Stop-and-Go Adaptive Cruise Control (ACC+) is an extension of Adaptive Cruise Control (ACC) that works at low speed as well as normal highway speeds to regulate the speed of the vehicle relative to the vehicle it is following. In this thesis, we design an ACC+ controller for a scale model electric vehicle that ensures the robust performance of the system under various models of uncertainty. We capture the operation of the hybrid system via a state-chart model that performs mode switching between different digital controllers with additional decision logic to guarantee the collision freedom of the system under normal operation. We apply different controller design methods such as Linear Quadratic Regulator (LQR) and H-infinity and perform multiple simulation runs in MATLAB/Simulink to validate the performance of the proposed designs. We compare the practicality of our design with existing formally verified ACC designs from the literature. The comparisons show that the other formally verified designs exhibit unacceptable behaviour in the form of mode thrashing that produces excessive acceleration and deceleration of the vehicle. While simulations provide some assurance of safe operation of the system design, they do not guarantee system safety under all possible cases. To increase confidence in the system, we use Differential Dynamic Logic (dL) to formally state environmental assumptions and prove safety goals, including collision freedom. The verification is done in two stages. First, we identify the invariant required to ensure the safe operation of the system and we formally verify that the invariant preserves the safety property of any system with similar dynamics. This procedure provides a high level abstraction of a class of safe solutions for ACC+ system designs. Second, we show that our ACC+ system design is a refinement of the abstract model. The safety of the closed loop ACC+ system is proven by verifying bounds on the system variables using the KeYmaera verification tool for hybrid systems. The thesis demonstrates how practical ACC+ controller designs optimized for fuel economy, passenger comfort, etc., can be verified by showing that they are a refinement of the abstract high level design. / Thesis / Master of Applied Science (MASc)

Wireless sensor networks (WSNs) have become pivotal in precision agriculture, environmental monitoring, and smart healthcare applications. However, the challenges of energy consumption and security, particularly concerning the reliance on large battery-operated nodes, pose significant hurdles for these networks. Energy-harvesting wireless sensor networks (EH-WSNs) emerged as a solution, enabling nodes to replenish energy from the environment remotely. Yet, the transition to EH-WSNs brought forth new obstacles in ensuring reliable and secure data transmission. In our initial study, we tackled the intermittent connectivity issue prevalent in EH-WSNs due to the dynamic behavior of energy harvesting nodes. Rapid shifts between ON and OFF states led to frequent changes in network topology, causing reduced link stability. To counter this, we introduced the hybrid routing method (HRM), amalgamating grid-based and opportunistic-based routing. HRM incorporated a packet fragmentation mechanism and cooperative localization for both static and mobile networks. Simulation results demonstrated HRM's superior performance, enhancing key metrics such as throughput, packet delivery ratio, and energy consumption in comparison to existing energy-aware adaptive opportunistic routing approaches. Our second research focused on countering emerging threats, particularly the malicious energy attack (MEA), which remotely powers specific nodes to manipulate routing paths. We developed intelligent energy attack methods utilizing Q-learning and Policy Gradient techniques. These methods enhanced attacking capabilities across diverse network settings without requiring internal network information. Simulation results showcased the efficacy of our intelligent methods in diverting traffic loads through compromised nodes, highlighting their superiority over traditional approaches. In our third study, we developed a deep learning-based two-stage framework to detect MEAs. Utilizing a stacked residual network (SR-Net) for global classification and a stacked LSTM network (SL-Net) to pinpoint specific compromised nodes, our approach demonstrated high detection accuracy. By deploying trained models as defenses, our method outperformed traditional threshold filtering techniques, emphasizing its accuracy in detecting MEAs and securing EH-WSNs. In summary, our research significantly advances the reliability and security of EH-WSN, particularly focusing on enhancing the network layer. These findings offer promising avenues for securing the future of wireless sensor technologies.

<p dir="ltr">Autonomous vehicles have gained substantial traction as the future of transportation, necessitating continuous research and innovation. While 2D object detection and instance segmentation methods have made significant strides, 3D object detection offers unparalleled precision. Deep neural network-based 3D object detection, coupled with sensor fusion, has become indispensable for self-driving vehicles, enabling a comprehensive grasp of the spatial geometry of physical objects. In our study of a Lidar-based 3D object detection network using point clouds, we propose a novel architectural model based on You Only Look Once (YOLO) framework. This innovative model combines the efficiency and accuracy of the YOLOv8 network, a swift 2D standard object detector, and a state-of-the-art model, with the real-time 3D object detection capability of the Complex YOLO model. By integrating the YOLOv8 model as the backbone network and employing the Euler Region Proposal (ERP) method, our approach achieves rapid inference speeds, surpassing other object detection models while upholding high accuracy standards. Our experiments, conducted on the KITTI dataset, demonstrate the superior efficiency of our new architectural model. It outperforms its predecessors, showcasing its prowess in advancing the field of 3D object detection in autonomous vehicles.</p>

