@phdthesis{Lilienkamp2024,
  author    = {Lilienkamp, Henning},
  title     = {Enhanced computational approaches for data-driven characterization of earthquake ground motion and rapid earthquake impact assessment},
  doi       = {10.25932/publishup-63195},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-631954},
  school      = {Universit{\"a}t Potsdam},
  pages     = {x, 145},
  year      = {2024},
  abstract  = {Rapidly growing seismic and macroseismic databases and simplified access to advanced machine learning methods have in recent years opened up vast opportunities to address challenges in engineering and strong motion seismology from novel, datacentric perspectives. In this thesis, I explore the opportunities of such perspectives for the tasks of ground motion modeling and rapid earthquake impact assessment, tasks with major implications for long-term earthquake disaster mitigation. In my first study, I utilize the rich strong motion database from the Kanto basin, Japan, and apply the U-Net artificial neural network architecture to develop a deep learning based ground motion model. The operational prototype provides statistical estimates of expected ground shaking, given descriptions of a specific earthquake source, wave propagation paths, and geophysical site conditions. The U-Net interprets ground motion data in its spatial context, potentially taking into account, for example, the geological properties in the vicinity of observation sites. Predictions of ground motion intensity are thereby calibrated to individual observation sites and earthquake locations. The second study addresses the explicit incorporation of rupture forward directivity into ground motion modeling. Incorporation of this phenomenon, causing strong, pulse like ground shaking in the vicinity of earthquake sources, is usually associated with an intolerable increase in computational demand during probabilistic seismic hazard analysis (PSHA) calculations. I suggest an approach in which I utilize an artificial neural network to efficiently approximate the average, directivity-related adjustment to ground motion predictions for earthquake ruptures from the 2022 New Zealand National Seismic Hazard Model. The practical implementation in an actual PSHA calculation demonstrates the efficiency and operational readiness of my model. In a follow-up study, I present a proof of concept for an alternative strategy in which I target the generalizing applicability to ruptures other than those from the New Zealand National Seismic Hazard Model. In the third study, I address the usability of pseudo-intensity reports obtained from macroseismic observations by non-expert citizens for rapid impact assessment. I demonstrate that the statistical properties of pseudo-intensity collections describing the intensity of shaking are correlated with the societal impact of earthquakes. In a second step, I develop a probabilistic model that, within minutes of an event, quantifies the probability of an earthquake to cause considerable societal impact. Under certain conditions, such a quick and preliminary method might be useful to support decision makers in their efforts to organize auxiliary measures for earthquake disaster response while results from more elaborate impact assessment frameworks are not yet available. The application of machine learning methods to datasets that only partially reveal characteristics of Big Data, qualify the majority of results obtained in this thesis as explorative insights rather than ready-to-use solutions to real world problems. The practical usefulness of this work will be better assessed in the future by applying the approaches developed to growing and increasingly complex data sets.},
  language  = {en}
}
@article{BaberowskiLeonhardtRentschetal.2023,
  author    = {Baberowski, David and Leonhardt, Thiemo and Rentsch, Susanne and Bergner, Nadine},
  title     = {Aufbau informatischer Kompetenzen im Kontext KI bei Lehramtsstudierenden des Faches Politik},
  series = {Hochschuldidaktik Informatik HDI 2021 (Commentarii informaticae didacticae)},
  journal   = {Hochschuldidaktik Informatik HDI 2021 (Commentarii informaticae didacticae)},
  number    = {13},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-548-4},
  issn      = {1868-0844},
  doi       = {10.25932/publishup-61599},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-615995},
  pages     = {189 -- 209},
  year      = {2023},
  abstract  = {Lehrkr{\"a}fte aller F{\"a}cher ben{\"o}tigen informatische Kompetenzen, um der wachsenden Alltagsrelevanz von Informatik und aktuell g{\"u}ltigen Lehrpl{\"a}nen gerecht zu werden. Beispielsweise verweist in Sachsen der Lehrplan f{\"u}r das Fach Gemeinschaftskunde, Rechtserziehung und Wirtschaft am Gymnasium mit dem f{\"u}r die Jahrgangsstufe 11 vorgesehenem Thema „Digitalisierung und sozialer Wandel" auf K{\"u}nstliche Intelligenz (KI) und explizit auf die Bedeutung der informatischen Bildung. Um die n{\"o}tigen informatischen Grundlagen zu vermitteln, wurde f{\"u}r Lehramtsstudierende des Faches Politik ein Workshop erarbeitet, der die Grundlagen der Funktionsweise von KI anhand von {\"u}berwachtem maschinellen Lernen in neuronalen Netzen vermittelt. Inhalt des Workshops ist es, mit Bezug auf gesellschaftliche Implikationen wie Datenschutz bei Trainingsdaten und algorithmic bias einen informierten Diskurs zu politischen Themen zu erm{\"o}glichen. Ziele des Workshops f{\"u}r Lehramtsstudierende mit dem Fach Politik sind: (1) Aufbau informatischer Kompetenzen in Bezug zum Thema KI, (2) St{\"a}rkung der Diskussionsf{\"a}higkeiten der Studierenden durch passende informatische Kompetenzen und (3) Anregung der Studierenden zum Transfer auf passende Themenstellungen im Politikunterricht. Das Evaluationskonzept umfasst eine Pre-Post-Befragung zur Zuversicht zur Vermittlungskompetenz unter Bezug auf maschinelles Lernen in neuronalen Netzen im Unterricht, sowie die Analyse einer abschließenden Diskussion. F{\"u}r die Pre-Post-Befragung konnte eine Steigerung der Zuversicht zur Vermittlungskompetenz beobachtet werden. Die Analyse der Diskussion zeigte das Bewusstsein der Alltagsrelevanz des Themas KI bei den Teilnehmenden, aber noch keine Anwendung der informatischen Inhalte des Workshops zur St{\"u}tzung der Argumente in der Diskussion.},
