth, Dawn M. and Bin Wei, Wen and White, Harvey and Whitfield, John B. and Wild, Sarah H. and Wilson, James F. and Wojczynski, Mary K. and Wong, Charlene and Wong, Tien-Yin and Xu, Liang and Yang, Qiong and Yasuda, Masayuki and Yerges-Armstrong, Laura M. and Zhang, Weihua and Zonderman, Alan B. and Rotter, Jerome I. and Bochud, Murielle and Psaty, Bruce M. and Vitart, Veronique and Wilson, James G. and Dehghan, Abbas and Parsa, Afshin and Chasman, Daniel I. and Ho, Kevin and Morris, Andrew P. and Devuyst, Olivier and Akilesh, Shreeram and Pendergrass, Sarah A. and Sim, Xueling and Boger, Carsten A. and Okada, Yukinori and Edwards, Todd L. and Snieder, Harold and Stefansson, Kari and Hung, Adriana M. and Heid, Iris M. and Scholz, Markus and Teumer, Alexander and Kottgen, Anna and Pattaro, Cristian},
  title     = {A catalog of genetic loci associated with kidney function from analyses of a million individuals},
  series = {Nature genetics},
  volume    = {51},
  journal   = {Nature genetics},
  number    = {6},
  publisher = {Nature Publ. Group},
  address   = {New York},
  organization    = {Lifelines COHort Study},
  issn      = {1061-4036},
  doi       = {10.1038/s41588-019-0407-x},
  pages     = {957 -- +},
  year      = {2019},
  abstract  = {Chronic kidney disease (CKD) is responsible for a public health burden with multi-systemic complications. Through transancestry meta-analysis of genome-wide association studies of estimated glomerular filtration rate (eGFR) and independent replication (n = 1,046,070), we identified 264 associated loci (166 new). Of these,147 were likely to be relevant for kidney function on the basis of associations with the alternative kidney function marker blood urea nitrogen (n = 416,178). Pathway and enrichment analyses, including mouse models with renal phenotypes, support the kidney as the main target organ. A genetic risk score for lower eGFR was associated with clinically diagnosed CKD in 452,264 independent individuals. Colocalization analyses of associations with eGFR among 783,978 European-ancestry individuals and gene expression across 46 human tissues, including tubulo-interstitial and glomerular kidney compartments, identified 17 genes differentially expressed in kidney. Fine-mapping highlighted missense driver variants in 11 genes and kidney-specific regulatory variants. These results provide a comprehensive priority list of molecular targets for translational research.},
  language  = {en}
}
@phdthesis{Wolf2021,
  author    = {Wolf, Johannes},
  title     = {Analysis and visualization of transport infrastructure based on large-scale geospatial mobile mapping data},
  doi       = {10.25932/publishup-53612},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-536129},
  school      = {Universit{\"a}t Potsdam},
  pages     = {vi, 121},
  year      = {2021},
  abstract  = {3D point clouds are a universal and discrete digital representation of three-dimensional objects and environments. For geospatial applications, 3D point clouds have become a fundamental type of raw data acquired and generated using various methods and techniques. In particular, 3D point clouds serve as raw data for creating digital twins of the built environment. This thesis concentrates on the research and development of concepts, methods, and techniques for preprocessing, semantically enriching, analyzing, and visualizing 3D point clouds for applications around transport infrastructure. It introduces a collection of preprocessing techniques that aim to harmonize raw 3D point cloud data, such as point density reduction and scan profile detection. Metrics such as, e.g., local density, verticality, and planarity are calculated for later use. One of the key contributions tackles the problem of analyzing and deriving semantic information in 3D point clouds. Three different approaches are investigated: a geometric analysis, a machine learning approach operating on synthetically generated 2D images, and a machine learning approach operating on 3D point clouds without intermediate representation. In the first application case, 2D image classification is applied and evaluated for mobile mapping data focusing on road networks to derive road marking vector data. The second application case investigates how 3D point clouds can be merged with ground-penetrating radar data for a combined visualization and to automatically identify atypical areas in the data. For example, the approach detects pavement regions with developing potholes. The third application case explores the combination of a 3D environment based on 3D point clouds with panoramic imagery to improve visual representation and the detection of 3D objects such as traffic signs. The presented methods were implemented and tested based on software frameworks for 3D point clouds and 3D visualization. In particular, modules for metric computation, classification procedures, and visualization techniques were integrated into a modular pipeline-based C++ research framework for geospatial data processing, extended by Python machine learning