Pose estimation has been studied since the early days of computer vision. The task of object pose estimation is to determine the transformation that maps an object from it's inherent coordinate system into the camera-centric coordinate system. This transformation describes the translation of the object relative to the camera and the orientation of the object in three dimensional space. The knowledge of an object's pose is a key ingredient in many application scenarios like robotic grasping, augmented reality, autonomous navigation and surveillance. A general estimation pipeline consists of the following four steps: extraction of distinctive points, creation of a hypotheses pool, hypothesis verification and, finally, the hypotheses refinement. In this work, we focus on the hypothesis generation process. We show that it is beneficial to utilize geometric knowledge in this process. We address the problem of hypotheses generation of articulated objects. Instead of considering each object part individually we model the object as a kinematic chain. This enables us to use the inner-part relationships when sampling pose hypotheses. Thereby we only need K correspondences for objects consisting of K parts. We show that applying geometric knowledge about part relationships improves estimation accuracy under severe self-occlusion and low quality correspondence predictions. In an extension we employ global reasoning within the hypotheses generation process instead of sampling 6D pose hypotheses locally. We therefore formulate a Conditional-Random-Field operating on the image as a whole inferring those pixels that are consistent with the 6D pose. Within the CRF we use a strong geometric check that is able to assess the quality of correspondence pairs. We show that our global geometric check improves the accuracy of pose estimation under heavy occlusion.

This paper proposes a novel algorithm in pixel-based pattern recognition in design layout which offers simplicity, speed and accuracy to recognize any patterns that later can be used to detect problematic pattern in lithography process so they can be removed or improved earlier in design stage.:Abstract 1 Content 3 List of Figure 6 List of Tables 8 List of Abbreviations 9 Chapter 1: Introduction 10 1.1 Motivation 10 1.2 Related Work 11 1.3 Purpose and Research Question 12 1.4 Approach and Methodology 12 1.5 Scope and Limitation 12 1.6 Target group 13 1.7 Outline 13 Chapter 2: Theoretical Background 14 2.1 Problematic Pattern in Computational Lithography 14 2.2 Optical Proximity Effect 16 2.3 Taxonomy of Pattern Recognition 17 2.3.1 Feature Generation 18 2.3.2 Classifier Model 19 2.3.3 System evaluation 20 2.4 Feature Selection Technique 20 2.4.1 Wrapper-Based Methods 21 2.4.2 Average-Based Methods 22 2.4.3 Binary Geometrical Transformation 24 2.4.3.1 Image Interpolation 24 2.4.3.2 Geometric Transformation 26 2.4.3.2.1 Forward Mapping: 26 2.4.3.2.2 Inverse Mapping: 27 2.4.3.3 Thresholding 27 2.5 Machine Learning Algorithm 28 2.5.1 Linear Classifier 29 2.5.2 Linear Discriminant Analysis (LDA) 30 2.5.3 Maximum likelihood 30 2.6 Scoring (Metrics to Measure Classifier Model Quality) 31 2.6.1 Accuracy 32 2.6.2 Sensitivity 32 2.6.3 Specifity 32 2.6.4 Precision 32 Chapter 3: Method 33 3.1 Problem Formulation 33 3.1.1 T2T Pattern 35 3.1.2 Iso-Dense Pattern 36 3.1.3 Hypothetical Hotspot Pattern 37 3.2 Classification System 38 3.2.1 Wrapper and Average-based 38 3.2.2 Binary Geometric Transformation Based 39 3.3 Window-Based Raster Scan 40 3.3.1 Scanning algorithm 40 3.4 Classifier Design 42 3.4.1 Training Phase 43 3.4.2 Discriminant Coefficient Function 44 3.4.3 SigmaDi 45 3.4.4 Maximum Posterior Probability 45 3.4.5 Classifier Model Block 46 3.5 Weka 3.8 47 3.6 Average-based Influence 49 3.7 BGT Based Model 50 Chapter 4: Results 55 4.1 Wrapper and Average-based LDA classifier 55 4.2 BGT Based LDA with SigmaDi Classifier 56 4.3 Estimation Output 57 4.4 Probability Function 58 Chapter 5: Conclusion 59 5.1 Conclusions 59 5.2 Future Research 60 Bibliography 61 Selbstständigkeitserklärung 63

