Recent advancements in the field of Computer Vision are a by-product of breakthroughs in the domain of Artificial Intelligence. Object detection in monocular images is now realized by an amalgamation of Computer Vision and Deep Learning. While most approaches detect objects as a mere two dimensional (2D) bounding box, there are a few that exploit rather traditional representation of the 3D object. Such approaches detect an object either as a 3D bounding box or exploit its shape primitives using active shape models which results in a wireframe-like detection. Such a wireframe detection is represented as combinations of detected keypoints (or landmarks) of the desired object. Apart from a faithful retrieval of the object’s true shape, wireframe based approaches are relatively robust in handling occlusions. The central task of this thesis was to find such an approach and to implement it with the goal of its performance evaluation. The object of interest is the vehicle class (cars, mini vans, trucks etc.) and the evaluation data is monocular traffic surveillance videos collected by the supervising chair. A wireframe type detection can aid several facets of traffic analysis by improved (compared to 2D bounding box) estimation of the detected object’s ground plane. The thesis encompasses the process of implementation of the chosen approach called Occlusion-Net [40], including its design details and a qualitative evaluation on traffic surveillance videos. The implementation reproduces most of the published results across several occlusion categories except the truncated car category. Occlusion-Net’s erratic detections are mostly caused by incorrect detection of the initial region of interest. It employs three instances of Graph Neural Networks for occlusion reasoning and localization. The thesis also provides a didactic introduction to the field of Machine and Deep Learning including intuitions of mathematical concepts required to understand the two disciplines and the implemented approach.:Contents 1 Introduction 1 2 Technical Background 7 2.1 AI, Machine Learning and Deep Learning 7 2.1.1 But what is AI ? 7 2.1.2 Representational composition by Deep Learning 10 2.2 Essential Mathematics for ML 14 2.2.1 Linear Algebra 15 2.2.2 Probability and Statistics 25 2.2.3 Calculus 34 2.3 Mathematical Introduction to ML 39 2.3.1 Ingredients of a Machine Learning Problem 39 2.3.2 The Perceptron 40 2.3.3 Feature Transformation 46 2.3.4 Logistic Regression 48 2.3.5 Artificial Neural Networks: ANN 53 2.3.6 Convolutional Neural Network: CNN 61 2.3.7 Graph Neural Networks 68 2.4 Specific Topics in Computer Vision 72 2.5 Previous work 76 3 Design of Implemented Approach 81 3.1 Training Dataset 81 3.2 Keypoint Detection : MaskRCNN 83 3.3 Occluded Edge Prediction : 2D-KGNN Encoder 84 3.4 Occluded Keypoint Localization : 2D-KGNN Decoder 86 3.5 3D Shape Estimation: 3D-KGNN Encoder 88 4 Implementation 93 4.1 Open-Source Tools and Libraries 93 4.1.1 Code Packaging: NVIDIA-Docker 94 4.1.2 Data Processing Libraries 94 4.1.3 Libraries for Neural Networks 95 4.1.4 Computer Vision Library 95 4.2 Dataset Acquisition and Training 96 4.2.1 Acquiring Dataset 96 4.2.2 Training Occlusion-Net 96 4.3 Refactoring 97 4.3.1 Error in Docker File 97 4.3.2 Image Directories as Input 97 4.3.3 Frame Extraction in Parallel 98 4.3.4 Video as Input 100 4.4 Functional changes 100 4.4.1 Keypoints In Output 100 4.4.2 Mismatched BB and Keypoints 101 4.4.3 Incorrect Class Labels 101 4.4.4 Bounding Box Overlay 101 5 Evaluation 103 5.1 Qualitative Evaluation 103 5.1.1 Evaluation Across Occlusion Categories 103 5.1.2 Performance on Moderate and Heavy Vehicles 105 5.2 Verification of Failure Analysis 106 5.2.1 Truncated Cars 107 5.2.2 Overlapping Cars 108 5.3 Analysis of Missing Frames 109 5.4 Test Performance 110 6 Conclusion 113 7 Future Work 117 Bibliography 119

Progressive download video services, such as YouTube and podcasts, are responsible for a major part of the transmitted data volume in the Internet and it is expected, that they will also strongly affect mobile networks. Streaming video quality mainly depends on the sustainable throughput achieved during transmission. To ensure acceptable video quality in mobile networks (with limited capacity resources) the perceived quality by the customer (QoE) needs to be monitored by estimation. For that, the streaming video quality needs to be measured and monitored permanently. For TCP based progressive download we propose to extract the the video timestamps which are encoded within the payload of the TCP segments by decoding the video within the payload. The actual estimation is then done by play out buffer fill level calculations based on the TCP segment timestamp and their internal play out timestamp. The perceived quality for the user is derived from the number and duration of video stalls. Algorithms for decoding Flash Video, MP4 and WebM Video have already been implemented. After deriving the play out time it is compared to the timestamp of the respective TCP segment. The result of this comparison is an estimate of the fill level of the play out buffer in terms of play out time within the client. This estimation is done without access to the end device. The same measurement procedure can be applied for any TCP based progressive download Internet service. Video was simply taken as an example because of its current large share in traffic volume in operator networks.