scripts. All visualization and analysis techniques scale to large real-world datasets such as road networks of entire cities or railroad networks. The thesis shows that some use cases allow taking advantage of established image vision methods to analyze images rendered from mobile mapping data efficiently. The two presented semantic classification methods working directly on 3D point clouds are use case independent and show similar overall accuracy when compared to each other. While the geometry-based method requires less computation time, the machine learning-based method supports arbitrary semantic classes but requires training the network with ground truth data. Both methods can be used in combination to gradually build this ground truth with manual corrections via a respective annotation tool. This thesis contributes results for IT system engineering of applications, systems, and services that require spatial digital twins of transport infrastructure such as road networks and railroad networks based on 3D point clouds as raw data. It demonstrates the feasibility of fully automated data flows that map captured 3D point clouds to semantically classified models. This provides a key component for seamlessly integrated spatial digital twins in IT solutions that require up-to-date, object-based, and semantically enriched information about the built environment.},
  language  = {en}
}
@article{WittigMirandaHoelzeretal.2022,
  author    = {Wittig, Alice and Miranda, Fabio Malcher and H{\"o}lzer, Martin and Altenburg, Tom and Bartoszewicz, Jakub Maciej and Beyvers, Sebastian and Dieckmann, Marius Alfred and Genske, Ulrich and Giese, Sven Hans-Joachim and Nowicka, Melania and Richard, Hugues and Schiebenhoefer, Henning and Schmachtenberg, Anna-Juliane and Sieben, Paul and Tang, Ming and Tembrockhaus, Julius and Renard, Bernhard Y. and Fuchs, Stephan},
  title     = {CovRadar},
  series = {Bioinformatics},
  volume    = {38},
  journal   = {Bioinformatics},
  number    = {17},
  publisher = {Oxford Univ. Press},
  address   = {Oxford},
  issn      = {1367-4803},
  doi       = {10.1093/bioinformatics/btac411},
  pages     = {4223 -- 4225},
  year      = {2022},
  abstract  = {The ongoing pandemic caused by SARS-CoV-2 emphasizes the importance of genomic surveillance to understand the evolution of the virus, to monitor the viral population, and plan epidemiological responses. Detailed analysis, easy visualization and intuitive filtering of the latest viral sequences are powerful for this purpose. We present CovRadar, a tool for genomic surveillance of the SARS-CoV-2 Spike protein. CovRadar consists of an analytical pipeline and a web application that enable the analysis and visualization of hundreds of thousand sequences. First, CovRadar extracts the regions of interest using local alignment, then builds a multiple sequence alignment, infers variants and consensus and finally presents the results in an interactive app, making accessing and reporting simple, flexible and fast.},
  language  = {en}
}
@article{WiemkerBunovaNeufeldetal.2022,
  author    = {Wiemker, Veronika and Bunova, Anna and Neufeld, Maria and Gornyi, Boris and Yurasova, Elena and Konigorski, Stefan and Kalinina, Anna and Kontsevaya, Anna and Ferreira-Borges, Carina and Probst, Charlotte},
  title     = {Pilot study to evaluate usability and acceptability of the 'Animated Alcohol Assessment Tool' in Russian primary healthcare},
  series = {Digital health},
  volume    = {8},
  journal   = {Digital health},
  publisher = {Sage Publications},
  address   = {London},
  issn      = {2055-2076},
  doi       = {10.1177/20552076211074491},
  pages     = {11},
  year      = {2022},
  abstract  = {Background and aims: Accurate and user-friendly assessment tools quantifying alcohol consumption are a prerequisite to effective prevention and treatment programmes, including Screening and Brief Intervention. Digital tools offer new potential in this field. We developed the 'Animated Alcohol Assessment Tool' (AAA-Tool), a mobile app providing an interactive version of the World Health Organization's Alcohol Use Disorders Identification Test (AUDIT) that facilitates the description of individual alcohol consumption via culturally informed animation features. This pilot study evaluated the Russia-specific version of the Animated Alcohol Assessment Tool with regard to (1) its usability and acceptability in a primary healthcare setting, (2) the plausibility of its alcohol consumption assessment results and (3) the adequacy of its Russia-specific vessel and beverage selection. Methods: Convenience samples of 55 patients (47\% female) and 15 healthcare practitioners (80\% female) in 2 Russian primary healthcare facilities self-administered the Animated Alcohol Assessment Tool and rated their experience on the Mobile Application Rating Scale - User Version. Usage data was automatically collected during app usage, and additional feedback on regional content was elicited in semi-structured interviews. Results: On average, patients completed the Animated