Spielt Ihr Gehirn Ihre letzten Lebenserfahrungen ab, während Sie sich ausruhen? Eine offene Frage in den Neurowissenschaften ist, welche Ereignisse unser Gehirn wiederholt und gibt es eine Korrelation zwischen der Wiederholung und der Dauer des Ereignisses? In dieser Studie habe ich versucht, dieser Frage nachzugehen, indem ich Magnetenzephalographie-Daten aus einem Experiment zum aktiven Hören verwendet habe. Die Magnetenzephalographie (MEG) ist ein nicht-invasives Neuroimaging-Verfahren, das verwendet wird, um die Gehirnaktivität zu untersuchen und die Gehirndynamik bei Wahrnehmungs- und kognitiven Aufgaben insbesondere in den Bereichen Sprache und Hören zu verstehen. Es zeichnet das in unserem Gehirn erzeugte Magnetfeld auf, um die Gehirnaktivität zu erkennen. Ich baue eine Pipeline für maschinelles Lernen, die einen Teil der Experimentdaten verwendet, um die Klangmuster zu lernen und dann das Vorhandensein von Geräuschen im späteren Teil der Aufnahmen vorhersagt, in denen die Teilnehmer untätig sitzen mussten und kein Ton zugeführt wurde. Das Ziel der Untersuchung der Testwiedergabe von gelernten Klangsequenzen in der Nachhörphase. Ich habe ein Klassifikationsschema verwendet, um Muster zu identifizieren, wenn MEG auf verschiedene Tonsequenzen in der Zeit nach der Aufgabe reagiert. Die Studie kam zu dem Schluss, dass die Lautfolgen über dem theoretischen Zufallsniveau identifiziert und unterschieden werden können und bewies damit die Gültigkeit unseres Klassifikators. Darüber hinaus könnte der Klassifikator die Geräuschsequenzen in der Nachhörzeit mit sehr hoher Wahrscheinlichkeit vorhersagen, aber um die Modellergebnisse über die Nachhörzeit zu validieren, sind mehr Beweise erforderlich. / Does your brain replay your recent life experiences while you are resting? An open question in neuroscience is which events does our brain replay and is there any correlation between the replay and duration of the event? In this study I tried to investigate this question by using Magnetoencephalography data from an active listening experiment. Magnetoencephalography (MEG) is a non-invasive neuroimaging technique used to study the brain activity and understand brain dynamics in perception and cognitive tasks particularly in the fields of speech and hearing. It records the magnetic field generated in our brains to detect the brain activity. I build a machine learning pipeline which uses part of the experiment data to learn the sound patterns and then predicts the presence of sound in the later part of the recordings in which the participants were made to sit idle and no sound was fed. The aim of the study of test replay of learned sound sequences in the post listening period. I have used classification scheme to identify patterns if MEG responses to different sound sequences in the post task period. The study concluded that the sound sequences can be identified and distinguished above theoretical chance level and hence proved the validity of our classifier. Further, the classifier could predict the sound sequences in the post-listening period with very high probability but in order to validate the model results on post listening period, more evidence is needed.

