@article{ŞahinEgloffsteinBotheetal.2021, author = {Şahin, Muhittin and Egloffstein, Marc and Bothe, Max and Rohloff, Tobias and Schenk, Nathanael and Schwerer, Florian and Ifenthaler, Dirk}, title = {Behavioral Patterns in Enterprise MOOCs at openSAP}, series = {EMOOCs 2021}, volume = {2021}, journal = {EMOOCs 2021}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-512-5}, doi = {10.25932/publishup-51735}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-517350}, pages = {281 -- 288}, year = {2021}, language = {en} } @article{OezdemirKurbanPekkan2021, author = {{\"O}zdemir, Paker Doğu and Kurban, Caroline Fell and Pekkan, Zelha Tun{\c{c}}}, title = {MOOC-Based Online Instruction}, series = {EMOOCs 2021}, volume = {2021}, journal = {EMOOCs 2021}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-512-5}, doi = {10.25932/publishup-51690}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-516900}, pages = {17 -- 33}, year = {2021}, abstract = {If taking a flipped learning approach, MOOC content can be used for online pre-class instruction. After which students can put the knowledge they gained from the MOOC into practice either synchronously or asynchronously. This study examined one such, asynchronous, course in teacher education. The course ran with 40 students over 13 weeks from February to May 2020. A case study approach was followed using mixed methods to assess the efficacy of the course. Quantitative data was gathered on achievement of learning outcomes, online engagement, and satisfaction. Qualitative data was gathered via student interviews from which a thematic analysis was undertaken. From a combined analysis of the data, three themes emerged as pertinent to course efficacy: quality and quantity of communication and collaboration; suitability of the MOOC; and significance for career development.}, language = {en} } @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} }