• Refine Query
  • Source
  • Publication year
  • to
  • Language
  • 127
  • 54
  • Tagged with
  • 179
  • 179
  • 179
  • 179
  • 179
  • 26
  • 24
  • 20
  • 18
  • 18
  • 17
  • 15
  • 15
  • 15
  • 14
  • About
  • The Global ETD Search service is a free service for researchers to find electronic theses and dissertations. This service is provided by the Networked Digital Library of Theses and Dissertations.
    Our metadata is collected from universities around the world. If you manage a university/consortium/country archive and want to be added, details can be found on the NDLTD website.
21

Explainable Artificial Intelligence for Image Segmentation and for Estimation of Optical Aberrations

Vinogradova, Kira 18 December 2023 (has links)
State-of-the-art machine learning methods such as convolutional neural networks (CNNs) are frequently employed in computer vision. Despite their high performance on unseen data, CNNs are often criticized for lacking transparency — that is, providing very limited if any information about the internal decision-making process. In some applications, especially in healthcare, such transparency of algorithms is crucial for end users, as trust in diagnosis and prognosis is important not only for the satisfaction and potential adherence of patients, but also for their health. Explainable artificial intelligence (XAI) aims to open up this “black box,” often perceived as a cryptic and inconceivable algorithm, to increase understanding of the machines’ reasoning.XAI is an emerging field, and techniques for making machine learning explainable are becoming increasingly available. XAI for computer vision mainly focuses on image classification, whereas interpretability in other tasks remains challenging. Here, I examine explainability in computer vision beyond image classification, namely in semantic segmentation and 3D multitarget image regression. This thesis consists of five chapters. In Chapter 1 (Introduction), the background of artificial intelligence (AI), XAI, computer vision, and optics is presented, and the definitions of the terminology for XAI are proposed. Chapter 2 is focused on explaining the predictions of U-Net, a CNN commonly used for semantic image segmentation, and variations of this architecture. To this end, I propose the gradient-weighted class activation mapping for segmentation (Seg-Grad-CAM) method based on the well-known Grad-CAM method for explainable image classification. In Chapter 3, I present the application of deep learning to estimation of optical aberrations in microscopy biodata by identifying the present Zernike aberration modes and their amplitudes. A CNN-based approach PhaseNet can accurately estimate monochromatic aberrations in images of point light sources. I extend this method to objects of complex shapes. In Chapter 4, an approach for explainable 3D multitarget image regression is reported. First, I visualize how the model differentiates the aberration modes using the local interpretable model-agnostic explanations (LIME) method adapted for 3D image classification. Then I “explain,” using LIME modified for multitarget 3D image regression (Image-Reg-LIME), the outputs of the regression model for estimation of the amplitudes. In Chapter 5, the results are discussed in a broader context. The contribution of this thesis is the development of explainability methods for semantic segmentation and 3D multitarget image regression of optical aberrations. The research opens the door for further enhancement of AI’s transparency.:Title Page i List of Figures xi List of Tables xv 1 Introduction 1 1.1 Essential Definitions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2 1.1.1 Artificial intelligence . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2 1.1.2 Explainable . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4 1.1.3 Proposed definitions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5 1.2 Explainable Artificial Intelligence . . . . . . . . . . . . . . . . . . . . . . . . . . 6 1.2.1 Aims and applications . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6 1.2.2 Methods . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7 1.3 Computer Vision . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10 1.3.1 Applications . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10 1.3.2 Image classification . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11 1.3.3 Image regression . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12 1.3.4 Image segmentation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12 1.4 Optics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13 1.4.1 Aberrations . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14 1.4.2 Zernike polynomials . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17 1.5 Thesis Overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19 1.5.1 Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19 1.5.2 Dissertation outline . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21 2 Explainable Image Segmentation 23 2.1 Abstract . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 23 2.2 Related Work . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 24 2.3 Methods . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 26 2.3.1 CAM . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 26 2.3.2 Grad-CAM . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 27 2.3.3 U-Net . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 29 2.3.4 Seg-Grad-CAM . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 30 2.4 Data . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 36 2.4.1 Circles . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 36 2.4.2 TextureMNIST . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 36 2.4.3 Cityscapes . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 37 2.5 Results . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 39 2.5.1 Circles . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 39 2.5.2 TextureMNIST . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 41 2.5.3 Cityscapes . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 47 2.6 Applications . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 51 2.7 Conclusions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 52 3 Estimation of Aberrations 55 3.1 Abstract . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 55 3.2 Related Work . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 56 3.3 Methods . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 58 3.3.1 PhaseNet . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 58 3.3.2 PhaseNet data generator . . . . . . . . . . . . . . . . . . . . . . . . . . . 59 3.3.3 Retrieval of noise parameters . . . . . . . . . . . . . . . . . . . . . . . . 62 3.3.4 Data generator with phantoms . . . . . . . . . . . . . . . . . . . . . . . 62 3.3.5 Restoration via deconvolution . . . . . . . . . . . . . . . . . . . . . . . . 63 3.3.6 Convolution with the “zero” synthetic PSF . . . . . . . . . . . . . . . . 63 3.4 Data . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 64 3.4.1 Astrocytes (synthetic data) . . . . . . . . . . . . . . . . . . . . . . . . . 65 3.4.2 Fluorescent beads . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 66 3.4.3 Drosophila embryo (live sample) . . . . . . . . . . . . . . . . . . . . . . 67 3.4.4 Neurons (fixed sample) . . . . . . . . . . . . . . . . . . . . . . . . . . . 68 3.5 Results . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 69 3.5.1 Astrocytes . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 69 3.5.2 Conclusions on the results for astrocytes . . . . . . . . . . . . . . . . . . 74 3.5.3 Fluorescent beads . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 75 3.5.4 Conclusions on the results for fluorescent beads . . . . . . . . . . . . . . 81 3.5.5 Drosophila embryo . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 83 3.5.6 Conclusions on the results for Drosophila embryo . . . . . . . . . . . . . 87 3.5.7 Neurons . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 88 3.6 Conclusions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 96 4 Explainable Multitarget Image Regression 99 4.1 Abstract . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 99 4.2 Related Work . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 100 4.3 Methods . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 102 4.3.1 LIME . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 102 4.3.2 Superpixel algorithms . . . . . . . . . . . . . . . . . . . . . . . . . . . . 104 4.3.3 LIME for 3D image classification . . . . . . . . . . . . . . . . . . . . . . 104 4.3.4 Image-Reg-LIME: LIME for 3D image regression . . . . . . . . . . . . . 107 4.4 Results: Classification of Aberrations . . . . . . . . . . . . . . . . . . . . . . . . 109 viii TABLE OF CONTENTS 4.4.1 Transforming the regression task into classification . . . . . . . . . . . . 110 4.4.2 Data augmentation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 111 4.4.3 Parameter search . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 112 4.4.4 Clustering of 3D images . . . . . . . . . . . . . . . . . . . . . . . . . . . 114 4.4.5 Explanations of classification . . . . . . . . . . . . . . . . . . . . . . . . 114 4.4.6 Conclusions on the results for classification . . . . . . . . . . . . . . . . 117 4.5 Results: Explainable Regression of Aberrations . . . . . . . . . . . . . . . . . . 118 4.5.1 Explanations with a reference value . . . . . . . . . . . . . . . . . . . . 121 4.5.2 Validation of explanations . . . . . . . . . . . . . . . . . . . . . . . . . . 122 4.6 Conclusions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 125 5 Conclusions and Outlook 127 References 129
22

Streaming-Based Progressive Enhancement of Websites for Slow and Error-Prone Networks