Alcohol Assessment Tool in 6:38 min (SD = 2.49, range = 3.00-17.16). User satisfaction was good, with all subscale Mobile Application Rating Scale - User Version scores averaging >3 out of 5 points. A majority of patients (53\%) and practitioners (93\%) would recommend the tool to 'many people' or 'everyone'. Assessed alcohol consumption was plausible, with a low number (14\%) of logically impossible entries. Most patients reported the Animated Alcohol Assessment Tool to reflect all vessels (78\%) and all beverages (71\%) they typically used. Conclusion: High acceptability ratings by patients and healthcare practitioners, acceptable completion time, plausible alcohol usage assessment results and perceived adequacy of region-specific content underline the Animated Alcohol Assessment Tool's potential to provide a novel approach to alcohol assessment in primary healthcare. After its validation, the Animated Alcohol Assessment Tool might contribute to reducing alcohol-related harm by facilitating Screening and Brief Intervention implementation in Russia and beyond.},
  language  = {en}
}
@misc{WelearegaiSchlueterHammer2019,
  author    = {Welearegai, Gebrehiwet B. and Schlueter, Max and Hammer, Christian},
  title     = {Static security evaluation of an industrial web application},
  series = {Proceedings of the 34th ACM/SIGAPP Symposium on Applied Computing},
  journal   = {Proceedings of the 34th ACM/SIGAPP Symposium on Applied Computing},
  publisher = {Association for Computing Machinery},
  address   = {New York},
  isbn      = {978-1-4503-5933-7},
  doi       = {10.1145/3297280.3297471},
  pages     = {1952 -- 1961},
  year      = {2019},
  abstract  = {JavaScript is the most popular programming language for web applications. Static analysis of JavaScript applications is highly challenging due to its dynamic language constructs and event-driven asynchronous executions, which also give rise to many security-related bugs. Several static analysis tools to detect such bugs exist, however, research has not yet reported much on the precision and scalability trade-off of these analyzers. As a further obstacle, JavaScript programs structured in Node. js modules need to be collected for analysis, but existing bundlers are either specific to their respective analysis tools or not particularly suitable for static analysis.},
  language  = {en}
}
@book{Weber2023,
  author    = {Weber, Benedikt},
  title     = {Human pose estimation for decubitus prophylaxis},
  number    = {153},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-551-4},
  issn      = {1613-5652},
  doi       = {10.25932/publishup-56719},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-567196},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {73},
  year      = {2023},
  abstract  = {Decubitus is one of the most relevant diseases in nursing and the most expensive to treat. It is caused by sustained pressure on tissue, so it particularly affects bed-bound patients. This work lays a foundation for pressure mattress-based decubitus prophylaxis by implementing a solution to the single-frame 2D Human Pose Estimation problem. For this, methods of Deep Learning are employed. Two approaches are examined, a coarse-to-fine Convolutional Neural Network for direct regression of joint coordinates and a U-Net for the derivation of probability distribution heatmaps. We conclude that training our models on a combined dataset of the publicly available Bodies at Rest and SLP data yields the best results. Furthermore, various preprocessing techniques are investigated, and a hyperparameter optimization is performed to discover an improved model architecture. Another finding indicates that the heatmap-based approach outperforms direct regression. This model achieves a mean per-joint position error of 9.11 cm for the Bodies at Rest data and 7.43 cm for the SLP data. We find that it generalizes well on data from mattresses other than those seen during training but has difficulties detecting the arms correctly. Additionally, we give a brief overview of the medical data annotation tool annoto we developed in the bachelor project and furthermore conclude that the Scrum framework and agile practices enhanced our development workflow.},
  language  = {en}
}
@article{VollmerTrappSchumannetal.2018,
  author    = {Vollmer, Jan Ole and Trapp, Matthias and Schumann, Heidrun and D{\"o}llner, J{\"u}rgen Roland Friedrich},
  title     = {Hierarchical spatial aggregation for level-of-detail visualization of 3D thematic data},
  series = {ACM transactions on spatial algorithms and systems},
  volume    = {4},
  journal   = {ACM transactions on spatial algorithms and systems},
  number    = {3},
  publisher = {Association for Computing Machinery},
  address   = {New York},
  issn      = {2374-0353},
  doi       = {10.1145/3234506},
  pages     = {23},
  year      = {2018},