  language  = {de}
}
@phdthesis{Smirnov2023,
  author    = {Smirnov, Artem},
  title     = {Understanding the dynamics of the near-earth space environment utilizing long-term satellite observations},
  doi       = {10.25932/publishup-61371},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-613711},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xxxvi, 286},
  year      = {2023},
  abstract  = {The near-Earth space environment is a highly complex system comprised of several regions and particle populations hazardous to satellite operations. The trapped particles in the radiation belts and ring current can cause significant damage to satellites during space weather events, due to deep dielectric and surface charging. Closer to Earth is another important region, the ionosphere, which delays the propagation of radio signals and can adversely affect navigation and positioning. In response to fluctuations in solar and geomagnetic activity, both the inner-magnetospheric and ionospheric populations can undergo drastic and sudden changes within minutes to hours, which creates a challenge for predicting their behavior. Given the increasing reliance of our society on satellite technology, improving our understanding and modeling of these populations is a matter of paramount importance. In recent years, numerous spacecraft have been launched to study the dynamics of particle populations in the near-Earth space, transforming it into a data-rich environment. To extract valuable insights from the abundance of available observations, it is crucial to employ advanced modeling techniques, and machine learning methods are among the most powerful approaches available. This dissertation employs long-term satellite observations to analyze the processes that drive particle dynamics, and builds interdisciplinary links between space physics and machine learning by developing new state-of-the-art models of the inner-magnetospheric and ionospheric particle dynamics. The first aim of this thesis is to investigate the behavior of electrons in Earth's radiation belts and ring current. Using ~18 years of electron flux observations from the Global Positioning System (GPS), we developed the first machine learning model of hundreds-of-keV electron flux at Medium Earth Orbit (MEO) that is driven solely by solar wind and geomagnetic indices and does not require auxiliary flux measurements as inputs. We then proceeded to analyze the directional distributions of electrons, and for the first time, used Fourier sine series to fit electron pitch angle distributions (PADs) in Earth's inner magnetosphere. We performed a superposed epoch analysis of 129 geomagnetic storms during the Van Allen Probes era and demonstrated that electron PADs have a strong energy-dependent response to geomagnetic activity. Additionally, we showed that the solar wind dynamic pressure could be used as a good predictor of the PAD dynamics. Using the observed dependencies, we created the first PAD model with a continuous dependence on L, magnetic local time (MLT) and activity, and developed two techniques to reconstruct near-equatorial electron flux observations from low-PA data using this model. The second objective of this thesis is to develop a novel model of the topside ionosphere. To achieve this goal, we collected observations from five of the most widely used ionospheric missions and intercalibrated these data sets. This allowed us to use these data jointly for model development, validation, and comparison with other existing empirical models. We demonstrated, for the first time, that ion density observations by Swarm Langmuir Probes exhibit overestimation (up to ~40-50\%) at low and mid-latitudes on the night side, and suggested that the influence of light ions could be a potential cause of this overestimation. To develop the topside model, we used 19 years of radio occultation (RO) electron density profiles, which were fitted with a Chapman function with a linear dependence of scale height on altitude. This approximation yields 4 parameters, namely the peak density and height of the F2-layer and the slope and intercept of the linear scale height trend, which were modeled using feedforward neural networks (NNs). The model was extensively validated against both RO and in-situ observations and was found to outperform the International Reference Ionosphere (IRI) model by up to an order of magnitude. Our analysis showed that the most substantial deviations of the IRI model from the data occur at altitudes of 100-200 km above the F2-layer peak. The developed NN-based ionospheric model reproduces the effects of various physical mechanisms observed in the topside ionosphere and provides highly accurate electron density predictions. This dissertation provides an extensive study of geospace dynamics, and the main results of this work contribute to the improvement of models of plasma populations in the near-Earth space environment.},
  language  = {en}
}
@phdthesis{Seleem2023,
  author    = {Seleem, Omar},
  title     = {Towards urban pluvial flood mapping using data-driven models},
  doi       = {10.25932/publishup-59813},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-598137},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xv, 95},
  year      = {2023},