The complexity of computer networks has been rising over the last decades. Increasing interconnectivity between multiple devices, growing complexity of performed tasks and a strong collaboration between nodes are drivers for this phenomenon. An example is represented by Internet-of-Things devices, whose relevance has been rising in recent years. The increasing number of devices requiring updates and supervision makes maintenance more difficult. Human interaction, in this case, is costly and requires a lot of time. To overcome this, self-adaptive software systems (SAS) can be used. SAS are a subset of autonomous systems which can monitor themselves and their environment to adapt to changes without human interaction. In the literature, different approaches for engineering SAS were proposed, including techniques for executing adaptations on multiple devices based on generated plans for reacting to changes. Among those solutions, also decentralised approaches can be found. To the best of our knowledge, no approach for engineering a SAS exists which tolerates errors during the execution of adaptation in a decentralised setting. While some approaches for role-based execution reset the application in case of a single failure during the adaptation process, others do not make assumptions about errors or do not consider an erroneous environment. In a real-world environment, errors will likely occur during run-time, and the adaptation process could be disturbed. This work aims to perform adaptations in a decentralised way on role-based systems with a relaxed consistency constraint, i.e., errors during the adaptation phase are tolerated. This increases the availability of nodes since no rollbacks are required in case of a failure. Moreover, a subset of applications, such as drone swarms, would benefit from an approach with a relaxed consistency model since parts of the system that adapted successfully can already operate in an adapted configuration instead of waiting for other peers to apply the changes in a later iteration. Moreover, if we eliminate the need for an atomic adaptation execution, asynchronous execution of adaptation would be possible. In that case, we can supervise the adaptation process for a long time and ensure that every peer takes the planned actions as soon as the internal task execution allows it. To allow for a relaxed consistent way of adaptation execution, we develop a decentralised adaptation execution protocol, which supports the notion of eventual consistency. As soon as devices reconnect after network congestion or restore their internal state after local failures, our protocol can coordinate the recovery process among multiple devices to attempt recovery of a globally consistent state after errors occur. By superseding the need for a central instance, every peer who received information about failing peers can start the recovery process. The developed approach can restore a consistent global configuration if almost all peers fail. Moreover, the approach supports asynchronous adaptations, i.e., the peers can execute planned adaptations as soon as they are ready, which increases overall availability in case of delayed adaptation of single nodes. The developed protocol is evaluated with the help of a proof-of-concept implementation. The approach was run in five different experiments with thousands of iterations to show the applicability and reliability of this novel approach. The time for execution of the protocol and the number of exchanged messages has been measured to compare the protocol for different error cases and system sizes, as well as to show the scalability of the approach. The developed solution has been compared to a blocking approach to show the feasibility compared to an atomic approach. The applicability in a real-world scenario has been described in an empirical study using an example of a fire-extinguishing drone swarm. The results show that an optimistic approach to adaptation is suitable and specific scenarios can benefit from the improved availability since no rollbacks are required. Systems can continue their work regardless of the failures of participating nodes in large-scale systems.:Abstract VI 1. Introduction 1 1.1. Motivational Use-Case 2 1.2. Problem Definition 3 1.3. Objectives 4 1.4. Research Questions 5 1.5. Contributions 5 1.6. Outline 6 2. Foundation 7 2.1. Role Concept 7 2.2. Self-Adaptive Software Systems 13 2.3. Terminology for Role-Based Self-Adaptation 15 2.4. Consistency Preservation and Consistency Models 17 2.5. Summary 20 3. Related Work 21 3.1. Role-Based Approaches 22 3.2. Actor Model of Computation and Akka 23 3.3. Adaptation Execution in Self-Adaptive Software Systems 24 3.4. Change Consistency in Distributed Systems 33 3.5. Comparison of the Evaluated Approaches 40 4. The Decentralised Consistency Compensation Protocol 43 4.1. System and Error Model 43 4.2. Requirements to the Concept 44 4.3. The Usage of Roles in Adaptations 45 4.4. Protocol Overview 47 4.5. Protocol Description 51 4.6. Protocol Corner- and Error Cases 64 4.7. Summary 66 5. Prototypical Implementation 67 5.1. Technology Overview 67 5.2. Reused Artifacts 68 5.3. Implementation Details 70 5.4. Setup of the Prototypical Implementation 76 5.5. Summary 77 6. Evaluation 79 6.1. Evaluation Methodology 79 6.2. Evaluation Setup 80 6.3. Experiment Overview 81 6.4. Default Case: Successful Adaptation 84 6.5. Compensation on Disconnection of Peers 85 6.6. Recovery from Failed Adaptation 88 6.7. Impact of Early Activation of Adaptations 91 6.8. Comparison with a Blocking Approach 92 6.9. Empirical Study: Fire Extinguishing Drones 95 6.10. Summary 97 7. Conclusion and Future Work 99 7.1. Recap of the Research Questions 99 7.2. Discussion 101 7.3. Future Work 101 A. Protocol Buffer Definition 103 Acronyms 108 Bibliography 109

Ein üblicher Ansatzpunkt zur Verbesserung der Energieeffizienz im High Performance Computing (HPC) ist, neben Verbesserungen an der Hardware oder einer effizienteren Nachnutzung der Wärme des Systems, die Optimierung der ausgeführten Programme. Dazu können zum Beispiel energieoptimale Einstellungen, wie die Frequenzen des Prozessors, für verschiedene Programmfunktionen bestimmt werden, um diese dann im späteren Verlauf des Programmes anwenden zu können. Mit jeder Änderung des Programmes kann sich dessen optimale Einstellung ändern, weshalb diese zeitaufwendig neu bestimmt werden muss. Das stellt eine wesentliche Hürde für die Anwendung solcher Verfahren dar. Dieser Prozess des Bestimmens der optimalen Frequenzen kann mithilfe von Machine-Learning-Methoden vereinfacht werden, wie in dieser Arbeit gezeigt wird. So lässt sich mithilfe von sogenannten Performance-Events ein neuronales Netz erstellen, mit dem während der Ausführung des Programmes die optimalen Frequenzen automatisch geschätzt werden können. Performance-Events sind prozessorintern und können Einblick in die Abläufe im Prozessor gewähren. Bei dem Einsatz von Performance-Events gilt es einige Fallstricke zu vermeiden. So werden die Performance-Events von Performance-Countern gezählt. Die Anzahl der Counter ist allerdings begrenzt, womit auch die Anzahl der Events, die gleichzeitig gezählt werden können, limitiert ist. Eine für diese Arbeit wesentliche Fragestellung