In der vorliegenden Dissertation wurde ein datengetriebenes Verfahren zum maschinellen Lernen von Mensch-Roboter Interaktionen auf Basis von Mensch-Mensch Demonstrationen entwickelt. Während einer Trainingsphase werden Bewegungen zweier Interakteure mittels Motion Capture erfasst und in einem Zwei-Personen Interaktionsmodell gelernt. Zur Laufzeit wird das Modell sowohl zur Erkennung von Bewegungen des menschlichen Interaktionspartners als auch zur Generierung angepasster Roboterbewegungen eingesetzt. Die Leistungsfähigkeit des Ansatzes wird in drei komplexen Anwendungen evaluiert, die jeweils kontinuierliche Bewegungskoordination zwischen Mensch und Roboter erfordern. Das Ergebnis der Dissertation ist ein Lernverfahren, das intuitive, zielgerichtete und sichere Kollaboration mit Robotern ermöglicht.

Machine Learning interatomic potentials (ML-IAP) are currently the most promising Non-empirical IAPs for molecular dynamic (MD) simulations. They use Machine Learning (ML) methods to fit the potential energy surface (PES) with large reference datasets of the atomic configurations and their corresponding properties. Promising near quantum mechanical accuracy while being orders of magnitudes faster than first principle methods, ML-IAPs are the new “hot topic” in material science research. Unfortunately, most of the available publications require advanced knowledge about ML methods and IAPs, making them hard to understand for beginners and outsiders. This work serves as a plain introduction, providing all the required knowledge about IAPs, ML, and ML-IAPs from the beginning and giving an overview of the most relevant approaches and concepts for building those potentials. Exemplary a gaussian approximation potential (GAP) for amorphous carbon is used to simulate the defect induced deformation of carbon nanotubes. Comparing the results with published density-functional tight-binding (DFTB) results and own Empirical IAP MD-simulations shows that publicly available ML-IAP can already be used for simulation, being indeed faster than and nearly as accurate as first-principle methods. For the future two main challenges appear: First, the availability of ML-IAPs needs to be improved so that they can be easily used in the established MD codes just as the Empirical IAPs. Second, an accurate characterization of the bonds represented in the reference dataset is needed to assure that a potential is suitable for a special application, otherwise making it a 'black-box' method.:1 Introduction 2 Molecular Dynamics 2.1 Introduction to Molecular Dynamics 2.2 Interatomic Potentials 2.2.1 Development of PES 3 Machine Learning Methods 3.1 Types of Machine Learning 3.2 Building Machine Learning Models 3.2.1 Preprocessing 3.2.2 Learning 3.2.3 Evaluation 3.2.4 Prediction 4 Machine Learning for Molecular Dynamics Simulation 4.1 Definition 4.2 Machine Learning Potentials 4.2.1 Neural Network Potentials 4.2.2 Gaussian Approximation Potential 4.2.3 Spectral Neighbor Analysis Potential 4.2.4 Moment Tensor Potentials 4.3 Comparison of Machine Learning Potentials 4.4 Machine Learning Concepts 4.4.1 On the fly 4.4.2 De novo Exploration 4.4.3 PES-Learn 5 Simulation of defect induced deformation of CNTs 5.1 Methodology 5.2 Results and Discussion 6 Conclusion and Outlook 6.1 Conclusion 6.2 Outlook

Alternative Geschäftsmodelle wie Software as a Service (SaaS) und Open-Source-Software (OSS) steigern die Attraktivität von Enterprise Resource Planning (ERP) Systemen für Kleine und Mittelständische Unternehmen (KMU). Jedoch stellen die Beratungsleistungen, die für die Konfiguration eines ERP-Systems zur Anpassung an die spezifischen Bedürfnisse eines Unternehmens notwendig sind, eine hohe Einführungshürde dar. Eine Konfigurationsoption, die bei vielen ERP-Systemen eine Rolle spielt, ist die Kategorienkonfiguration. Mit Hilfe einer automatisierten Konfigurationsunterstützung können Geschäftsführer von kleinen Unternehmen die Kategorienkonfiguration selbst durchführen und einen Teil der Einführungskosten einsparen. Im Rahmen der kumulativen Dissertation werden Automatisierungsansätze zur Konfigurationsunterstützung für die ERP-Kategorienkonfiguration generiert und auf das Open-Source ERP-System ERP5 angewandt. Die Automatisierungsansätze basieren auf Ähnlichkeitsberechnungen zu Falldatensätzen von 235 Unternehmen, Kategorien-Konsolidierung durch Umleitungsinformationen in Wikipedia-Artikeln, Templates und Meta-Templates. Die empirische Evaluation in einem Laborexperiment mit 100 Teilnehmern und eine Umfrage bestätigen die Gültigkeit, Nützlichkeit und Effektivität der generierten Ansätze. Die Konfigurationsunterstützung kann durch einen standardisierten Beratungsprozess und die Vermittlung des für eine konkrete ERP-Einführung notwendigen Wissens mittels Massenindividualisierung ergänzt werden. Dieser Ansatz wurde mit und für ERP5 umgesetzt und lässt sich auch auf andere Open-Source-Projekte übertragen.