Eingebettet in die Theorie der Weiterbildung nimmt die Dissertation die Forderung der bildungstheoretisch orientierten Biographieforschung auf, den transformatorischen Bildungsbegriff zu präzisieren. Aus der Diagnose einer Stagnation in diesem Bereich wird der Wechsel vom interpretativen zum relationalen Paradigma vorgeschlagen und eine relationale Entwicklungslogik als methodologische Basis relationalen Denkens eingeführt. Mit der Übertragung der Ergebnisse der informellen Axiomatisierung von Robert Kegans strukturaler Entwicklungstheorie auf den Bildungsbegriff wird unter Verwendung weiterer Referenztheorien aus dem Bereich der relationalen Kommunikationstheorien die Präzisierung des Begriffs möglich. Bildung wird als Prozess der Transformation der Regel der Bedeutungsbildung einer Person unter Konfrontation mit der Regel der Bedeutungsbildung nächsthöherer Ordnung definiert und als eine Struktur der Übergänge zwischen Kontext-Regeln beschrieben, die ein Beobachter der Person im Interaktionsprozess zuschreibt. Mit dem hier entwickelten Kontext-Ebenen-Modell der Bedeutungsbildung lassen sich zum einen Zeichen-Arten ZA definieren, die eine empirische Beschreibung des Bildungsprozesses einer Person zulassen, und zum anderen drei Typen von Kontext-Regeln XR bestimmen, die aus der relationalen Entwicklungslogik abgeleitet, die Prinzipien der Bedeutungsbildung als Regeln der Zeichenrelationierung darstellen. Das Kontext-Ebenen-Modell der Bedeutungsbildung steht als Ergebnis einerseits für eine erfolgreiche Präzisierung des transformatorischen Bildungsbegriffs, andererseits für die Leistungsfähigkeit der strukturalistischen Methode im Rahmen des Programms der relationalen Weiterbildungsforschung. / Embedded in the theory of adult education (andragogy) this PhD-thesis takes up the challenge proclaimed by the biography research based on the concept of Bildung and seeks to define the concept of transformational Bildung more precisely. To overcome the identified stagnation in this research field, this thesis proposes a change from qualitative research paradigm to relational paradigm and introduces the relational logic of development as methodology of relational thinking. The application of the results of the informal axiomatization of Robert Kegan’s theory of human development to the concept of transformational Bildung as well as the use of various approaches based on relational communication theories allowed to provide a more precise definition of the concept of transformational Bildung. In this thesis Bildung is defined as a process of transformation of individual’s rules of meaning making caused by a person’s confrontation with the rules of meaning making of a higher order. From the observer’s perspective the structure of the Bildung process can be described as a transition from one context rule to another. The developed model of context levels of meaning making allows defining types of signs (ZA) that enable to measure the levels in the process of Bildung. Furthermore, this model allows determining three types of context rules (XR), which – according to the relational logic of development – represent principles of meaning making seen as rules for relating signs. Thus, on the one hand, the model of context levels of meaning making has succeeded to specify the concept of transformational Bildung and, on the other hand, has proven the effectiveness of the structuralist method for the relational adult education research.

Im Rahmen eines Dissertationsvorhabens am Albrecht Daniel Thaer-Institut für Agrar- und Gartenbauwissenschaften der Humboldt-Universität zu Berlin wurde die „Entwicklung beruflicher Handlungskompetenz in der gärtnerischen Berufsausbildung durch die Anwendung des Lernfeldkonzepts“ untersucht und in einem pädagogischen Unterrichtsexperiment an gartenbaulichen Berufsschulen in sechs Bundesländern durchgeführt. Damit eine durchgängige Kompetenz- und Outcome-Orientierung Berücksichtigung finden kann, erweiterte der Autor die Untersuchung zur Kompetenzentwicklung um die Aspekte Kompetenzmessung und Kompetenzbewertung. Basierend auf einer Arbeitsprozessanalyse zum Ausbildungsberuf Gärtner der Fachrichtung Garten- und Landschaftsbau wurden im Dialog mit dem Berufsstand Kriterien und Indikatoren beruflicher Handlungskompetenz von Landschaftsgärtnern definiert sowie berufliche Handlungsfelder (Tätigkeitsfelder) gebildet, aus denen Lernfelder abgeleitet und ein lernfeldstrukturierten Rahmenlehrplan für den berufsbezogenen Unterricht der Berufsschule konzipiert werden konnte. So war es möglich, handlungs- und kompetenzorientierte Lernaufgaben für den Berufsschulunterricht zu entwickeln, die sich an berufstypischen Arbeitssituationen orientieren. Durch die Bearbeitung dieser Lernaufgaben wurden bei den Versuchspersonen didaktisch begründete Lernhandlungen ausgelöst und angestrebte Kompetenzen entwickelt, die mittels eines standardisierten Bewertungsbogens durch Beobachtung (Fremdeinschätzung) und Befragung (Selbsteinschätzung) gemessen werden konnten. Die Bewertung ausgeprägter Kompetenzen erfolgte durch den Einsatz eines outcome-orientierten Abschlusstests „Virtuelle Kleinbaustelle“. Diese schriftliche Mehrfach-Situations-Aufgabe wurde nach Maßgabe eines systematischen Bewertungsrahmens unter Berücksichtigung der Anschlussfähigkeit an DQR und EQR ausgewertet, sodass auf den Erwerb beruflicher Handlungskompetenz in der Ausbildung zum Landschaftsgärtner geschlossen werden kann. / Within a PhD project at the Albrecht Daniel Thaer-Institute for Agricultural and Horticultural Sciences at Humboldt-Universität zu Berlin the “development of vocational action competencies regarding the training of gardeners based on the application of the concept of domains of learning” was studied in a teaching experiment at six horticultural vocational schools in six German states. To allow for a consistent focus on competencies and outcome, aspects of competencies measurement and competencies evaluation were included in the study of competency development. Based on an analysis of work processes in occupational training of landscape gardeners, criteria and indicators of vocational action competencies in this field were defined in collaboration with the gardening profession; furthermore, vocational fields of activities were developed. On their basis “domains of learning” (“Lernfelder”) could be derived and accordingly a framework curriculum could be developed for vocational lessons at vocational schools. In this manner it was possible to develop activity- and competence oriented learning tasks for lessons at vocational schools. These learning tasks focus on typical work situations in landscape gardening. When the test persons performed these learning tasks, didactically meaningful learning activities were initiated and the test persons developed the desired competencies. These competencies were measured by means of a standardized evaluation form by observation (external evaluation) and questioning (self-evaluation). The evaluation of profound competencies was carried out using an outcome-oriented final examination tool “small virtual building site”. This written multi-situation task was evaluated according to a systematic evaluation frame under consideration of compatibility with GQF and EQF, so that conclusions can be drawn regarding the acquisition of vocational action competencies during the training for landscape gardener.