In a world with an ever-increasing amount of data processed, providing tools for highquality and fast data processing is imperative. Database Management Systems (DBMSs) are complex adaptive systems supplying reliable and fast data analysis and storage capabilities. To boost the usability of DBMSs even further, a core research area of databases is performance optimization, especially for query processing. With the successful application of Artificial Intelligence (AI) and Machine Learning (ML) in other research areas, the question arises in the database community if ML can also be beneficial for better data processing in DBMSs. This question has spawned various works successfully replacing DBMS components with ML models. However, these global models have four common drawbacks due to their large, complex, and inflexible one-size-fits-all structures. These drawbacks are the high complexity of model architectures, the lower prediction quality, the slow training, and the slow forward passes. All these drawbacks stem from the core expectation to solve a certain problem with one large model at once. The full potential of ML models as DBMS components cannot be reached with a global model because the model’s complexity is outmatched by the problem’s complexity. Therefore, we present a novel general strategy for using ML models to solve data management problems and to replace DBMS components. The novel strategy is based on four advantages derived from the four disadvantages of global learning strategies. In essence, our local learning strategy utilizes divide-and-conquer to place less complex but more expressive models specializing in sub-problems of a data management problem. It splits the problem space into less complex parts that can be solved with lightweight models. This circumvents the one-size-fits-all characteristics and drawbacks of global models. We will show that this approach and the lesser complexity of the specialized local models lead to better problem-solving qualities and DBMS performance. The local learning strategy is applied and evaluated in three crucial use cases to replace DBMS components with ML models. These are cardinality estimation, query optimizer hinting, and integer algorithm selection. In all three applications, the benefits of the local learning strategy are demonstrated and compared to related work. We also generalize the strategy’s usability for a broader application and formulate best practices with instructions for others.

Unmanned aerial vehicles have developed rapidly in recent years due to technological advances. UAV technology can be applied to a wide range of applications in surveillance, rescue, agriculture and transport. The problems that can exist in these areas can be mitigated by combining clusters of drones with several technologies. For example, when a swarm of drones is under attack, it may not be able to obtain the position feedback provided by the Global Positioning System (GPS). This poses a new challenge for the UAV swarm to fulfill a specific mission. This thesis intends to use as few sensors as possible on the UAVs and to design the smallest possible information transfer between the UAVs to maintain the shape of the UAV formation in flight and to follow a predetermined trajectory. This thesis presents Extended Kalman Filter methods to navigate autonomously in a GPS-denied environment. The UAV formation control and distributed communication methods are also discussed and given in detail.

Die Komplexität des Forschungsmanagements an Universitäten und Hochschulen für Angewandte Wissenschaften hat in den letzten Jahren zugenommen, sowohl auf Seiten der Wissenschaftler als auch auf administrativer Ebene. Insbesondere die Texterstellung und -verarbeitung für Forschungsanträge, Publikationen und andere wissenschaftliche Dokumente erfordern erheblichen Aufwand. Gleichzeitig existieren Methoden und Technologien in den Bereichen Information Retrieval, Maschinelles Lernen und Semantischer Technologien, die für die Analyse und Bewertung dieser Texte geeignet sind. Diese Arbeit zielt darauf ab, Aufwände im Lebenszyklus von öffentlich geförderten Forschungsprojekten zu optimieren. Sie identifiziert aktuelle Entwicklungen und Technologien, um Kriterien für eine Gesamtarchitektur abzuleiten, die wissenschaftliche Texte qualitativ annotiert, trainiert und evaluiert. Das resultierende Framework namens FELIX dient als prototypisches System für die computergestützte Assistenz zur Evaluation wissenschaftlicher Texte. Datenkorpora aus Forschungsanträgen und Publikationen wurden für explorative Experimente verwendet, die u. a. auf Methoden des Maschinellen Lernens basieren. FELIX ermöglicht die Analyse von Texten und Metadaten, die Klassifizierung nach definierten Kriterien und die Vorhersage der Bewilligung von Forschungsanträgen. Die Konzeption und Evaluierung von FELIX führte zu wissenschaftlichen und praktischen Implikationen zur Optimierung des Forschungsmanagements.:1. MOTIVATION 2. THEORETISCHE FUNDIERUNG DES DIGITALEN FORSCHUNGSMANAGEMENTS 3. TECHNOLOGISCHE METHODEN UND STRATEGIEN 4. KONZEPTION EINER SYSTEMARCHITEKTUR 5. EXPLORATIVE STUDIE ZUR COMPUTERGESTÜTZTEN ASSISTENZ ZUR EVALUATION WISSENSCHAFTLICHER TEXTE 6. ZUSAMMENFASSUNG UND AUSBLICK ANHANG