ist also: Welche dieser Events sind relevant und müssen gezählt werden? Bei der Beantwortung dieser Frage sind Merkmalsauswahlverfahren hilfreich, besonders sogenannte Filtermethoden, bei denen die Merkmale vor dem Training ausgewählt werden. Viele bekannte Methoden gehen dabei entweder davon aus, dass die Zusammenhänge zwischen den Merkmalen linear sind, wie z. B. bei Verfahren, die den Pearson-Korrelationskoeffizienten verwenden, oder die Daten müssen in Klassen eingeteilt werden, wie etwa bei Verfahren, die auf der Transinformation beruhen. Beides ist für Performance-Events nicht ideal. Auf der einen Seite können keine linearen Zusammenhänge angenommen werden. Auf der anderen Seite bedeutet das Einteilen in Klassen einen Verlust an Information. Um diese Probleme zu adressieren, werden in dieser Arbeit bestehende Merkmalsauswahlverfahren mit den dazugehörigen Algorithmen analysiert, neue Verfahren entworfen und miteinander verglichen. Es zeigt sich, dass mit neuen Verfahren, die auf sogenannten Copulas basieren, auch nichtlineare Zusammenhänge erkannt werden können, ohne dass die Daten in Klassen eingeteilt werden müssen. So lassen sich schließlich einige Events identifiziert, die zusammen mit neuronalen Netzen genutzt werden können, um die Energieeffizienz von HPC-Anwendung zu steigern. Das in dieser Arbeit erstellte Framework erfüllt dabei neben der Auswahl der Performance-Events weitere Aufgaben: Es stellt sicher, dass diverse Programmteile mit verschiedenen optimalen Einstellungen voneinander unterschieden werden können. Darüber hinaus sorgt das Framework dafür, dass genügend Daten erzeugt werden, um ein neuronales Netz zu trainieren, und dass dieses Netz später einfach genutzt werden kann. Dabei ist das Framework so flexibel, dass auch andere Machine-Learning-Methoden getestet werden können. Die Leistungsfähigkeit des Frameworks wird abschließend in einer Ende-zu-Ende-Evaluierung an einem beispielhaften Programm demonstriert. Die Evaluierung il­lus­t­riert, dass bei nur 7% längerer Laufzeit eine Energieeinsparung von 24% erzielt werden kann und zeigt damit, dass mit Machine-Learning-Methoden wesentliche Energieeinsparungen erreicht werden können.:1 Einleitung und Motiovation 2 Energieeffizienz und Machine-Learning – eine thematische Einführung 2.1 Energieeffizienz von Programmen im Hochleistungsrechnen 2.1.1 Techniken zur Energiemessung oder -abschätzung 2.1.2 Techniken zur Beeinflussung der Energieeffizienz in der Hardware 2.1.3 Grundlagen zur Performanceanalyse 2.1.4 Regionsbasierte Ansätze zur Erhöhung der Energieeffizienz 2.1.5 Andere Ansätze zur Erhöhung der Energieeffizienz 2.2 Methoden zur Merkmalsauswahl 2.2.1 Merkmalsauswahlmethoden basierend auf der Informationstheorie 2.2.2 Merkmalsauswahl für stetige Merkmale 2.2.3 Andere Verfahren zur Merkmalsauswahl 2.3 Machine-Learning mit neuronalen Netzen 2.3.1 Neuronale Netze 2.3.2 Backpropagation 2.3.3 Aktivierungsfunktionen 3 Merkmalsauswahl für mehrdimensionale nichtlineare Abhängigkeiten 3.1 Analyse der Problemstellung, Merkmale und Zielgröße 3.2 Merkmalsauswahl mit mehrdimensionaler Transinformation für stetige Merkmale 3.2.1 Mehrdimensionale Copula-Entropie und mehrdimensionale Transinformation 3.2.2 Schätzung der mehrdimensionalen Transinformation basierend auf Copula-Dichte 3.3 Normierung 3.4 Vergleich von Copula-basierten Maßzahlen mit der klassischen Transinformation und dem Pearson-Korrelationskoeffizienten 3.4.1 Deterministische Abhängigkeit zweier Variablen 3.4.2 UnabhängigkeitVergleich verschiedener Methoden zur Auswahl stetiger Merkmale 3.5 Vergleich verschiedener Methoden zur Auswahl stetiger Merkmale 3.5.1 Erzeugung synthetischer Daten 3.5.2 Szenario 1 – fünf relevante Merkmale 3.5.3 Szenario 2 – fünf relevante Merkmale, fünf wiederholte Merkmale 3.5.4 Schlussfolgerungen aus den Simulationen 3.6 Zusammenfassung 4 Entwicklung und Umsetzung des Frameworks 4.1 Erweiterungen der READEX Runtime Library 4.1.1 Grundlegender Aufbau der READEX Runtime Library 4.1.2 Call-Path oder Call-Tree 4.1.3 Calibration-Module 4.2 Testsystem 4.2.1 Architektur 4.2.2 Bestimmung des Offsets zur Energiemessung mit RAPL 4.3 Verwendete Benchmarks zur Erzeugung der Datengrundlage 4.3.1 Datensatz 1: Der Stream-Benchmark 4.3.2 Datensatz 2: Eine Sammlung verschiedener Benchmarks 4.4 Merkmalsauswahl und Modellgenerierung 4.4.1 Datenaufbereitung 4.4.2 Merkmalsauswahl Algorithmus 4.4.3 Performance-Events anderer Arbeiten zum Vergleich 4.4.4 Erzeugen und Validieren eines Modells mithilfe von TensorFlow und Keras 4.5 Zusammenfassung 5 Evaluierung des Ansatzes 5.1 Der Stream-Benchmark 5.1.1 Analyse der gewählten Merkmale 5.1.2 Ergebnisse des Trainings 5.2 Verschiedene Benchmarks 5.2.1 Ausgewählte Merkmale 5.2.2 Ergebnisse des Trainings 5.3 Energieoptimierung einer Anwendung 6 Zusammenfassung und Ausblick Literatur Abbildungsverzeichnis Tabellenverzeichnis Quelltextverzeichnis / There are a variety of different approaches to improve energy efficiency in High Performance Computing (HPC). Besides advances to the hardware or cooling systems, optimising the executed programmes' energy efficiency is another a promising approach. Determining energy-optimal settings of program functions, such as the processor frequency, can be applied during the program's execution to reduce energy consumption. However, when the program is modified, the optimal setting might change. Therefore, the energy-optimal settings need to be determined again, which is a time-consuming process and a significant impediment for applying such methods. Fortunately, finding the optimal frequencies can be simplified using machine learning methods, as shown in this thesis. With the help of so-called performance events, a neural network can be trained, which can automatically estimate the optimal processor frequencies during program execution. Performance events are processor-specific and can provide insight into the procedures of a processor. However, there are some pitfalls to be avoided when using performance events. Performance events are counted by performance counters, but as the number of counters is limited, the number of events that can be counted simultaneously is also limited. This poses the question of which of these events are relevant and need to be counted. % Though the issue has received some attention in several publications, a convincing solution remains to be found. In answering this question, feature selection methods are helpful, especially so-called filter methods, where features are selected before the training. Unfortunately, many feature selection methods either assume a linear correlation between the features, such as methods using the Pearson correlation coefficient or require data split into classes, particularly methods based on mutual information. Neither can be applied to performance events as linear correlation cannot be assumed, and splitting the data into classes would result in a loss of information. In order to address that problem, this thesis analyses existing feature selection methods together with their corresponding algorithms, designs new methods, and compares different feature selection methods. By utilising new methods based on the mathematical concept of copulas, it was possible to detect non-linear correlations without