Vogel, Lucas Jacob 29 June 2023 (has links)
This thesis aims to improve the loading times of web pages by streaming the content in a non-render-blocking way. At the beginning of this thesis, a large-scale analysis was performed, spanning all downloadable pages of the top 10.000 web pages according to the Tranco-list. This analysis aimed to gather data about the render-blocking properties of web page resources, including HTML, JavaScript, and CSS. It further gathered data about code coverage, giving insight into how much of the render-blocking code is actually used. Therefore, the structural optimization potential could be determined. Less render-blocking code will, in turn, lead to faster loading times due to requiring less data to display the page. The analysis showed that there is significant optimization potential left. On average, modern web pages are built with a combined 86.7% of JavaScript and CSS, the rest being HTML. Both JavaScript and CSS are loaded mostly render-blocking, with 91.8% of JavaScript and 89.47% of CSS loaded in this way. Furthermore, only 40.8% of JavaScript and 15.9% of CSS is used until render. This shows that, on average, web pages have significant room for improvement. The concept, which is then developed based on the results of this analysis, aims to load web pages in a new way by streaming all render-blocking content. The related work showed that multiple sub-techniques are required first, which were conceptualized next. First, an optimization and splitting tool for CSS is proposed, called Essential. This is followed by an optimization framework concept for JavaScript, consisting of Waiter and AUTRATAC. Lastly, a backward-compatible approach was developed, which allows for splitting HTML and streaming all content to a client. The evaluation showed that the streamed web page loads significantly faster when comparing FCP, content ”Above-the-Fold,” and total transfer time of all render-blocking resources of the document. For example, the case study test determined that the streamed page could reduce the time until FCP by 83.3% at 2 Mbps and the time until the last render-blocking data is transferred by up to 70.4% at 2 Mbps. Furthermore, existing streaming methods were also compared, determining that WebSockets meets the requirements to stream web page content sufficiently. Lastly, an anonymous online user questionnaire showed that 85% of users preferred this new style of loading pages.
23

Multi-Scale Modeling and Simulation of Cell Signaling and Transport in Renal Collecting Duct Principal Cells

