@phdthesis{Rezaei2019,
  author    = {Rezaei, Mina},
  title     = {Deep representation learning from imbalanced medical imaging},
  doi       = {10.25932/publishup-44275},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-442759},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xxviii, 160},
  year      = {2019},
  abstract  = {Medical imaging plays an important role in disease diagnosis, treatment planning, and clinical monitoring. One of the major challenges in medical image analysis is imbalanced training data, in which the class of interest is much rarer than the other classes. Canonical machine learning algorithms suppose that the number of samples from different classes in the training dataset is roughly similar or balance. Training a machine learning model on an imbalanced dataset can introduce unique challenges to the learning problem. A model learned from imbalanced training data is biased towards the high-frequency samples. The predicted results of such networks have low sensitivity and high precision. In medical applications, the cost of misclassification of the minority class could be more than the cost of misclassification of the majority class. For example, the risk of not detecting a tumor could be much higher than referring to a healthy subject to a doctor. The current Ph.D. thesis introduces several deep learning-based approaches for handling class imbalanced problems for learning multi-task such as disease classification and semantic segmentation. At the data-level, the objective is to balance the data distribution through re-sampling the data space: we propose novel approaches to correct internal bias towards fewer frequency samples. These approaches include patient-wise batch sampling, complimentary labels, supervised and unsupervised minority oversampling using generative adversarial networks for all. On the other hand, at algorithm-level, we modify the learning algorithm to alleviate the bias towards majority classes. In this regard, we propose different generative adversarial networks for cost-sensitive learning, ensemble learning, and mutual learning to deal with highly imbalanced imaging data. We show evidence that the proposed approaches are applicable to different types of medical images of varied sizes on different applications of routine clinical tasks, such as disease classification and semantic segmentation. Our various implemented algorithms have shown outstanding results on different medical imaging challenges.},
  language  = {en}
}
@phdthesis{Kriegerowski2019,
  author    = {Kriegerowski, Marius},
  title     = {Development of waveform-based, automatic analysis tools for the spatio-temporal characterization of massive earthquake clusters and swarms},
  doi       = {10.25932/publishup-44404},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-444040},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xv, 83},
  year      = {2019},
  abstract  = {Earthquake swarms are characterized by large numbers of events occurring in a short period of time within a confined source volume and without significant mainshock aftershock pattern as opposed to tectonic sequences. Intraplate swarms in the absence of active volcanism usually occur in continental rifts as for example in the Eger Rift zone in North West Bohemia, Czech Republic. A common hypothesis links event triggering to pressurized fluids. However, the exact causal chain is often poorly understood since the underlying geotectonic processes are slow compared to tectonic sequences. The high event rate during active periods challenges standard seismological routines as these are often designed for single events and therefore costly in terms of human resources when working with phase picks or computationally costly when exploiting full waveforms. This methodological thesis develops new approaches to analyze earthquake swarm seismicity as well as the underlying seismogenic volume. It focuses on the region of North West (NW) Bohemia, a well studied, well monitored earthquake swarm region. In this work I develop and test an innovative approach to detect and locate earthquakes using deep convolutional neural networks. This technology offers great potential as it allows to efficiently process large amounts of data which becomes increasingly important given that seismological data storage grows at increasing pace. The proposed deep neural network trained on NW Bohemian earthquake swarm records is able to locate 1000 events in less than 1 second using full waveforms while approaching precision of double difference relocated catalogs. A further technological novelty is that the trained filters of the deep neural network's first layer can be repurposed to function as a pattern matching event detector without additional training on noise datasets. For further methodological development and benchmarking, I present a new toolbox to generate realistic earthquake cluster catalogs as well as synthetic full waveforms of those clusters in an automated fashion. The input is parameterized using constraints on source volume geometry, nucleation and frequency-magnitude relations. It harnesses recorded noise to produce highly realistic synthetic data for benchmarking and development. This tool is used to study and assess detection performance in terms of magnitude of completeness Mc of a full waveform detector applied to synthetic data of a hydrofracturing experiment at the Wysin site, Poland. Finally, I present and demonstrate a novel approach to overcome the masking effects of wave propagation between earthquake and stations and to determine source volume attenuation directly in the source volume where clustered earthquakes occur. The new event couple spectral ratio approach exploits high frequency spectral slopes of two events sharing the greater part of their rays. Synthetic tests based on the toolbox mentioned before show that this method is able to infer seismic wave attenuation within the source volume at high spatial resolution. Furthermore, it is independent from the distance towards a station as well as the complexity of the attenuation and velocity structure outside of the source volume of swarms. The application to recordings of the NW Bohemian earthquake swarm shows increased P phase attenuation within the source volume (Qp < 100) based on results at a station located close to the village Luby (LBC). The recordings of a station located in epicentral proximity, close to Nov{\´y} Kostel (NKC), show a relatively high complexity indicating that waves arriving at that station experience more scattering than signals recorded at other stations. The high level of complexity destabilizes the inversion. Therefore, the Q estimate at NKC is not reliable and an independent proof of the high attenuation finding given the geometrical and frequency constraints is still to be done. However, a high attenuation in the source volume of NW Bohemian swarms has been postulated before in relation to an expected, highly damaged zone bearing CO 2 at high pressure. The methods developed in the course of this thesis yield the potential to improve our understanding regarding the role of fluids and gases in intraplate event clustering.},
  language  = {en}
}
@phdthesis{TorcatoMordido2021,
  author    = {Torcato Mordido, Gon{\c{c}}alo Filipe},
  title     = {Diversification, compression, and evaluation methods for generative adversarial networks},
  doi       = {10.25932/publishup-53546},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-535460},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xiii, 148},
  year      = {2021},
  abstract  = {Generative adversarial networks (GANs) have been broadly applied to a wide range of application domains since their proposal. In this thesis, we propose several methods that aim to tackle different existing problems in GANs. Particularly, even though GANs are generally able to generate high-quality samples, the diversity of the generated set is often sub-optimal. Moreover, the common increase of the number of models in the original GANs framework, as well as their architectural sizes, introduces additional costs. Additionally, even though challenging, the proper evaluation of a generated set is an important direction to ultimately improve the generation process in GANs. We start by introducing two diversification methods that extend the original GANs framework to multiple adversaries to stimulate sample diversity in a generated set. Then, we introduce a new post-training compression method based on Monte Carlo methods and importance sampling to quantize and prune the weights and activations of pre-trained neural networks without any additional training. The previous method may be used to reduce the memory and computational costs introduced by increasing the number of models in the original GANs framework. Moreover, we use a similar procedure to quantize and prune gradients during training, which also reduces the communication costs between different workers in a distributed training setting. We introduce several topology-based evaluation methods to assess data generation in different settings, namely image generation and language generation. Our methods retrieve both single-valued and double-valued metrics, which, given a real set, may be used to broadly assess a generated set or separately evaluate sample quality and sample diversity, respectively. Moreover, two of our metrics use locality-sensitive hashing to accurately assess the generated sets of highly compressed GANs. The analysis of the compression effects in GANs paves the way for their efficient employment in real-world applications. Given their general applicability, the methods proposed in this thesis may be extended beyond the context of GANs. Hence, they may be generally applied to enhance existing neural networks and, in particular, generative frameworks.},
  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}
}
@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}
}