splitting the data into classes. Thus, several performance events could be identified, which can be utilised together with neural networks to increase the energy efficiency of HPC applications. In addition to selecting performance events, the created framework ensures that different programme parts, which might have different optimal settings, can be identified. Moreover, it assures that sufficient data for the training of the neural networks is generated and that the network can easily be applied. Furthermore, the framework is flexible enough to evaluate other machine learning methods. Finally, an end-to-end evaluation with a sample application demonstrated the framework's performance. The evaluation illustrates that, while extending the runtime by only 7%, energy savings of 24% can be achieved, showing that substantial energy savings can be attained using machine learning approaches.:1 Einleitung und Motiovation 2 Energieeffizienz und Machine-Learning – eine thematische Einführung 2.1 Energieeffizienz von Programmen im Hochleistungsrechnen 2.1.1 Techniken zur Energiemessung oder -abschätzung 2.1.2 Techniken zur Beeinflussung der Energieeffizienz in der Hardware 2.1.3 Grundlagen zur Performanceanalyse 2.1.4 Regionsbasierte Ansätze zur Erhöhung der Energieeffizienz 2.1.5 Andere Ansätze zur Erhöhung der Energieeffizienz 2.2 Methoden zur Merkmalsauswahl 2.2.1 Merkmalsauswahlmethoden basierend auf der Informationstheorie 2.2.2 Merkmalsauswahl für stetige Merkmale 2.2.3 Andere Verfahren zur Merkmalsauswahl 2.3 Machine-Learning mit neuronalen Netzen 2.3.1 Neuronale Netze 2.3.2 Backpropagation 2.3.3 Aktivierungsfunktionen 3 Merkmalsauswahl für mehrdimensionale nichtlineare Abhängigkeiten 3.1 Analyse der Problemstellung, Merkmale und Zielgröße 3.2 Merkmalsauswahl mit mehrdimensionaler Transinformation für stetige Merkmale 3.2.1 Mehrdimensionale Copula-Entropie und mehrdimensionale Transinformation 3.2.2 Schätzung der mehrdimensionalen Transinformation basierend auf Copula-Dichte 3.3 Normierung 3.4 Vergleich von Copula-basierten Maßzahlen mit der klassischen Transinformation und dem Pearson-Korrelationskoeffizienten 3.4.1 Deterministische Abhängigkeit zweier Variablen 3.4.2 UnabhängigkeitVergleich verschiedener Methoden zur Auswahl stetiger Merkmale 3.5 Vergleich verschiedener Methoden zur Auswahl stetiger Merkmale 3.5.1 Erzeugung synthetischer Daten 3.5.2 Szenario 1 – fünf relevante Merkmale 3.5.3 Szenario 2 – fünf relevante Merkmale, fünf wiederholte Merkmale 3.5.4 Schlussfolgerungen aus den Simulationen 3.6 Zusammenfassung 4 Entwicklung und Umsetzung des Frameworks 4.1 Erweiterungen der READEX Runtime Library 4.1.1 Grundlegender Aufbau der READEX Runtime Library 4.1.2 Call-Path oder Call-Tree 4.1.3 Calibration-Module 4.2 Testsystem 4.2.1 Architektur 4.2.2 Bestimmung des Offsets zur Energiemessung mit RAPL 4.3 Verwendete Benchmarks zur Erzeugung der Datengrundlage 4.3.1 Datensatz 1: Der Stream-Benchmark 4.3.2 Datensatz 2: Eine Sammlung verschiedener Benchmarks 4.4 Merkmalsauswahl und Modellgenerierung 4.4.1 Datenaufbereitung 4.4.2 Merkmalsauswahl Algorithmus 4.4.3 Performance-Events anderer Arbeiten zum Vergleich 4.4.4 Erzeugen und Validieren eines Modells mithilfe von TensorFlow und Keras 4.5 Zusammenfassung 5 Evaluierung des Ansatzes 5.1 Der Stream-Benchmark 5.1.1 Analyse der gewählten Merkmale 5.1.2 Ergebnisse des Trainings 5.2 Verschiedene Benchmarks 5.2.1 Ausgewählte Merkmale 5.2.2 Ergebnisse des Trainings 5.3 Energieoptimierung einer Anwendung 6 Zusammenfassung und Ausblick Literatur Abbildungsverzeichnis Tabellenverzeichnis Quelltextverzeichnis

In this thesis I will use state-of-the-art (SOTA) image denoising methods to denoise electron microscopy (EM) data. Then, I will present NoiseVoid a deep learning based self-supervised image denoising approach which is trained on single noisy observations. Eventually, I approach the missing wedge problem in tomography and introduce a novel image encoding, based on the Fourier transform which I am using to predict missing Fourier coefficients directly in Fourier space with Fourier Image Transformer (FIT). In the next paragraphs I will summarize the individual contributions briefly. Electron microscopy is the go to method for high-resolution images in biological research. Modern scanning electron microscopy (SEM) setups are used to obtain neural connectivity maps, allowing us to identify individual synapses. However, slow scanning speeds are required to obtain SEM images of sufficient quality. In (Weigert et al. 2018) the authors show, for fluorescence microscopy, how pairs of low- and high-quality images can be obtained from biological samples and use them to train content-aware image restoration (CARE) networks. Once such a network is trained, it can be applied to noisy data to restore high quality images. With SEM-CARE I present how this approach can be directly applied to SEM data, allowing us to scan the samples faster, resulting in $40$- to $50$-fold imaging speedups for SEM imaging. In structural biology cryo transmission electron microscopy (cryo TEM) is used to resolve protein structures and describe molecular interactions. However, missing contrast agents as well as beam induced sample damage (Knapek and Dubochet 1980) prevent acquisition of high quality projection images. Hence, reconstructed tomograms suffer from low signal-to-noise ratio (SNR) and low contrast, which makes post-processing of such data difficult and often has to be done manually. To facilitate down stream analysis and manual data browsing of cryo tomograms I present cryoCARE a Noise2Noise (Lehtinen et al. 2018) based denoising method which is able to restore high contrast, low noise tomograms from sparse-view low-dose tilt-series. An implementation of cryoCARE is publicly available as Scipion (de la Rosa-Trevín et al. 2016) plugin. Next, I will discuss the problem of self-supervised image denoising. With cryoCARE I exploited the fact that modern cryo TEM cameras acquire multiple low-dose images, hence the Noise2Noise (Lehtinen et al. 2018) training paradigm can be applied. However, acquiring multiple noisy observations is not always possible e.g. in live imaging, with old cryo TEM cameras or simply by lack of access to the used imaging system. In such cases we have to fall back to self-supervised denoising methods and with Noise2Void I present the first self-supervised neural network based image denoising approach. Noise2Void is also available as an open-source Python package and as a one-click solution in Fiji (Schindelin et al. 2012). In the last part of this thesis I present Fourier Image Transformer (FIT) a novel approach to image reconstruction with Transformer networks. I develop a novel 1D image encoding based on the Fourier transform where each prefix encodes the whole image at reduced resolution, which I call Fourier Domain Encoding (FDE). I use FIT with FDEs and present proof of concept for super-resolution and tomographic reconstruction with missing wedge correction. The missing wedge artefacts in tomographic imaging originate in sparse-view imaging. Sparse-view imaging is used to keep the total exposure of the imaged sample to a minimum, by only acquiring a limited number of projection images. However, tomographic reconstructions from sparse-view acquisitions are affected by missing wedge artefacts, characterized by missing wedges in the Fourier space and visible as streaking artefacts in real image space. I show that FITs can be applied to tomographic reconstruction and that they fill in missing Fourier coefficients. Hence, FIT for tomographic reconstruction solves the missing wedge problem at its source.:Contents Summary iii Acknowledgements v 1 Introduction 1 1.1 Scanning Electron Microscopy . . . . . . . . . . . . . . . . . . . . 