Leberecht, Christoph 22 December 2022 (has links)
The response of cells to their environment is driven by a variety of proteins and messenger molecules. In eukaryotes, their distribution and location in the cell is regulated by the vesicular transport system. The transport of aquaporin 2 between membrane and storage region is a crucial part of the water reabsorption in renal principal cells, and its malfunction can lead to Diabetes insipidus. To understand the regulation of this system, I aggregated pathways and mechanisms from literature and derived models in a hypothesis-driven approach. Furthermore, I combined the models to a single multi-scale model to gain insight into key regulatory mechanisms of aquaporin 2 recycling. To achieve this, I developed a computational framework for the modeling and simulation of cellular signaling systems. The framework integrates reaction and difusion of biochemical entities on a microscopic scale with mobile vesicles, membranes, and compartments on a cellular level. The simulation uses an adaptive step-width approach that e ciently regulates the agent-based simulation of macroscopic components with the numerical integration of mass action kinetics and grid-based nite diference methods. A reaction network generation algorithm was designed, that, in combination with a highly-modular modeling approach, allows for fast model prototyping. The analysis of the aquaporin 2 model system rationalizes that the compartmentalization of cAMP in renal principal cells is a result of the protein kinase A signalosome and can only occur if speci c cellular components are observed in conjunction. Endocytotic and exocytotic processes are inherently connected and can be regulated by the same protein kinase A signal.:Abstract 1. Introduction 1.1. Eukaryotic Signaling 1.2. Modeling and Simulation of Cellular Processes 1.3. Aquaporin 2 recycling 1.4. Motivation and Aims 1.5. Outline I. Background 2. Modeling and Simulation of Complex Signaling Pathways 2.1. Multi-scale Modeling 2.1.1. Approaches to Multi-scale Modeling 2.1.2. Reduction of Computational Complexity 2.2. Models of Chemical Reaction Networks 2.2.1. Reactions and Reaction Rates 2.2.2. Numerical Solutions 2.2.3. Reaction Network Generation 2.3. Models of Intracellular Transport 2.3.1. Undirected Transport 2.3.2. Directed Transport 3. Aquaporin 2 Recycling in Renal Principal Cells 3.1. The Physiology of Water Homeostasis 3.2. Molecular Mechanisms of the Vasopressin Response 3.2.1. The Vasopressin Receptor 3.2.2. cAMP Regulation of Protein Kinase A 3.2.3. Endo- and Exocytosis 3.3. Models of Water Transport in Renal Principal Cells II. Results & Discussion 4. Multi-scale Simulation of Cellular Signaling Pathways 4.1. Scale Separation and Bridging 4.2. Micro-scale Simulation Approach 4.2.1. Difusion and Discretization of the Simulation Space 4.2.2. Reaction Kinetics 4.3. Rule-based Reaction Network Generation 4.3.1. Definition of the Data Model 4.3.2. Design of Rule Based Reactions 4.3.3. Automated Generation of Reaction Networks 4.4. Macro-scale Simulation Approach 4.4.1. Agent-based Simulation of Discrete Entities 4.4.2. Modules for Displacement-based Behavior 4.5. Modularization and Error Estimation 4.5.1. Determination of the Numerical Error 4.5.2. Modularization of Concentration-based Events 4.5.3. Determination of the Displacement-based Error 5. Aquaporin 2 Recycling Model and Simulation 5.1. Model of Allosteric PKA Phosphorylation 5.1.1. Model Design 5.1.2. Simulation Results and Discussion 5.1.3. Conclusions 5.2. cAMP Compartmentalization in the Vesicle Storage Region 5.2.1. Model Design 5.2.2. Simulation Results and Discussion 5.2.3. Conclusions 5.3. Clathrin-mediated Endocytosis 5.3.1. Model Design 5.3.2. Simulation Results and Discussion 5.3.3. Conclusions 5.4. Intracellular Transport and Recycling 5.4.1. Model Design 5.4.2. Simulation Results and Discussion 6. Conclusion 6.1. Modeling and simulation approach 6.2. Insights into the AQP2 recycling model III. Appendix A. Code Availability B. Module Overview Bibliography
24