  abstract  = {Casualties and damages from urban pluvial flooding are increasing. Triggered by short, localized, and intensive rainfall events, urban pluvial floods can occur anywhere, even in areas without a history of flooding. Urban pluvial floods have relatively small temporal and spatial scales. Although cumulative losses from urban pluvial floods are comparable, most flood risk management and mitigation strategies focus on fluvial and coastal flooding. Numerical-physical-hydrodynamic models are considered the best tool to represent the complex nature of urban pluvial floods; however, they are computationally expensive and time-consuming. These sophisticated models make large-scale analysis and operational forecasting prohibitive. Therefore, it is crucial to evaluate and benchmark the performance of other alternative methods. The findings of this cumulative thesis are represented in three research articles. The first study evaluates two topographic-based methods to map urban pluvial flooding, fill-spill-merge (FSM) and topographic wetness index (TWI), by comparing them against a sophisticated hydrodynamic model. The FSM method identifies flood-prone areas within topographic depressions while the TWI method employs maximum likelihood estimation to calibrate a TWI threshold (τ) based on inundation maps from the 2D hydrodynamic model. The results point out that the FSM method outperforms the TWI method. The study highlights then the advantage and limitations of both methods. Data-driven models provide a promising alternative to computationally expensive hydrodynamic models. However, the literature lacks benchmarking studies to evaluate the different models' performance, advantages and limitations. Model transferability in space is a crucial problem. Most studies focus on river flooding, likely due to the relative availability of flow and rain gauge records for training and validation. Furthermore, they consider these models as black boxes. The second study uses a flood inventory for the city of Berlin and 11 predictive features which potentially indicate an increased pluvial flooding hazard to map urban pluvial flood susceptibility using a convolutional neural network (CNN), an artificial neural network (ANN) and the benchmarking machine learning models random forest (RF) and support vector machine (SVM). I investigate the influence of spatial resolution on the implemented models, the models' transferability in space and the importance of the predictive features. The results show that all models perform well and the RF models are superior to the other models within and outside the training domain. The models developed using fine spatial resolution (2 and 5 m) could better identify flood-prone areas. Finally, the results point out that aspect is the most important predictive feature for the CNN models, and altitude is for the other models. While flood susceptibility maps identify flood-prone areas, they do not represent flood variables such as velocity and depth which are necessary for effective flood risk management. To address this, the third study investigates data-driven models' transferability to predict urban pluvial floodwater depth and the models' ability to enhance their predictions using transfer learning techniques. It compares the performance of RF (the best-performing model in the previous study) and CNN models using 12 predictive features and output from a hydrodynamic model. The findings in the third study suggest that while CNN models tend to generalise and smooth the target function on the training dataset, RF models suffer from overfitting. Hence, RF models are superior for predictions inside the training domains but fail outside them while CNN models could control the relative loss in performance outside the training domains. Finally, the CNN models benefit more from transfer learning techniques than RF models, boosting their performance outside training domains. In conclusion, this thesis has evaluated both topographic-based methods and data-driven models to map urban pluvial flooding. However, further studies are crucial to have methods that completely overcome the limitation of 2D hydrodynamic models.},
  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}
}
@book{RanaMohapatraSidorovaetal.2022,
  author    = {Rana, Kaushik and Mohapatra, Durga Prasad and Sidorova, Julia and Lundberg, Lars and Sk{\"o}ld, Lars and Lopes Grim, Lu{\´i}s Fernando and Sampaio Gradvohl, Andr{\´e} Leon and Cremerius, Jonas and Siegert, Simon and Weltzien, Anton von and Baldi, Annika and Klessascheck, Finn and Kalancha, Svitlana and Lichtenstein, Tom and Shaabani, Nuhad and Meinel, Christoph and Friedrich, Tobias and Lenzner, Pascal and Schumann, David and Wiese, Ingmar and Sarna, Nicole and Wiese, Lena and Tashkandi, Araek Sami and van der Walt, Est{\´e}e and Eloff, Jan H. P. and Schmidt, Christopher and H{\"u}gle, Johannes and Horschig, Siegfried and Uflacker, Matthias and Najafi, Pejman and Sapegin, Andrey and Cheng, Feng and Stojanovic, Dragan and Stojnev Ilić, Aleksandra and Djordjevic, Igor and Stojanovic, Natalija and Predic, Bratislav and Gonz{\´a}lez-Jim{\´e}nez, Mario and de Lara, Juan and Mischkewitz, Sven and Kainz, Bernhard and van Hoorn, Andr{\´e} and Ferme, Vincenzo and Schulz, Henning and Knigge, Marlene and Hecht, Sonja and Prifti, Loina and Krcmar, Helmut and Fabian, Benjamin and Ermakova, Tatiana and Kelkel, Stefan and Baumann, Annika and Morgenstern, Laura and Plauth, Max and Eberhard, Felix and Wolff, Felix and Polze, Andreas and Cech, Tim and Danz, Noel and Noack, Nele Sina and Pirl, Lukas and Beilharz, Jossekin Jakob and De Oliveira, Roberto C. L. and Soares, F{\´a}bio Mendes and Juiz, Carlos and Bermejo, Belen and M{\"u}hle, Alexander and Gr{\"u}ner, Andreas and Saxena, Vageesh and Gayvoronskaya, Tatiana and Weyand, Christopher and Krause, Mirko and Frank, Markus and Bischoff, Sebastian and Behrens, Freya and R{\"u}ckin, Julius and Ziegler, Adrian and Vogel, Thomas and Tran, Chinh and Moser, Irene and Grunske, Lars and Sz{\´a}rnyas, G{\´a}bor and Marton, J{\´o}zsef and Maginecz, J{\´a}nos and Varr{\´o}, D{\´a}niel and Antal, J{\´a}nos Benjamin},
  title     = {HPI Future SOC Lab - Proceedings 2018},
  number    = {151},