3 1.2 Cryo Transmission Electron Microscopy . . . . . . . . . . . . . . . 4 1.2.1 Single Particle Analysis . . . . . . . . . . . . . . . . . . . . 5 1.2.2 Cryo Tomography . . . . . . . . . . . . . . . . . . . . . . . 7 1.3 Tomographic Reconstruction . . . . . . . . . . . . . . . . . . . . . 8 1.4 Overview and Contributions . . . . . . . . . . . . . . . . . . . . . 11 2 Denoising in Electron Microscopy 15 2.1 Image Denoising . . . . . . . . . . . . . . . . . . . . . . . . . . . 17 2.2 Supervised Image Restoration . . . . . . . . . . . . . . . . . . . . 19 2.2.1 Training and Validation Loss . . . . . . . . . . . . . . . . 19 2.2.2 Neural Network Architectures . . . . . . . . . . . . . . . . 21 2.3 SEM-CARE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 23 2.3.1 SEM-CARE Experiments . . . . . . . . . . . . . . . . . . 23 2.3.2 SEM-CARE Results . . . . . . . . . . . . . . . . . . . . . 25 2.4 Noise2Noise . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 26 2.5 cryoCARE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 27 2.5.1 Restoration of cryo TEM Projections . . . . . . . . . . . . 27 2.5.2 Restoration of cryo TEM Tomograms . . . . . . . . . . . . 29 2.5.3 Automated Downstream Analysis . . . . . . . . . . . . . . 31 2.6 Implementations and Availability . . . . . . . . . . . . . . . . . . 32 2.7 Discussion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 33 2.7.1 Tasks Facilitated through cryoCARE . . . . . . . . . . . 33 3 Noise2Void: Self-Supervised Denoising 35 3.1 Probabilistic Image Formation . . . . . . . . . . . . . . . . . . . . 37 3.2 Receptive Field . . . . . . . . . . . . . . . . . . . . . . . . . . . . 38 3.3 Noise2Void Training . . . . . . . . . . . . . . . . . . . . . . . . . 39 3.3.1 Implementation Details . . . . . . . . . . . . . . . . . . . . 41 3.4 Experiments . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 42 3.4.1 Natural Images . . . . . . . . . . . . . . . . . . . . . . . . 43 3.4.2 Light Microscopy Data . . . . . . . . . . . . . . . . . . . . 44 3.4.3 Electron Microscopy Data . . . . . . . . . . . . . . . . . . 47 3.4.4 Errors and Limitations . . . . . . . . . . . . . . . . . . . . 48 3.5 Conclusion and Followup Work . . . . . . . . . . . . . . . . . . . 50 4 Fourier Image Transformer 53 4.1 Transformers . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 55 4.1.1 Attention Is All You Need . . . . . . . . . . . . . . . . . . 55 4.1.2 Fast-Transformers . . . . . . . . . . . . . . . . . . . . . . . 56 4.1.3 Transformers in Computer Vision . . . . . . . . . . . . . . 57 4.2 Methods . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 57 4.2.1 Fourier Domain Encodings (FDEs) . . . . . . . . . . . . . 57 4.2.2 Fourier Coefficient Loss . . . . . . . . . . . . . . . . . . . . 59 4.3 FIT for Super-Resolution . . . . . . . . . . . . . . . . . . . . . . . 60 4.3.1 Super-Resolution Data . . . . . . . . . . . . . . . . . . . . 60 4.3.2 Super-Resolution Experiments . . . . . . . . . . . . . . . . 61 4.4 FIT for Tomography . . . . . . . . . . . . . . . . . . . . . . . . . 63 4.4.1 Computed Tomography Data . . . . . . . . . . . . . . . . 64 4.4.2 Computed Tomography Experiments . . . . . . . . . . . . 66 4.5 Discussion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 69 5 Conclusions and Outlook 71

Articulatory copy synthesis (ACS), a subarea of speech inversion, refers to the reproduction of natural utterances and involves both the physiological articulatory processes and their corresponding acoustic results. This thesis proposes two novel methods for the ACS of human speech using the articulatory speech synthesizer VocalTractLab (VTL) to address or mitigate the existing problems of speech inversion, such as non-unique mapping, acoustic variation among different speakers, and the time-consuming nature of the process. The first method involved finding appropriate VTL gestural scores for given natural utterances using a genetic algorithm. It consisted of two steps: gestural score initialization and optimization. In the first step, gestural scores were initialized using the given acoustic signals with speech recognition, grapheme-to-phoneme (G2P), and a VTL rule-based method for converting phoneme sequences to gestural scores. In the second step, the initial gestural scores were optimized by a genetic algorithm via an analysis-by-synthesis (ABS) procedure that sought to minimize the cosine distance between the acoustic features of the synthetic and natural utterances. The articulatory parameters were also regularized during the optimization process to restrict them to reasonable values. The second method was based on long short-term memory (LSTM) and convolutional neural networks, which were responsible for capturing the temporal dependence and the spatial structure of the acoustic features, respectively. The neural network regression models were trained, which used acoustic features as inputs and produced articulatory trajectories as outputs. In addition, to cover as much of the articulatory and acoustic space as possible, the training samples were augmented by manipulating the phonation type, speaking effort, and the vocal tract length of the synthetic utterances. Furthermore, two regularization methods were proposed: one based on the smoothness loss of articulatory trajectories and another based on the acoustic loss between original and predicted acoustic features. The best-performing genetic algorithms and convolutional LSTM systems (evaluated in terms of the difference between the estimated and reference VTL articulatory parameters) obtained average correlation coefficients of 0.985 and 0.983 for speaker-dependent utterances, respectively, and their reproduced speech achieved recognition accuracies of 86.25% and 64.69% for speaker-independent utterances of German words, respectively. When applied to German sentence utterances, as well as English and Mandarin Chinese word utterances, the neural network based ACS systems achieved recognition accuracies of 73.88%, 52.92%, and 52.41%, respectively. The results showed that both of these methods not only reproduced the articulatory processes but also reproduced the acoustic signals of reference utterances. Moreover, the regularization methods led to more physiologically plausible articulatory processes and made the estimated articulatory trajectories be more articulatorily preferred by VTL, thus reproducing more natural and intelligible speech. This study also found that the convolutional layers, when used in conjunction with batch normalization layers, automatically learned more distinctive features from log power spectrograms. Furthermore, the neural network based ACS systems trained using German data could be generalized to the utterances of other languages.