Sich selbst organisierende Produktionsplanung und -steuerung

Krockert, Martin 07 February 2024 (has links)
In dieser Dissertation wird die Entwicklung eines selbstorganisierenden Produktionssystems untersucht, um die Herausforderungen in der Produktionsplanung und -steuerung, insbesondere bei Unsicherheiten, besser zu bewältigen. Die Arbeit analysiert zunächst die Grundlagen der Produktionsplanung und -steuerung, gefolgt von einer detaillierten Untersuchung des interdisziplinären Themas der Selbstorganisation. Basierend darauf wird ein Vorgehen zur Identifikation geeigneter Methoden der Selbstorganisation für eine bestimmte Problemstellung entwickelt und auf Produktionsplanung und -steuerung angewendet. Durch die Bewertung bestehender Referenzarchitekturen und deren Integration in ein Framework für selbstorganisierende Produktion, werden selbstorganisierende Verfahren mit etablierten Verfahren der Produktionsplanung und -steuerung verglichen. Die Arbeit zeigt die Überlegenheit der selbstorganisierenden Systeme bei der Planung unter Unsicherheit und liefert nachweislich Verbesserungen hinsichtlich der sekundären und tertiären Ziele der Produktion. Die Dissertation gliedert sich in acht Kapitel, die jeweils verschiedene Aspekte der Selbstorganisation, Produktionsplanung und -steuerung, sowie die Entwicklung und Evaluation eines selbstorganisierenden Produktionssystems behandeln. Die Ergebnisse dieser Arbeit haben das Potenzial, die Produktionsplanung und -steuerung unter Unsicherheit effektiver zu gestalten und somit eine bedeutende Verbesserung für die Industrie zu bieten.:1. Einleitung 18 1.1. Motivation zur Nutzung von Selbstorganisation in der Produktionsplanung und -steuerung 1.2. Forschungsfragen: Wie kann Selbstorganisation bei der Bewältigung der Aufgaben der PPS helfen? 1.3. Aufbau und Vorgehensweise dieser Arbeit 2. Produktionsplanung und -steuerung 2.1. Einführung in die Produktionsplanung und -steuerung 2.1.1. Planung 2.1.2. Produktion 2.1.3. Produktionsplanung und -steuerung 2.2. Ziele der Produktionsplanung und -steuerung 2.2.1. Primäre Ziele 2.2.2. Sekundäre Ziele 2.2.3. Tertiäre Ziele 2.3. Zentral organisierte Produktionsplanung und -steuerung 2.3.1. Aufbau der zentral organisierten Produktionsplanung und -steuerung 2.3.2. Ablauf der zentral organisierten Produktionsplanung 2.3.3. Ablauf der zentral organisierten Produktionssteuerung 2.4. Unsicherheit in der Produktionsplanung und -steuerung 2.5. Arten von Entscheidungsproblemen in der Produktionsplanung und -steuerung 3. Selbstorganisation 3.1. Selbstorganisation in komplexen Systemen 3.2. Sich selbst organisierenden Systemen zugeschriebene Eigenschaften 3.2.1. Offenheit des Systems 3.2.2. Emergenz des Systems 3.2.3. Nichtlinearität des Systems 3.2.4. Attraktoren im Zustandsraum des Systems 3.2.5. Indeterminismus des Systems 3.2.6. Pfadabhängigkeit des Systems 3.2.7. Autonomie der Elemente im System 3.2.8. Autopoiesis neuer Elemente im System 3.2.9. Anpassungsfähigkeit des Systems 3.3. Von statischen zu sich selbst organisierenden Systemen 4. Vorgehensweise zur Entwicklung eines sich selbst organisierenden Systems zur Produktionsplanung und -steuerung 4.1. Vorgehen zur Entwicklung sich selbst organisierender Systeme 4.2. Elemente eines sich