In this thesis inhibition as a means for competition among neurons in an unsupervised learning system is studied. In the first part of the thesis, the role of inhibition in robustness against loss of information in the form of occlusion in visual data is investigated. In the second part, inhibition as a reason for loss of information in the mathematical models of neural system is addressed. In that part, a learning rule for modeling inhibition with lowered loss of information and also a dis-inhibitory system which induces a winner-take-all mechanism are introduced. The models used in this work are unsupervised feature extractors made of biologically plausible neural networks which simulate the V1 layer of the visual cortex.

Sandra Jaworeck's dissertation, submitted to the Faculty of Sociology at Chemnitz University of Technology, examines the connection between machine learning and multilevel analysis to integrate both subjective and objective criteria in health research. At the core of her work is the development of a novel index to measure access to healthcare systems, which considers both subjective and objective criteria. Traditionally, primarily objective criteria such as the number of hospital beds and a country’s healthcare expenditures are used to represent the value of a healthcare system. While these objective measurements provide valuable insights, they often overlook the subjective experiences and perceptions that significantly influence individuals' well-being and health. Jaworeck argues that both subjective and objective measurements have their advantages and disadvantages and that their combination can lead to deeper insights in health research. Using machine learning methods, she develops, for the first time, an index that captures the subjective perception of access to healthcare systems across various countries by integrating both subjective and objective indicators. This advanced approach opens new avenues for better understanding and analyzing the often invisible differences between healthcare systems in different countries. Ultimately, Jaworeck’s work may contribute to explaining the perception of equity in access to healthcare services. Her dissertation fills a significant gap in international health research by developing, validating, and comparing a missing index with existing health indices to highlight its relevance and explanatory power. In summary, Jaworeck's work underscores the importance of integrating subjective perspectives into health research and demonstrates innovative methods for utilizing these perspectives alongside objective criteria to evaluate healthcare systems more comprehensively. / Die Dissertation von Sandra Jaworeck, eingereicht an der Fakultät für Soziologie der Technischen Universität Chemnitz, untersucht die Verbindung zwischen maschinellem Lernen und Mehrebenenanalyse, um sowohl subjektive als auch objektive Kriterien in der Gesundheitsforschung zu integrieren. Im Mittelpunkt ihrer Arbeit steht die Entwicklung eines neuartigen Indexes zur Messung des Zugangs zu Gesundheitssystemen, der sowohl subjektive als auch objektive Kriterien berücksichtigt. Traditionell werden hauptsächlich objektive Kriterien wie die Anzahl der Krankenhausbetten und die Gesundheitsausgaben eines Landes genutzt um den Wert eines Gesundheitssystems darzustellen. Diese objektiven Messungen bieten zwar wertvolle Einblicke, übersehen jedoch oft die subjektiven Erfahrungen und Wahrnehmungen, die das Wohlbefinden und damit auch die Gesundheit von Menschen erheblich beeinflussen können. Jaworeck argumentiert, dass sowohl subjektive als auch objektive Messungen ihre Vor- und Nachteile haben, und dass ihre Kombination zu tiefergehenden Erkenntnissen in der Gesundheitsforschung führen kann. Durch den Einsatz von maschinellen Lernverfahren entwickelt sie erstmals einen Index, der durch den Einbezug von subjektiven und objektiven Indikatoren am Ende die subjektive Wahrnehmung des Zugangs zu Gesundheitssystemen in verschiedenen Ländern erfasst. Dieser fortschrittliche Ansatz eröffnet neue Wege, um die oft unsichtbaren Unterschiede zwischen den Gesundheitssystemen verschiedener Länder besser zu verstehen und gezielt zu analysieren. Letztlich kann Jaworecks Arbeit dazu beitragen, die Gerechtigkeitswahrnehmung im Zugang zu Gesundheitsleistungen zu erklären. Ihre Dissertation schließt eine wichtige Lücke in der internationalen Gesundheitsforschung, indem sie einen fehlenden Index entwickelt, validiert und mit bestehenden Gesundheitsindizes vergleicht, um dessen Relevanz und Aussagekraft zu unterstreichen. Zusammenfassend trägt Jaworecks Arbeit dazu bei, die Bedeutung der Integration subjektiver Perspektiven in die Gesundheitsforschung hervorzuheben und zeigt innovative Methoden auf, wie diese zusammen mit objektiven Kriterien genutzt werden können, um Gesundheitssysteme umfassender zu bewerten.