Optimization is omnipresent in our world. Its numerous applications spread from industrial cases, such as logistics, construction management or production planning; to the private sphere, filled with problems of selecting daycare or vacation planning. In this thesis, we concentrate on expensive black-box optimization (EBBO) problems, a subset of optimization problems (OPs), which are characterized by an expensive cost of evaluating an objective function. Such OPs are reoccurring in various domains, being known as: hyperpameter optimization in machine learning, performance configuration optimization or parameter tuning in search-based software engineering, simulation optimization in operations research, meta-optimization or parameter tuning in the optimization domain itself. High diversity of domains introduces a plethora of solving approaches, which adhere to a similar structure and workflow, but differ in details. The software frameworks stemming from different areas possess only partially intersecting manageability points, i.e., lack manageability. In this thesis, we argue that the lack of manageability in EBBO is a major problem, which leads to underachieving optimization quality. The goal of this thesis is to study the role of manageability in EBBO and to investigate whether improving the manageability of EBBO frameworks increases optimization quality. To reach this goal, we appeal to software product line engineering (SPLE), a methodology for developing highly-manageable software systems. Based on the foundations of SPLE, we introduce a novel framework for EBBO called BRISE. It offers: 1) a loosely-coupled software architecture, separating concerns of the experiment designer and the developer of EBBO strategies; 2) a full coverage of all EBBO problem types; and 3) a context-aware variability model, which captures the experiment-designer-defined OP with the content model; and manageability points including their variants and constraints with the cardinality-based feature model. High manageability of the introduced BRISE framework enables us: 1) to extend the framework with novel efficient strategies, such as adaptive repetition management; and 2) to introduce novel EBBO mechanisms, such as multi-objective compositional surrogate modeling, dynamic sampling and hierarchical surrogate modeling. The evaluation of the novel approaches with a set of case studies, including: the WFG benchmark for multi-objective optimization, combined selection and parameter control of meta-heuristics, and energy optimization; demonstrated their superiority over the state-of-the-art competitors. Thus, it supports the research hypothesis of this thesis: Improving manageability of an EBBO framework enables to increase optimization quality.

Querying and efficiently analyzing complex data is required to gain valuable business insights, to support machine learning applications, and to make up-to-date information available. Therefore, this thesis investigates opportunities and challenges of selecting the most efficient execution strategy for analytical queries. These challenges include hard-to-capture data characteristics such as skew and correlation, the support of arbitrary data types, and the optimization time overhead of complex queries. Existing approaches often rely on optimistic assumptions about the data distribution, which can result in significant response time delays when these assumptions are not met. On the contrary, we focus on robust query optimization, emphasizing consistent query performance and applicability. Our presentation follows the general select-project-join query pattern, representing the fundamental stages of analytical query processing. To support arbitrary data types and complex filter expressions in the select stage, a novel sampling-based selectivity estimator is developed. Our approach exploits information from filter subexpressions and estimates correlations that are not captured by existing sampling-based methods. We demonstrate improved estimation accuracy and query execution time. Further, to minimize the runtime overhead of sampling, we propose new techniques that exploit access patterns and auxiliary database objects such as indices. For the join stage, we introduce a robust optimization approach by developing an upper-bound join enumeration strategy that connects accurate filter selectivity estimates –e.g., using our sampling-based approach– to join ordering. We demonstrate that join orders based on our upper-bound join ordering strategy achieve more consistent performance and faster workload execution on state-of-the-art database systems. However, besides identifying good logical join orders, it is crucial to determine appropriate physical join operators before query plan execution. To understand the importance of fine-grained physical operator selections, we exhaustively execute fixed join orders with all possible operator combinations. This analysis reveals that none of the investigated query optimizers fully reaches the potential of optimal operator decisions. Based on these insights and to achieve fine-grained operator selections for the previously determined join orders, the thesis presents a lightweight learning-based physical execution plan refinement component called. We show that this refinement component consistently outperforms existing approaches for physical operator selection while enabling a novel two-stage optimizer design. We conclude the thesis by providing a framework for the two-stage optimizer design that allows users to modify, replicate, and further analyze the concepts discussed throughout this thesis.:1 INTRODUCTION 1.1 Analytical Query Processing . . . . . . . . . . . . . . . . . . . . . . . . . . 12 1.2 Select-Project-Join Queries . . . . . . . . . . . . . . . . . . . . . . . . . . . 13 1.3 Basics of SPJ Query Optimization . . . . . . . . . . . . . . . . . . . . . . . 14 1.3.1 Plan Enumeration . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14 1.3.2 Cost Model . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15 1.3.3 Cardinality Estimation . . . . . . . . . . . . . . . . . . . . . . . . . . 15 1.4 Robust SPJ Query Optimization . . . . . . . . . . . . . . . . . . . . . . . . 16 1.4.1 Tail Latency Root Cause Analysis . . . . . . . . . . . . . . . . . . . 17 1.4.2 Tenets of Robust Query Optimization . . . . . . . . . . . . . . . . . 19 1.5 Contribution . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19 1.6 Outline . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20 2 SELECT (-PROJECT) STAGE 2.1 Sampling for Selectivity Estimation . . . . . . . . . . . . . . . . . . . . . . 24 2.2 Related Work . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 28 2.2.1 Combined Selectivity Estimation (CSE) . . . . . . . . . . . . . . . . 29 2.2.2 Kernel Density Estimator . . . . . . . . . . . . . . . . . . . . . . . . . 31 2.2.3 Machine Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . 32 2.3 Beta Estimator for 0-Tuple-Situations . . . . . . . . . . . . . . . . . . . . . 33 2.3.1 Methodology . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 33 2.3.2 Beta Distribution in Non-0-TS . . . . . . . . . . . . . . . . . . . . . . 35 2.3.3 Parameter Estimation in 0-TS . . . . . . . . . . . . . . . . . . . . . . 37 2.3.4 Selectivity Estimation and Predicate Ordering . . . . . . . . . . . 39 2.3.5 Evaluation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 46 2.4 Customized Sampling Techniques . . . . . . . . . . . . . . . . . . . . . . 53 2.4.1 Focused Sampling . . . . . . . . . . . . . . . . . . . . . . . . . . . . 54 2.4.2 Conditional Sampling . . . . . . . . . . . . . . . . . . . . . . . . . . 56 2.4.3 Zone Pruning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 58 2.4.4 Discussion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 59 2.5 Summary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 59 3 JOIN STAGE: LOGICAL ENUMERATION 3.1 Related Work . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 62 3.1.1 Point Estimates . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 63 3.1.2 Join Cardinality Upper Bound . . . . . . . . . . . . . . . . . . . . . 64 3.2 Upper Bound Join Enumeration with Synopsis (UES) . . . . . . . . . . . . 66 3.2.1 U-Block: Simple Upper Bound for Joins . . . . . . . . . . . . . . . . 67 3.2.2 E-Block: Customized Enumeration Scheme . . . . . . . . . . . . . 68 3.2.3 UES Algorithm . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 69 3.3 Evaluation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 71 3.3.1 General Performance . . . . . . . . . . . . . . . . . . . . . . . . . . 72 3.3.2 Discussion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 74 3.4 Summary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 76 4 JOIN STAGE: PHYSICAL OPERATOR SELECTION 4.1 Operator Selection vs Join Ordering . . . . . . . . . . . . . . . . . . . . . 77 4.2 Related Work . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 80 4.2.1 Adaptive Query Processing . . . . . . . . . . . . . . . . . . . . . . 80 4.2.2 Bandit Optimizer (Bao) . . . . . . . . . . . . . . . . . . . . . . . . . 81 4.3 TONIC: Learned Physical Join Operator Selection . . . . . . . . . . . . . 82 4.3.1 Query Execution Plan Synopsis (QEP-S) . . . . . . . . . . . . . . . 83 4.3.2 QEP-S Life-Cycle . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 84 4.3.3 QEP-S Design Considerations . . . . . . . . . . . . . . . . . . . . . . 87 4.4 Evaluation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 89 4.4.1 Performance Factors . . . . . . . . . . . . . . . . . . . . . . . . . . . 90 4.4.2 Rate of Improvement . . . . . . . . . . . . . . . . . . . . . . . . . . 92 4.4.3 Data Shift . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 95 4.4.4 TONIC - Runtime Traits . . . . . . . . . . . . . . . . . . . . . . . . . . 97 4.4.5 Discussion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 97 4.5 Summary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 99 5 TWO-STAGE OPTIMIZER FRAMEWORK 5.1 Upper-Bound-Driven Join Ordering Component . . . . . . . . . . . . . 101 5.2 Physical Operator Selection Component . . . . . . . . . . . . . . . . . . 103 5.3 Example Query Optimization . . . . . . . . . . . . . . . . . . . . . . . . . 103 6 CONCLUSION 107 BIBLIOGRAPHY 109 LIST OF FIGURES 117 LIST OF TABLES 121 A APPENDIX A.1 Basics of Query Execution . . . . . . . . . . . . . . . . . . . . . . . . . . . 123 A.2 Why Q? . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 124 A.3 0-TS Proof of Unbiased Estimate . . . . . . . . . . . . . . . . . . . . . . . . 125 A.4 UES Upper Bound Property . . . . . . . . . . . . . . . . . . . . . . . . . . . 127 A.5 TONIC – Selectivity-Aware Branching . . . . . . . . . . . . . . . . . . . . . 128 A.6 TONIC – Sequences of Query Execution . . . . . . . . . . . . . . . . . . . 129

Modern semiconductor manufacturing is a complex process with a multitude of software applications. This application landscape has to be constantly monitored, since the communication and access patterns provide important insights. Because of the high event rates of the equipment log data stream in modern factories, big-data tools are required for scalable state and history analytics. The choice of suitable big-data solutions and their technical realization remains a challenging task. This thesis compares big-data architectures and discovers solutions for log-data ingest, enrichment, analytics and visualization. Based on the use cases and requirements of developers working in this field, a comparison of a custom assembled stack and a complete solution is made. Since the complete stack is a preferable solution, Datadog, Grafana Loki and the Elastic 8 Stack are selected for a more detailed study. These three systems are implemented and compared based on the requirements. All three systems are well suited for big-data logging and fulfill most of the requirements, but show different capabilities when implemented and used.:1 Introduction 1.1 Motivation 1.2 Structure 2 Fundamentals and Prerequisites 2.1 Logging 2.1.1 Log level 2.1.2 CSFW log 2.1.3 SECS log 2.2 Existing system and data 2.2.1 Production process 2.2.2 Log data in numbers 2.3 Requirements 2.3.1 Functional requirements 2.3.2 System requirements 2.3.3 Quality requirements 2.4 Use Cases 2.4.1 Finding specific communication sequence 2.4.2 Watching system changes 2.4.3 Comparison with expected production path 2.4.4 Enrichment with metadata 2.4.5 Decoupled log analysis 3 State of the Art and Potential Software Stacks 3.1 State of the art software stacks 3.1.1 IoT flow monitoring system 3.1.2 Big-Data IoT monitoring system 3.1.3 IoT Cloud Computing Stack 3.1.4 Big-Data Logging Architecture 3.1.5 IoT Energy Conservation System 3.1.6 Similarities of the architectures 3.2 Selection of software stack 3.2.1 Components for one layer 3.2.2 Software solutions for the stack 4 Analysis and Implementation 4.1 Full stack vs. a custom assembled stack 4.1.1 Drawbacks of a custom assembled stack 4.1.2 Advantages of a complete solution 4.1.3 Exclusion of a custom assembled stack 4.2 Selection of full stack solutions 4.2.1 Elastic vs. Amazon 4.2.2 Comparison of Cloud-Only-Solutions 4.2.3 Comparison of On-Premise-Solutions 4.3 Implementation of selected solutions 4.3.1 Datadog 4.3.2 Grafana Loki Stack 4.3.3 Elastic 8 Stack 5 Comparison 5.1 Comparison of components 5.1.1 Collection 5.1.2 Analysis 5.1.3 Visualization 5.2 Comparison of