selbst organisierenden Systems 4.3. Umwelteinflüsse und Interaktionsmuster sich selbst organisierender Systeme 4.3.1. Taxonomie der Interaktion zur Koordination 4.3.2. Interaktionsmuster zur Koordination sich selbst organisierender Systeme 4.3.3. Zuordnung von Interaktionsmustern zu Entscheidungsproblemen 4.4. Organisationsstrukturen von Systemen 4.5. Ungewollte Phänomene bei der Verwendung von Selbstorganisation 4.6. Anwendungsgebiete der Selbstorganisation in der Produktionsplanung und -steuerung 5. Referenzarchitekturen für sich selbst organisierende Systeme und für die Produktionsplanung und -steuerung 85 5.1. Anforderungen an eine sich selbst organisierende Produktionsplanung und -steuerung 5.2. Referenzarchitekturen für sich selbst organisierende Systeme 5.2.1. Autonomic Computing 5.2.2. Organic Computing 5.2.3. Multi-Agenten Systeme 5.2.4. Aktor-Modell 5.2.5. Warteschlangennetzwerke 5.3. Referenzarchitekturen für die Produktionsplanung und -steuerung 5.3.1. Product Ressource Order Straff Architecture 5.3.2. ISA-95 5.3.3. Reference Architecture Model for Industry 4.0 5.4. Herausforderungen der Überführung einer sich selbst organisierenden Produktion in die Realität 6. Architektur für eine sich selbst organisierte Produktion 105 6.1. MATE - Manufacturing on Actor Technology 6.2. Elemente der sich selbst organisierenden Produktionsplanung und -steuerung 108 6.3. Umwelteinflüsse auf die sich selbst organisierende Produktionsplanung und -steuerung 6.4. Organisation der Elemente 6.4.1. Koordination der sich selbst organisierenden Produktionsplanung und -steuerung 6.4.2. Verhalten bei der sich selbst organisierten Planung 6.4.3. Verhalten bei der sich selbst organisierten Produktionssteuerung 7. Evaluierung der sich selbst organisierenden Produktionsplanung und -steuerung 122 7.1. Ablauf der Evaluation der Produktionsplanung und -steuerung 7.2. Datenerhebung für verschiedene Produktionen 7.2.1. Möglichkeiten der Datenerhebung 7.2.2. Grundlegendes Vorgehen zur Testdatengenerierung 7.2.3. Strukturbeschreibende Kennzahlen der Produktion 7.3. Generierung der Daten für die Evaluierung der Produktionsplanung und - steuerung 7.3.1. Validierung der generierten Testdaten 7.3.2. Generierung der zu evaluierenden Produktion 7.4. Beschreibung der Ansätze zur zentralen und dezentralen Produktionsplanung und -steuerung zum Zweck des Vergleichs 7.4.1. Zentral organisiertes Planungssystem 7.4.2. Dezentral organisiertes Planungssystem mittels erschöpfender Zuteilung 7.5. Vergleich der Ansätze hinsichtlich der Ziele der Produktionsplanung und - steuerung 7.5.1. Effizienz 7.5.2. Termintreue der Kundenaufträge 7.5.3. Durchlaufzeit der Materialien 7.5.4. Auslastung der Produktionsressourcen 7.5.5. Lagerbelegung über die Zeit 7.5.6. Stabilität 7.5.7. Robustheit 7.5.8. Flexibilität 7.5.9. Anpassungsfähigkeit 7.5.10. Skalierbarkeit 7.6. Vergleich der Ansätze hinsichtlich verschiedener Eigenschaften der Produktion 8. Einordnung und Bewertung der Ergebnisse, Zusammenfassung und Ausblick 8.1. Einordnung der Eigenschaften der sich selbst organisierenden Produktionsplanung und -steuerung 8.2. Bewertung der Ergebnisse der Evaluation der sich selbst organisierenden Produktionsplanung und -steuerung 8.3. Zusammenfassung 8.4. Ausblick
25