  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      = {978-3-86956-547-7},
  issn      = {1613-5652},
  doi       = {10.25932/publishup-56371},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-563712},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {x, 277},
  year      = {2022},
  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 2018. Selected projects have presented their results on April 17th and November 14th 2017 at the Future SOC Lab Day events.},
  language  = {en}
}
@phdthesis{Chen2023,
  author    = {Chen, Junchao},
  title     = {A self-adaptive resilient method for implementing and managing the high-reliability processing system},
  doi       = {10.25932/publishup-58313},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-583139},
  school      = {Universit{\"a}t Potsdam},
  pages     = {XXIII, 167},
  year      = {2023},
  abstract  = {As a result of CMOS scaling, radiation-induced Single-Event Effects (SEEs) in electronic circuits became a critical reliability issue for modern Integrated Circuits (ICs) operating under harsh radiation conditions. SEEs can be triggered in combinational or sequential logic by the impact of high-energy particles, leading to destructive or non-destructive faults, resulting in data corruption or even system failure. Typically, the SEE mitigation methods are deployed statically in processing architectures based on the worst-case radiation conditions, which is most of the time unnecessary and results in a resource overhead. Moreover, the space radiation conditions are dynamically changing, especially during Solar Particle Events (SPEs). The intensity of space radiation can differ over five orders of magnitude within a few hours or days, resulting in several orders of magnitude fault probability variation in ICs during SPEs. This thesis introduces a comprehensive approach for designing a self-adaptive fault resilient multiprocessing system to overcome the static mitigation overhead issue. This work mainly addresses the following topics: (1) Design of on-chip radiation particle monitor for real-time radiation environment detection, (2) Investigation of space environment predictor, as support for solar particle events forecast, (3) Dynamic mode configuration in the resilient multiprocessing system. Therefore, according to detected and predicted in-flight space radiation conditions, the target system can be configured to use no mitigation or low-overhead mitigation during non-critical periods of time. The redundant resources can be used to improve system performance or save power. On the other hand, during increased radiation activity periods, such as SPEs, the mitigation methods can be dynamically configured appropriately depending on the real-time space radiation environment, resulting in higher system reliability. Thus, a dynamic trade-off in the target system between reliability, performance and power consumption in real-time can be achieved. All results of this work are evaluated in a highly reliable quad-core multiprocessing system that allows the self-adaptive setting of optimal radiation mitigation mechanisms during run-time. Proposed methods can serve as a basis for establishing a comprehensive self-adaptive resilient system design process. Successful implementation of the proposed design in the quad-core multiprocessor shows its application perspective also in the other designs.},
  language  = {en}
}
@phdthesis{Brill2022,
  author    = {Brill, Fabio Alexander},
  title     = {Applications of machine learning and open geospatial data in flood risk modelling},
  doi       = {10.25932/publishup-55594},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-555943},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xix, 124},
  year      = {2022},
  abstract  = {Der technologische Fortschritt erlaubt es, zunehmend komplexe Vorhersagemodelle auf Basis immer gr{\"o}ßerer Datens{\"a}tze zu produzieren. F{\"u}r das Risikomanagement von Naturgefahren sind eine Vielzahl von Modellen als Entscheidungsgrundlage notwendig, z.B. in der Auswertung von Beobachtungsdaten, f{\"u}r die Vorhersage von Gefahrenszenarien, oder zur statistischen Absch{\"a}tzung der zu erwartenden Sch{\"a}den. Es stellt sich also die Frage, inwiefern moderne Modellierungsans{\"a}tze wie das maschinelle Lernen oder Data-Mining in diesem Themenbereich sinnvoll eingesetzt werden k{\"o}nnen. Zus{\"a}tzlich ist im Hinblick auf die Datenverf{\"u}gbarkeit und -zug{\"a}nglichkeit ein Trend zur {\"O}ffnung (open data) zu beobachten. Thema dieser Arbeit ist daher, die M{\"o}glichkeiten und Grenzen des maschinellen Lernens und frei verf{\"u}gbarer Geodaten auf dem Gebiet der Hochwasserrisikomodellierung im weiteren Sinne zu untersuchen. Da dieses {\"u}bergeordnete Thema sehr breit ist, werden einzelne relevante Aspekte herausgearbeitet und detailliert betrachtet. Eine prominente Datenquelle im Bereich Hochwasser ist die satellitenbasierte Kartierung von {\"U}berflutungsfl{\"a}chen, die z.B. {\"u}ber den Copernicus Service der Europ{\"a}ischen Union frei zur Verf{\"u}gung gestellt werden. Große Hoffnungen werden in der wissenschaftlichen Literatur in diese Produkte gesetzt, sowohl f{\"u}r die akute Unterst{\"u}tzung der Einsatzkr{\"a}fte im Katastrophenfall, als auch in der Modellierung mittels hydrodynamischer Modelle oder zur Schadensabsch{\"a}tzung. Daher wurde ein Fokus in dieser Arbeit auf die Untersuchung dieser Flutmasken gelegt. Aus der Beobachtung, dass die Qualit{\"a}t dieser Produkte in bewaldeten und urbanen Gebieten unzureichend ist, wurde ein Verfahren zur nachtr{\"a}glichenVerbesserung mittels maschinellem Lernen entwickelt. Das Verfahren basiert auf einem Klassifikationsalgorithmus der nur Trainingsdaten von einer vorherzusagenden Klasse ben{\"o}tigt, im konkreten Fall also Daten von {\"U}berflutungsfl{\"a}chen, nicht jedoch von der negativen Klasse (trockene Gebiete). Die Anwendung f{\"u}r Hurricane Harvey in Houston zeigt großes Potenzial der Methode, abh{\"a}ngig