requirements 5.2.1 Functional requirements 5.2.2 System requirements 5.2.3 Quality requirements 5.3 Results 6 Conclusion and Future Work 6.1 Conclusion 6.2 Future Work / Die moderne Halbleiterfertigung ist ein komplexer Prozess mit einer Vielzahl von Softwareanwendungen. Diese Anwendungslandschaft muss ständig überwacht werden, da die Kommunikations- und Zugriffsmuster wichtige Erkenntnisse liefern. Aufgrund der hohen Ereignisraten des Logdatenstroms der Maschinen in modernen Fabriken werden Big-Data-Tools für skalierbare Zustands- und Verlaufsanalysen benötigt. Die Auswahl geeigneter Big-Data-Lösungen und deren technische Umsetzung ist eine anspruchsvolle Aufgabe. Diese Arbeit vergleicht Big-Data-Architekturen und untersucht Lösungen für das Sammeln, Anreicherung, Analyse und Visualisierung von Log-Daten. Basierend auf den Use Cases und den Anforderungen von Entwicklern, die in diesem Bereich arbeiten, wird ein Vergleich zwischen einem individuell zusammengestellten Stack und einer Komplettlösung vorgenommen. Da die Komplettlösung vorteilhafter ist, werden Datadog, Grafana Loki und der Elastic 8 Stack für eine genauere Untersuchung ausgewählt. Diese drei Systeme werden auf der Grundlage der Anforderungen implementiert und verglichen. Alle drei Systeme eignen sich gut für Big-Data-Logging und erfüllen die meisten Anforderungen, zeigen aber unterschiedliche Fähigkeiten bei der Implementierung und Nutzung.:1 Introduction 1.1 Motivation 1.2 Structure 2 Fundamentals and Prerequisites 2.1 Logging 2.1.1 Log level 2.1.2 CSFW log 2.1.3 SECS log 2.2 Existing system and data 2.2.1 Production process 2.2.2 Log data in numbers 2.3 Requirements 2.3.1 Functional requirements 2.3.2 System requirements 2.3.3 Quality requirements 2.4 Use Cases 2.4.1 Finding specific communication sequence 2.4.2 Watching system changes 2.4.3 Comparison with expected production path 2.4.4 Enrichment with metadata 2.4.5 Decoupled log analysis 3 State of the Art and Potential Software Stacks 3.1 State of the art software stacks 3.1.1 IoT flow monitoring system 3.1.2 Big-Data IoT monitoring system 3.1.3 IoT Cloud Computing Stack 3.1.4 Big-Data Logging Architecture 3.1.5 IoT Energy Conservation System 3.1.6 Similarities of the architectures 3.2 Selection of software stack 3.2.1 Components for one layer 3.2.2 Software solutions for the stack 4 Analysis and Implementation 4.1 Full stack vs. a custom assembled stack 4.1.1 Drawbacks of a custom assembled stack 4.1.2 Advantages of a complete solution 4.1.3 Exclusion of a custom assembled stack 4.2 Selection of full stack solutions 4.2.1 Elastic vs. Amazon 4.2.2 Comparison of Cloud-Only-Solutions 4.2.3 Comparison of On-Premise-Solutions 4.3 Implementation of selected solutions 4.3.1 Datadog 4.3.2 Grafana Loki Stack 4.3.3 Elastic 8 Stack 5 Comparison 5.1 Comparison of components 5.1.1 Collection 5.1.2 Analysis 5.1.3 Visualization 5.2 Comparison of requirements 5.2.1 Functional requirements 5.2.2 System requirements 5.2.3 Quality requirements 5.3 Results 6 Conclusion and Future Work 6.1 Conclusion 6.2 Future Work

Today's Internet is seeing a massive shift from traditional client-server applications towards real-time, context-sensitive, and highly immersive applications. The fusion between Cyber-physical systems, The Internet of Things (IoT), Augmented/Virtual-Reality (AR/VR), and the Tactile Internet with the Human-in-the-Loop (TaHIL) means that Ultra-Reliable Low Latency Communication (URLLC) is a key functional requirement. Mobile Edge Computing (MEC) has emerged as a network architectural paradigm to address such ever-increasing resource demands. MEC leverages networking and computational resource pools that are closer to the end-users at the far edge of the network, eliminating the need to send and process large volumes of data over multiple distant hops at central cloud computing data centers. Multiple 'cloudlets' are formed at the edge, and the access to resources is shared and federated across them over multiple network domains that are distributed over various geographical locations. However, this federated access comes at the cost of a fuzzy and dynamically-changing network security perimeter because there are multiple sources of mobility. Not only are the end users mobile, but the applications themselves virtually migrate over multiple network domains and cloudlets to serve the end users, bypassing statically placed network security middleboxes and firewalls. This work aims to address this problem by proposing adaptive network security measures that can be dynamically changed at runtime, and are decoupled from the ever-changing network topology. In particular, we: 1) use the state of the art in programmable networking to protect MEC networks from internal adversaries that can adapt and laterally move, 2) Automatically infer application security contexts, and device vulnerabilities, then evolve the network access control policies to segment the network in such a way that minimizes the attack surface with minimal impact on its utility, 3) propose new metrics to assess the susceptibility of edge nodes to a new class of stealthy attacks that bypasses traditional statically placed Intrusion Detection Systems (IDS), and a probabilistic approach to pro-actively protect them.:Acknowledgments Acronyms & Abbreviations 1 Introduction 1.1 Prelude 1.2 Motivation and Challenges 1.3 Aim and objectives 1.4 Contributions 1.5 Thesis structure 2 Background 2.1 A primer on computer networks 2.2 Network security 2.3 Network softwarization 2.4 Cloudification of networks 2.5 Securing cloud networks 2.6 Towards Securing Edge Cloud Networks 2.7 Summary I Adaptive security in consumer edge cloud networks 3 Automatic microsegmentation of smarthome IoT networks 3.1 Introduction 3.2 Related work 3.3 Smart home microsegmentation 3.4 Software-Defined Secure Isolation 3.5 Evaluation 3.6 Summary 4 Smart home microsegmentation with user privacy in mind 4.1 Introduction 4.2 Related Work 4.3 Goals and Assumptions 4.4 Quantifying the security and privacy of SHIoT devices 4.5 Automatic microsegmentation 4.6 Manual microsegmentation 4.7 Experimental setup 4.8 Evaluation 4.9 Summary II Adaptive security in enterprise edge cloud networks 5 Adaptive real-time network deception and isolation 5.1 Introduction 5.2 Related work 5.3 Sandnet’s concept 5.4 Live Cloning and Network Deception 5.5 Evaluation 5.6 Summary 6 Localization of internal stealthy DDoS attacks on Microservices 6.1 Introduction 6.2 Related work 6.3 Assumptions & Threat model 6.4 Mitigating SILVDDoS 6.5 Evaluation 6.6 Summary III Summary of Results 7 Conclusion 7.1 Main outcomes 7.2 Future outlook Listings Bibliography List of Algorithms List of Figures List of Tables Appendix