In recent years, researchers have recognized relational tables on the Web as an important source of information. To assist this research we developed the Dresden Web Tables Corpus (DWTC), a collection of about 125 million data tables extracted from the Common Crawl (CC) which contains 3.6 billion web pages and is 266TB in size. As the vast majority of HTML tables are used for layout purposes and only a small share contains genuine tables with different surface forms, accurate table detection is essential for building a large-scale Web table corpus. Furthermore, correctly recognizing the table structure (e.g. horizontal listings, matrices) is important in order to understand the role of each table cell, distinguishing between label and data cells. In this paper, we present an extensive table layout classification that enables us to identify the main layout categories of Web tables with very high precision. We therefore identify and develop a plethora of table features, different feature selection techniques and several classification algorithms. We evaluate the effectiveness of the selected features and compare the performance of various state-of-the-art classification algorithms. Finally, the winning approach is employed to classify millions of tables resulting in the Dresden Web Table Corpus (DWTC).

Data completeness is one of the most important data quality dimensions and an essential premise in data analytics. With new emerging Big Data trends such as the data lake concept, which provides a low cost data preparation repository instead of moving curated data into a data warehouse, the problem of data completeness is additionally reinforced. While traditionally the process of filling in missing values is addressed by the data imputation community using statistical techniques, we complement these approaches by using external data sources from the data lake or even the Web to lookup missing values. In this paper we propose a novel hybrid data imputation strategy that, takes into account the characteristics of an incomplete dataset and based on that chooses the best imputation approach, i.e. either a statistical approach such as regression analysis or a Web-based lookup or a combination of both. We formalize and implement both imputation approaches, including a Web table retrieval and matching system and evaluate them extensively using a corpus with 125M Web tables. We show that applying statistical techniques in conjunction with external data sources will lead to a imputation system which is robust, accurate, and has high coverage at the same time.

The automotive industry is continuously innovating and adapting new technologies. Along with that, the companies work towards maintaining the quality of a hardware product and meeting the customer demands. Before delivering the product to the customer, it is essential to test and approve it for the safe use. The concept remains the same when it comes to a software. Adapting modern technologies will further improve the efficiency of testing a software. The thesis aims to build a machine learning algorithm for the implementation during the software testing. In general, the evaluation of a generated test report after the testing consumes more time. The built algorithm should be able to reduce the time spent and the manual effort during the evaluation. Basically, the machine learning algorithms will analyze and learn the data available in the old test reports. Based on the learnt data pattern, it will suggest the possible root causes for the failed test cases in the future. The thesis report has the literature survey that helped in understanding the machine learning concepts in different industries for similar problems. The tasks involved while building the model are data loading, data pre-processing, selecting the best conditions for each algorithm and comparison of the performance among them. It also suggest the possible future work towards improving the performance of the models. The entire work is implemented in Jupyter notebook using pandas and scikit-learn libraries.

Depth sensing is pivotal in robotics; however, monocular depth estimation encounters significant challenges. Existing algorithms relying on large-scale labeled data and large Deep Convolutional Neural Networks (DCNNs) hinder real-world applications. We propose two lightweight architectures that achieve commendable accuracy rates of 91.2% and 90.1%, simultaneously reducing the Root Mean Square Error (RMSE) of depth to 4.815 and 5.036. Our lightweight depth model operates at 29-44 FPS on the Jetson Nano GPU, showcasing efficient performance with minimal power consumption. Moreover, we introduce a mask network designed to visualize and analyze the compact depth network, aiding in discerning informative samples for the active learning approach. This contributes to increased model accuracy and enhanced generalization capabilities. Furthermore, our methodology encompasses the introduction of an active learning framework strategically designed to enhance model performance and accuracy by efficiently utilizing limited labeled training data. This novel framework outperforms previous studies by achieving commendable results with only 18.3% utilization of the KITTI Odometry dataset. This performance reflects a skillful balance between computational efficiency and accuracy, tailored for low-cost devices while reducing data training requirements.:1. Introduction 2. Literature Review 3. AI Technologies for Edge Computing 4. Monocular Depth Estimation Methodology 5. Implementation 6. Result and Evaluation 7. Conclusion and Future Scope Appendix