von der Qualit{\"a}t der urspr{\"u}nglichen Flutmaske. Anschließend wird anhand einer prozessbasierten Modellkette untersucht, welchen Einfluss implementierte physikalische Prozessdetails auf das vorhergesagte statistische Risiko haben. Es wird anschaulich gezeigt, was eine Risikostudie basierend auf etablierten Modellen leisten kann. Solche Modellketten sind allerdings bereits f{\"u}r Flusshochwasser sehr komplex, und f{\"u}r zusammengesetzte oder kaskadierende Ereignisse mit Starkregen, Sturzfluten, und weiteren Prozessen, kaum vorhanden. Im vierten Kapitel dieser Arbeit wird daher getestet, ob maschinelles Lernen auf Basis von vollst{\"a}ndigen Schadensdaten einen direkteren Weg zur Schadensmodellierung erm{\"o}glicht, der die explizite Konzeption einer solchen Modellkette umgeht. Dazu wird ein staatlich erhobener Datensatz der gesch{\"a}digten Geb{\"a}ude w{\"a}hrend des schweren El Ni{\~n}o Ereignisses 2017 in Peru verwendet. In diesem Kontext werden auch die M{\"o}glichkeiten des Data-Mining zur Extraktion von Prozessverst{\"a}ndnis ausgelotet. Es kann gezeigt werden, dass diverse frei verf{\"u}gbare Geodaten n{\"u}tzliche Informationen f{\"u}r die Gefahren- und Schadensmodellierung von komplexen Flutereignissen liefern, z.B. satellitenbasierte Regenmessungen, topographische und hydrographische Information, kartierte Siedlungsfl{\"a}chen, sowie Indikatoren aus Spektraldaten. Zudem zeigen sich Erkenntnisse zu den Sch{\"a}digungsprozessen, die im Wesentlichen mit den vorherigen Erwartungen in Einklang stehen. Die maximale Regenintensit{\"a}t wirkt beispielsweise in St{\"a}dten und steilen Schluchten st{\"a}rker sch{\"a}digend, w{\"a}hrend die Niederschlagssumme in tiefliegenden Flussgebieten und bewaldeten Regionen als aussagekr{\"a}ftiger befunden wurde. L{\"a}ndliche Gebiete in Peru weisen in der pr{\"a}sentierten Studie eine h{\"o}here Vulnerabilit{\"a}t als die Stadtgebiete auf. Jedoch werden auch die grunds{\"a}tzlichen Grenzen der Methodik und die Abh{\"a}ngigkeit von spezifischen Datens{\"a}tzen and Algorithmen offenkundig. In der {\"u}bergreifenden Diskussion werden schließlich die verschiedenen Methoden - prozessbasierte Modellierung, pr{\"a}diktives maschinelles Lernen, und Data-Mining - mit Blick auf die Gesamtfragestellungen evaluiert. Im Bereich der Gefahrenbeobachtung scheint eine Fokussierung auf neue Algorithmen sinnvoll. Im Bereich der Gefahrenmodellierung, insbesondere f{\"u}r Flusshochwasser, wird eher die Verbesserung von physikalischen Modellen, oder die Integration von prozessbasierten und statistischen Verfahren angeraten. In der Schadensmodellierung fehlen nach wie vor die großen repr{\"a}sentativen Datens{\"a}tze, die f{\"u}r eine breite Anwendung von maschinellem Lernen Voraussetzung ist. Daher ist die Verbesserung der Datengrundlage im Bereich der Sch{\"a}den derzeit als wichtiger einzustufen als die Auswahl der Algorithmen.},
  language  = {en}
}
@phdthesis{Elsaid2022,
  author    = {Elsaid, Mohamed Esameldin Mohamed},
  title     = {Virtual machines live migration cost modeling and prediction},
  doi       = {10.25932/publishup-54001},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-540013},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xiv, 107},
  year      = {2022},
  abstract  = {Dynamic resource management is an essential requirement for private and public cloud computing environments. With dynamic resource management, the physical resources assignment to the cloud virtual resources depends on the actual need of the applications or the running services, which enhances the cloud physical resources utilization and reduces the offered services cost. In addition, the virtual resources can be moved across different physical resources in the cloud environment without an obvious impact on the running applications or services production. This means that the availability of the running services and applications in the cloud is independent on the hardware resources including the servers, switches and storage failures. This increases the reliability of using cloud services compared to the classical data-centers environments. In this thesis we briefly discuss the dynamic resource management topic and then deeply focus on live migration as the definition of the compute resource dynamic management. Live migration is a commonly used and an essential feature in cloud and virtual data-centers environments. Cloud computing load balance, power saving and fault tolerance features are all dependent on live migration to optimize the virtual and physical resources usage. As we will discuss in this thesis, live migration shows many benefits to cloud and virtual data-centers environments, however the cost of live migration can not be ignored. Live migration cost includes the migration time, downtime, network overhead, power consumption increases and CPU overhead. IT admins run virtual machines live migrations without an idea about the migration cost. So, resources bottlenecks, higher migration cost and migration failures might happen. The first problem that we discuss in this thesis is how to model the cost of the virtual machines live migration. Secondly, we investigate how to make use of machine learning techniques to help the cloud admins getting an estimation of this cost before initiating the migration for one of multiple virtual machines. Also, we discuss the optimal timing for a specific virtual machine before live migration to another server. Finally, we propose practical solutions that can be used by the cloud admins to be integrated with the cloud administration portals to answer the raised research questions above. Our research methodology to achieve the project objectives is to propose empirical models based on using VMware test-beds with different benchmarks tools. Then we make use of the machine learning techniques to propose a prediction approach for virtual machines live migration cost. Timing optimization for live migration is