Diese Arbeit zeigt ausgehend von einer Darstellung der theoretischen Grundlagen automatischer Textklassifikation, dass die aus der Statistical Learning Theory stammenden Support Vector Machines geeignet sind, zu einer präziseren Erkennung unerwünschter E-Mail-Werbung beizutragen. In einer Testumgebung mit einem Corpus von 20 000 E-Mails wurden Testläufe verschiedene Parameter der Vorverarbeitung und der Support Vector Machine automatisch evaluiert und grafisch visualisiert. Aufbauend darauf wird eine Erweiterung für die Open-Source-Software SpamAssassin beschrieben, die die vorhandenen Klassifikationsmechanismen um eine Klassifikation per Support Vector Machine erweitert.

Techn. Universiẗat, Diss., 2002--Darmstadt.

Neurosurgery is a demanding medical discipline that requires a complex interplay of several neuroimaging techniques. This allows structural as well as functional information to be recovered and then visualized to the surgeon. In the case of tumor resections this approach allows more fine-grained differentiation of healthy and pathological tissue which positively influences the postoperative outcome as well as the patient's quality of life. In this work, we will discuss several approaches to establish thermal imaging as a novel neuroimaging technique to primarily visualize neural activity and perfusion state in case of ischaemic stroke. Both applications require novel methods for data-preprocessing, visualization, pattern recognition as well as regression analysis of intraoperative thermal imaging. Online multimodal integration of preoperative and intraoperative data is accomplished by a 2D-3D image registration and image fusion framework with an average accuracy of 2.46 mm. In navigated surgeries, the proposed framework generally provides all necessary tools to project intraoperative 2D imaging data onto preoperative 3D volumetric datasets like 3D MR or CT imaging. Additionally, a fast machine learning framework for the recognition of cortical NaCl rinsings will be discussed throughout this thesis. Hereby, the standardized quantification of tissue perfusion by means of an approximated heating model can be achieved. Classifying the parameters of these models yields a map of connected areas, for which we have shown that these areas correlate with the demarcation caused by an ischaemic stroke segmented in postoperative CT datasets. Finally, a semiparametric regression model has been developed for intraoperative neural activity monitoring of the somatosensory cortex by somatosensory evoked potentials. These results were correlated with neural activity of optical imaging. We found that thermal imaging yields comparable results, yet doesn't share the limitations of optical imaging. In this thesis we would like to emphasize that thermal imaging depicts a novel and valid tool for both intraoperative functional and structural neuroimaging.

Thermal imaging is a non-invasive and marker-free approach for intraoperative measurements of small temperature variations. In this work, we demonstrate the abilities of active dynamic thermal imaging for analysis of tissue perfusion state in case of cerebral ischemia. For this purpose, a NaCl irrigation is applied to the exposed cortex during hemicraniectomy. The cortical temperature changes are measured by a thermal imaging system and the thermal signal is recognized by a novel machine learning framework. Subsequent tissue heating is then approximated by a double exponential function to estimate tissue temperature decay constants. These constants allow us to characterize tissue with respect to its dynamic thermal properties. Using a Gaussian mixture model we show the correlation of these estimated parameters with infarct demarcations of post-operative CT. This novel scheme yields a standardized representation of cortical thermodynamic properties and might guide further research regarding specific intraoperative diagnostics.

Neurosurgery is a demanding medical discipline that requires a complex interplay of several neuroimaging techniques. This allows structural as well as functional information to be recovered and then visualized to the surgeon. In the case of tumor resections this approach allows more fine-grained differentiation of healthy and pathological tissue which positively influences the postoperative outcome as well as the patient's quality of life. In this work, we will discuss several approaches to establish thermal imaging as a novel neuroimaging technique to primarily visualize neural activity and perfusion state in case of ischaemic stroke. Both applications require novel methods for data-preprocessing, visualization, pattern recognition as well as regression analysis of intraoperative thermal imaging. Online multimodal integration of preoperative and intraoperative data is accomplished by a 2D-3D image registration and image fusion framework with an average accuracy of 2.46 mm. In navigated surgeries, the proposed framework generally provides all necessary tools to project intraoperative 2D imaging data onto preoperative 3D volumetric datasets like 3D MR or CT imaging. Additionally, a fast machine learning framework for the recognition of cortical NaCl rinsings will be discussed throughout this thesis. Hereby, the standardized quantification of tissue perfusion by means of an approximated heating model can be achieved. Classifying the parameters of these models yields a map of connected areas, for which we have shown that these areas correlate with the demarcation caused by an ischaemic stroke segmented in postoperative CT datasets. Finally, a semiparametric regression model has been developed for intraoperative neural activity monitoring of the somatosensory cortex by somatosensory evoked potentials. These results were correlated with neural activity of optical imaging. We found that thermal imaging yields comparable results, yet doesn't share the limitations of optical imaging. In this thesis we would like to emphasize that thermal imaging depicts a novel and valid tool for both intraoperative functional and structural neuroimaging.