Diffusion-Based Generation of SVG Images

Jbara, Hassan 06 February 2024 (has links)
Diffusion Models have achieved state-of-the-art results in image generating tasks, yet face different challenges when used in different domains. We first give a brief overview of the Diffusion Models architecture. Then, we present a new model and architecture called SVGFusion that applies the principles of Diffusion Models to generate Vector Graphics. Vector Graphics have a complex structure and are vastly different than pixel images, and thus the main challenge when working with Vector Graphics is how to represent their complex structure in a way that a Diffusion Model can effectively process. We will explain this and the further challenges that we encountered during the process and how we successfully addressed some of them. We demonstrate the effectiveness of our approach by training a sample model on a decently sized dataset as well as running valuable experiments. Furthermore, we offer useful insights, recommendations and code to researchers who wish to further explore this topic.
26

Computer Vision Approaches for Mapping Gene Expression onto Lineage Trees

Lalit, Manan 06 December 2022 (has links)
This project concerns studying the early development of living organisms. This period is accompanied by dynamic morphogenetic events. There is an increase in the number of cells, changes in the shape of cells and specification of cell fate during this time. Typically, in order to capture the dynamic morphological changes, one can employ a form of microscopy imaging such as Selective Plane Illumination Microscopy (SPIM) which offers a single-cell resolution across time, and hence allows observing the positions, velocities and trajectories of most cells in a developing embryo. Unfortunately, the dynamic genetic activity which underlies these morphological changes and influences cellular fate decision, is captured only as static snapshots and often requires processing (sequencing or imaging) multiple distinct individuals. In order to set the stage for characterizing the factors which influence cellular fate, one must bring the data arising from the above-mentioned static snapshots of multiple individuals and the data arising from SPIM imaging of other distinct individual(s) which characterizes the changes in morphology, into the same frame of reference. In this project, a computational pipeline is established, which achieves the aforementioned goal of mapping data from these various imaging modalities and specimens to a canonical frame of reference. This pipeline relies on the three core building blocks of Instance Segmentation, Tracking and Registration. In this dissertation work, I introduce EmbedSeg which is my solution to performing instance segmentation of 2D and 3D (volume) image data. Next, I introduce LineageTracer which is my solution to performing tracking of a time-lapse (2d+t, 3d+t) recording. Finally, I introduce PlatyMatch which is my solution to performing registration of volumes. Errors from the application of these building blocks accumulate which produces a noisy observation estimate of gene expression for the digitized cells in the canonical frame of reference. These noisy estimates are processed to infer the underlying hidden state by using a Hidden Markov Model (HMM) formulation. Lastly, for wider dissemination of these methods, one requires an effective visualization strategy. A few details about the employed approach are also discussed in the dissertation work. The pipeline was designed keeping imaging volume data in mind, but can easily be extended to incorporate other data modalities, if available, such as single cell RNA Sequencing (scRNA-Seq) (more details are provided in the Discussion chapter). The methods elucidated in this dissertation would provide a fertile playground for several experiments and analyses in the future. Some of such potential experiments and current weaknesses of the computational pipeline are also discussed additionally in the Discussion Chapter.
27

Methods and Tools for Battery-free Wireless Networks

Geißdörfer, Kai 15 November 2022 (has links)
Embedding small wireless sensors into the environment allows for monitoring physical processes with high spatio-temporal resolutions. Today, these devices are equipped with a battery to supply them with power. Despite technological advances, the high maintenance cost and environmental impact of batteries prevent the widespread adoption of wireless sensors. Battery-free devices that store energy harvested from light, vibrations, and other ambient sources in a capacitor promise to overcome the drawbacks of (rechargeable) batteries, such as bulkiness, wear-out and toxicity. Because of low energy input and low storage capacity, battery-free devices operate intermittently; they are forced to remain inactive for most of the time charging their capacitor before being able to operate for a short time. While it is known how to deal with intermittency on a single device, the coordination and communication among groups of multiple battery-free devices remain largely unexplored. For the first time, the present thesis addresses this problem by proposing new methods and tools to investigate and overcome several fundamental challenges.
28

Automatisierte Messdatenauswertung am Motorprüfstand in Python

Brückner, Kathleen, Lenz, Matthias, Bachmann, Thomas 28 May 2024 (has links)
In diesem Dokument ist ein Skript vorgestellt, welches Messdaten in Python aus verschiedenen Messsystemen eines Motorprüfstands automatisiert zusammenfasst, erforderliche motorische Berechnungen durchführt und Diagramme ausgewählter Kennwerte zeichnet.:1. Problemstellung 2. Datenverarbeitung im Auswerteskript 2.1. Import der Messdaten 2.2. Benennung der Messdaten zur Datenüberprüfung 3. Verarbeitung und Berechnung 4. Diagrammerstellung zur Auswertung 5. Fazit Literatur
29

Topological properties of music collaboration networks: The case of Jazz and Hip Hop

Burghardt, Manuel, Gienapp, Lukas, Kruckenberg, Clara 29 May 2024 (has links)
Studying collaboration in music is a prominent area of research in fields such as cultural studies, history, and musicology. For scholars interested in studying collaboration, network analysis has proven to be a viable methodological approach. Yet, a challenge is that heterogeneous data makes it difficult to study collaboration networks across music genres, which means that there are almost only studies on individual genres. To solve this problem, we propose a generalizable approach to studying the topological properties of music collaboration networks within and between genres that relies on data from the freely available Discogs database. To illustrate the approach, we provide a comparison of the genres Jazz and Hip Hop.
30

Augmentierte Notizbücher und Natürliche Interaktion: Unterstützung der Kulturtechnik Handschrift in einer digitalen Forschungswelt

Schwappach, Florin, Burghardt, Manuel 11 June 2024 (has links)
No description available.

Page generated in 0.1487 seconds