also proposed in this thesis based on using the cost prediction and data-centers network utilization prediction. Live migration with persistent memory clusters is also discussed at the end of the thesis. The cost prediction and timing optimization techniques proposed in this thesis could be practically integrated with VMware vSphere cluster portal such that the IT admins can now use the cost prediction feature and timing optimization option before proceeding with a virtual machine live migration. Testing results show that our proposed approach for VMs live migration cost prediction shows acceptable results with less than 20\% prediction error and can be easily implemented and integrated with VMware vSphere as an example of a commonly used resource management portal for virtual data-centers and private cloud environments. The results show that using our proposed VMs migration timing optimization technique also could save up to 51\% of migration time of the VMs migration time for memory intensive workloads and up to 27\% of the migration time for network intensive workloads. This timing optimization technique can be useful for network admins to save migration time with utilizing higher network rate and higher probability of success. At the end of this thesis, we discuss the persistent memory technology as a new trend in servers memory technology. Persistent memory modes of operation and configurations are discussed in detail to explain how live migration works between servers with different memory configuration set up. Then, we build a VMware cluster with persistent memory inside server and also with DRAM only servers to show the live migration cost difference between the VMs with DRAM only versus the VMs with persistent memory inside.},
  language  = {en}
}
@phdthesis{Lazaridou2021,
  author    = {Lazaridou, Konstantina},
  title     = {Revealing hidden patterns in political news and social media with machine learning},
  doi       = {10.25932/publishup-50273},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-502734},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xv, 140},
  year      = {2021},
  abstract  = {As part of our everyday life we consume breaking news and interpret it based on our own viewpoints and beliefs. We have easy access to online social networking platforms and news media websites, where we inform ourselves about current affairs and often post about our own views, such as in news comments or social media posts. The media ecosystem enables opinions and facts to travel from news sources to news readers, from news article commenters to other readers, from social network users to their followers, etc. The views of the world many of us have depend on the information we receive via online news and social media. Hence, it is essential to maintain accurate, reliable and objective online content to ensure democracy and verity on the Web. To this end, we contribute to a trustworthy media ecosystem by analyzing news and social media in the context of politics to ensure that media serves the public interest. In this thesis, we use text mining, natural language processing and machine learning techniques to reveal underlying patterns in political news articles and political discourse in social networks. Mainstream news sources typically cover a great amount of the same news stories every day, but they often place them in a different context or report them from different perspectives. In this thesis, we are interested in how distinct and predictable newspaper journalists are, in the way they report the news, as a means to understand and identify their different political beliefs. To this end, we propose two models that classify text from news articles to their respective original news source, i.e., reported speech and also news comments. Our goal is to capture systematic quoting and commenting patterns by journalists and news commenters respectively, which can lead us to the newspaper where the quotes and comments are originally published. Predicting news sources can help us understand the potential subjective nature behind news storytelling and the magnitude of this phenomenon. Revealing this hidden knowledge can restore our trust in media by advancing transparency and diversity in the news. Media bias can be expressed in various subtle ways in the text and it is often challenging to identify these bias manifestations correctly, even for humans. However, media experts, e.g., journalists, are a powerful resource that can help us overcome the vague definition of political media bias and they can also assist automatic learners to find the hidden bias in the text. Due to the enormous technological advances in artificial intelligence, we hypothesize that identifying political bias in the news could be achieved through the combination of sophisticated deep learning modelsxi and domain expertise. Therefore, our second contribution is a high-quality and reliable news dataset annotated by journalists for political bias and a state-of-the-art solution for this task based on curriculum learning. Our aim is to discover whether domain expertise is necessary for this task and to provide an automatic solution for this traditionally manually-solved problem. User generated content is fundamentally different from news articles, e.g., messages are shorter, they are often personal and opinionated, they refer to specific topics and persons, etc. Regarding political and socio-economic news, individuals in online communities make use of social networks to keep their peers up-to-date and to share their own views on ongoing affairs. We believe that social media is also an as powerful instrument for information flow as the news sources are, and we use its unique characteristic of rapid news coverage for two applications. We analyze Twitter messages and debate transcripts during live political presidential debates to automatically predict the topics that Twitter users discuss. Our goal is to discover the favoured topics in online communities on the dates of political events as a way to understand the political subjects of public interest. With the up-to-dateness of microblogs, an additional opportunity emerges, namely to use social media posts and leverage the real-time verity about discussed individuals to find their locations. That is, given a person of interest that is mentioned in online discussions, we use the wisdom of the crowd to automatically track her physical locations over time. We evaluate our approach in the context of politics, i.e., we predict the locations of US politicians as a proof of concept for important use cases, such as to track people that are national risks, e.g., warlords and wanted criminals.},