  abstract  = {Thematic maps are a common tool to visualize semantic data with a spatial reference. Combining thematic data with a geometric representation of their natural reference frame aids the viewer's ability in gaining an overview, as well as perceiving patterns with respect to location; however, as the amount of data for visualization continues to increase, problems such as information overload and visual clutter impede perception, requiring data aggregation and level-of-detail visualization techniques. While existing aggregation techniques for thematic data operate in a 2D reference frame (i.e., map), we present two aggregation techniques for 3D spatial and spatiotemporal data mapped onto virtual city models that hierarchically aggregate thematic data in real time during rendering to support on-the-fly and on-demand level-of-detail generation. An object-based technique performs aggregation based on scene-specific objects and their hierarchy to facilitate per-object analysis, while the scene-based technique aggregates data solely based on spatial locations, thus supporting visual analysis of data with arbitrary reference geometry. Both techniques can apply different aggregation functions (mean, minimum, and maximum) for ordinal, interval, and ratio-scaled data and can be easily extended with additional functions. Our implementation utilizes the programmable graphics pipeline and requires suitably encoded data, i.e., textures or vertex attributes. We demonstrate the application of both techniques using real-world datasets, including solar potential analyses and the propagation of pressure waves in a virtual city model.},
  language  = {en}
}
@phdthesis{Vogel2018,
  author    = {Vogel, Thomas},
  title     = {Model-driven engineering of self-adaptive software},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-409755},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xvi, 357},
  year      = {2018},
  abstract  = {The development of self-adaptive software requires the engineering of an adaptation engine that controls the underlying adaptable software by a feedback loop. State-of-the-art approaches prescribe the feedback loop in terms of numbers, how the activities (e.g., monitor, analyze, plan, and execute (MAPE)) and the knowledge are structured to a feedback loop, and the type of knowledge. Moreover, the feedback loop is usually hidden in the implementation or framework and therefore not visible in the architectural design. Additionally, an adaptation engine often employs runtime models that either represent the adaptable software or capture strategic knowledge such as reconfiguration strategies. State-of-the-art approaches do not systematically address the interplay of such runtime models, which would otherwise allow developers to freely design the entire feedback loop. This thesis presents ExecUtable RuntimE MegAmodels (EUREMA), an integrated model-driven engineering (MDE) solution that rigorously uses models for engineering feedback loops. EUREMA provides a domain-specific modeling language to specify and an interpreter to execute feedback loops. The language allows developers to freely design a feedback loop concerning the activities and runtime models (knowledge) as well as the number of feedback loops. It further supports structuring the feedback loops in the adaptation engine that follows a layered architectural style. Thus, EUREMA makes the feedback loops explicit in the design and enables developers to reason about design decisions. To address the interplay of runtime models, we propose the concept of a runtime megamodel, which is a runtime model that contains other runtime models as well as activities (e.g., MAPE) working on the contained models. This concept is the underlying principle of EUREMA. The resulting EUREMA (mega)models are kept alive at runtime and they are directly executed by the EUREMA interpreter to run the feedback loops. Interpretation provides the flexibility to dynamically adapt a feedback loop. In this context, EUREMA supports engineering self-adaptive software in which feedback loops run independently or in a coordinated fashion within the same layer as well as on top of each other in different layers of the adaptation engine. Moreover, we consider preliminary means to evolve self-adaptive software by providing a maintenance interface to the adaptation engine. This thesis discusses in detail EUREMA by applying it to different scenarios such as single, multiple, and stacked feedback loops for self-repairing and self-optimizing the mRUBiS application. Moreover, it investigates the design and expressiveness of EUREMA, reports on experiments with a running system (mRUBiS) and with alternative solutions, and assesses EUREMA with respect to quality attributes such as performance and scalability. The conducted evaluation provides evidence that EUREMA as an integrated and open MDE approach for engineering self-adaptive software seamlessly integrates the development and runtime environments using the same formalism to specify and execute feedback loops, supports the dynamic adaptation of feedback loops in layered architectures, and achieves an efficient execution of feedback loops by leveraging incrementality.},
  language  = {en}
}