  language  = {en}
}
@phdthesis{Loster2021,
  author    = {Loster, Michael},
  title     = {Knowledge base construction with machine learning methods},
  doi       = {10.25932/publishup-50145},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-501459},
  school      = {Universit{\"a}t Potsdam},
  pages     = {ii, 130},
  year      = {2021},
  abstract  = {Modern knowledge bases contain and organize knowledge from many different topic areas. Apart from specific entity information, they also store information about their relationships amongst each other. Combining this information results in a knowledge graph that can be particularly helpful in cases where relationships are of central importance. Among other applications, modern risk assessment in the financial sector can benefit from the inherent network structure of such knowledge graphs by assessing the consequences and risks of certain events, such as corporate insolvencies or fraudulent behavior, based on the underlying network structure. As public knowledge bases often do not contain the necessary information for the analysis of such scenarios, the need arises to create and maintain dedicated domain-specific knowledge bases. This thesis investigates the process of creating domain-specific knowledge bases from structured and unstructured data sources. In particular, it addresses the topics of named entity recognition (NER), duplicate detection, and knowledge validation, which represent essential steps in the construction of knowledge bases. As such, we present a novel method for duplicate detection based on a Siamese neural network that is able to learn a dataset-specific similarity measure which is used to identify duplicates. Using the specialized network architecture, we design and implement a knowledge transfer between two deduplication networks, which leads to significant performance improvements and a reduction of required training data. Furthermore, we propose a named entity recognition approach that is able to identify company names by integrating external knowledge in the form of dictionaries into the training process of a conditional random field classifier. In this context, we study the effects of different dictionaries on the performance of the NER classifier. We show that both the inclusion of domain knowledge as well as the generation and use of alias names results in significant performance improvements. For the validation of knowledge represented in a knowledge base, we introduce Colt, a framework for knowledge validation based on the interactive quality assessment of logical rules. In its most expressive implementation, we combine Gaussian processes with neural networks to create Colt-GP, an interactive algorithm for learning rule models. Unlike other approaches, Colt-GP uses knowledge graph embeddings and user feedback to cope with data quality issues of knowledge bases. The learned rule model can be used to conditionally apply a rule and assess its quality. Finally, we present CurEx, a prototypical system for building domain-specific knowledge bases from structured and unstructured data sources. Its modular design is based on scalable technologies, which, in addition to processing large datasets, ensures that the modules can be easily exchanged or extended. CurEx offers multiple user interfaces, each tailored to the individual needs of a specific user group and is fully compatible with the Colt framework, which can be used as part of the system. We conduct a wide range of experiments with different datasets to determine the strengths and weaknesses of the proposed methods. To ensure the validity of our results, we compare the proposed methods with competing approaches.},
  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}
}
@inproceedings{OPUS4-40678,
  title     = {HPI Future SOC Lab},
  editor    = {Meinel, Christoph and Polze, Andreas and Oswald, Gerhard and Strotmann, Rolf and Seibold, Ulrich and Schulzki, Bernhard},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-406787},
  pages     = {iii, 180},
  year      = {2016},
  abstract  = {The "HPI Future SOC Lab" is a cooperation of the Hasso Plattner Institute (HPI) and industrial partners. Its mission is to enable and promote exchange and interaction between the research community and the industrial 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 2016. Selected projects have presented their results on April 5th and November 3th 2016 at the Future SOC Lab Day events.},
  language  = {en}
}
@inproceedings{KurbelNowakAzodietal.2015,
  author    = {Kurbel, Karl and Nowak, Dawid and Azodi, Amir and Jaeger, David and Meinel, Christoph and Cheng, Feng and Sapegin, Andrey and Gawron, Marian and Morelli, Frank and Stahl, Lukas and Kerl, Stefan and Janz, Mariska and Hadaya, Abdulmasih and Ivanov, Ivaylo and Wiese, Lena and Neves, Mariana and Schapranow, Matthieu-Patrick and F{\"a}hnrich, Cindy and Feinbube, Frank and Eberhardt, Felix and Hagen, Wieland and Plauth, Max and Herscheid, Lena and Polze, Andreas and Barkowsky, Matthias and Dinger, Henriette and Faber, Lukas and Montenegro, Felix and Czach{\´o}rski, Tadeusz and Nycz, Monika and Nycz, Tomasz and Baader, Galina and Besner, Veronika and Hecht, Sonja and Schermann, Michael and Krcmar, Helmut and Wiradarma, Timur Pratama and Hentschel, Christian and Sack, Harald and Abramowicz, Witold and Sokolowska, Wioletta and Hossa, Tymoteusz and Opalka, Jakub and Fabisz, Karol and Kubaczyk, Mateusz and Cmil, Milena and Meng, Tianhui and Dadashnia, Sharam and Niesen, Tim and Fettke, Peter and Loos, Peter and Perscheid, Cindy and Schwarz, Christian and Schmidt, Christopher and Scholz, Matthias and Bock, Nikolai and Piller, Gunther and B{\"o}hm, Klaus and Norkus, Oliver and Clark, Brian and Friedrich, Bj{\"o}rn and Izadpanah, Babak and Merkel, Florian and Schweer, Ilias and Zimak, Alexander and Sauer, J{\"u}rgen and Fabian, Benjamin and Tilch, Georg and M{\"u}ller, David and Pl{\"o}ger, Sabrina and Friedrich, Christoph M. and Engels, Christoph and Amirkhanyan, Aragats and van der Walt, Est{\´e}e and Eloff, J. H. P. and Scheuermann, Bernd and Weinknecht, Elisa},
  title     = {HPI Future SOC Lab},
  editor    = {Meinel, Christoph and Polze, Andreas and Oswald, Gerhard and Strotmann, Rolf and Seibold, Ulrich and Schulzki, Bernhard},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-102516},
  pages     = {iii, 154},
  year      = {2015},
  abstract  = {Das Future SOC Lab am HPI ist eine Kooperation des Hasso-Plattner-Instituts mit verschiedenen Industriepartnern. Seine Aufgabe ist die Erm{\"o}glichung und F{\"o}rderung des Austausches zwischen Forschungsgemeinschaft und Industrie. Am Lab wird interessierten Wissenschaftlern eine Infrastruktur von neuester Hard- und Software kostenfrei f{\"u}r Forschungszwecke zur Verf{\"u}gung gestellt. Dazu z{\"a}hlen teilweise noch nicht am Markt verf{\"u}gbare Technologien, die im normalen Hochschulbereich in der Regel nicht zu finanzieren w{\"a}ren, bspw. Server mit bis zu 64 Cores und 2 TB Hauptspeicher. Diese Angebote richten sich insbesondere an Wissenschaftler in den Gebieten Informatik und Wirtschaftsinformatik. Einige der Schwerpunkte sind Cloud Computing, Parallelisierung und In-Memory Technologien. In diesem Technischen Bericht werden die Ergebnisse der Forschungsprojekte des Jahres 2015 vorgestellt. Ausgew{\"a}hlte Projekte stellten ihre Ergebnisse am 15. April 2015 und 4. November 2015 im Rahmen der Future SOC Lab Tag Veranstaltungen vor.},
  language  = {en}
}
@phdthesis{Haider2013,
  author    = {Haider, Peter},
  title     = {Prediction with Mixture Models},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-69617},
  school      = {Universit{\"a}t Potsdam},
  year      = {2013},
  abstract  = {Learning a model for the relationship between the attributes and the annotated labels of data examples serves two purposes. Firstly, it enables the prediction of the label for examples without annotation. Secondly, the parameters of the model can provide useful insights into the structure of the data. If the data has an inherent partitioned structure, it is natural to mirror this structure in the model. Such mixture models predict by combining the individual predictions generated by the mixture components which correspond to the partitions in the data. Often the partitioned structure is latent, and has to be inferred when learning the mixture model. Directly evaluating the accuracy of the inferred partition structure is, in many cases, impossible because the ground truth cannot be obtained for comparison. However it can be assessed indirectly by measuring the prediction accuracy of the mixture model that arises from it. This thesis addresses the interplay between the improvement of predictive accuracy by uncovering latent cluster structure in data, and further addresses the validation of the estimated structure by measuring the accuracy of the resulting predictive model. In the application of filtering unsolicited emails, the emails in the training set are latently clustered into advertisement campaigns. Uncovering this latent structure allows filtering of future emails with very low false positive rates. In order to model the cluster structure, a Bayesian clustering model for dependent binary features is developed in this thesis. Knowing the clustering of emails into campaigns can also aid in uncovering which emails have been sent on behalf of the same network of captured hosts, so-called botnets. This association of emails to networks is another layer of latent clustering. Uncovering this latent structure allows service providers to further increase the accuracy of email filtering and to effectively defend against distributed denial-of-service attacks. To this end, a discriminative clustering model is derived in this thesis that is based on the graph of observed emails. The partitionings inferred using this model are evaluated through their capacity to predict the campaigns of new emails. Furthermore, when classifying the content of emails, statistical information about the sending server can be valuable. Learning a model that is able to make use of it requires training data that includes server statistics. In order to also use training data where the server statistics are missing, a model that is a mixture over potentially all substitutions thereof is developed. Another application is to predict the navigation behavior of the users of a website. Here, there is no a priori partitioning of the users into clusters, but to understand different usage scenarios and design different layouts for them, imposing a partitioning is necessary. The presented approach simultaneously optimizes the discriminative as well as the predictive power of the clusters. Each model is evaluated on real-world data and compared to baseline methods. The results show that explicitly modeling the assumptions about the latent cluster structure leads to improved predictions compared to the baselines. It is beneficial to incorporate a small number of hyperparameters that can be tuned to yield the best predictions in cases where the prediction accuracy can not be optimized directly.},
  language  = {en}
}