This research study focuses on the application models of Data Mining and Machine Learning covering cellular network traffic, in the objective to arm Mobile Network Operators with full view of performance branches (Services, Device, Subscribers). The purpose is to optimize and minimize the time to detect service and subscriber patterns behaviour. Different data mining techniques and predictive algorithms have been applied on real cellular network datasets to uncover different data usage patterns using specific Key Performance Indicators (KPIs) and Key Quality Indicators (KQI). The following tools will be used to develop the concept: RStudio for Machine Learning and process visualization, Apache Spark, SparkSQL for data and big data processing and clicData for service Visualization. Two use cases have been studied during this research. In the first study, the process of Data and predictive Analytics are fully applied in the field of Telecommunications to efficiently address users’ experience, in the goal of increasing customer loyalty and decreasing churn or customer attrition. Using real cellular network transactions, prediction analytics are used to predict customers who are likely to churn, which can result in revenue loss. Prediction algorithms and models including Classification Tree, Random Forest, Neural Networks and Gradient boosting have been used with an exploratory Data Analysis, determining relationship between predicting variables. The data is segmented in to two, a training set to train the model and a testing set to test the model. The evaluation of the best performing model is based on the prediction accuracy, sensitivity, specificity and the Confusion Matrix on the test set. The second use case analyses Service Quality Management using modern data mining techniques and the advantages of in-memory big data processing with Apache Spark and SparkSQL to save cost on tool investment; thus, a low-cost Service Quality Management model is proposed and analyzed. With increase in Smart phone adoption, access to mobile internet services, applications such as streaming, interactive chats require a certain service level to ensure customer satisfaction. As a result, an SQM framework is developed with Service Quality Index (SQI) and Key Performance Index (KPI). The research concludes with recommendations and future studies around modern technology applications in Telecommunications including Internet of Things (IoT), Cloud and recommender systems. / Cellular networks have evolved and are still evolving, from traditional GSM (Global System for Mobile Communication) Circuit switched which only supported voice services and extremely low data rate, to LTE all Packet networks accommodating high speed data used for various service applications such as video streaming, video conferencing, heavy torrent download; and for say in a near future the roll-out of the Fifth generation (5G) cellular networks, intended to support complex technologies such as IoT (Internet of Things), High Definition video streaming and projected to cater massive amount of data. With high demand on network services and easy access to mobile phones, billions of transactions are performed by subscribers. The transactions appear in the form of SMSs, Handovers, voice calls, web browsing activities, video and audio streaming, heavy downloads and uploads. Nevertheless, the stormy growth in data traffic and the high requirements of new services introduce bigger challenges to Mobile Network Operators (NMOs) in analysing the big data traffic flowing in the network. Therefore, Quality of Service (QoS) and Quality of Experience (QoE) turn in to a challenge. Inefficiency in mining, analysing data and applying predictive intelligence on network traffic can produce high rate of unhappy customers or subscribers, loss on revenue and negative services’ perspective. Researchers and Service Providers are investing in Data mining, Machine Learning and AI (Artificial Intelligence) methods to manage services and experience. This research study focuses on the application models of Data Mining and Machine Learning covering network traffic, in the objective to arm Mobile Network Operators with full view of performance branches (Services, Device, Subscribers). The purpose is to optimize and minimize the time to detect service and subscriber patterns behaviour. Different data mining techniques and predictive algorithms will be applied on cellular network datasets to uncover different data usage patterns using specific Key Performance Indicators (KPIs) and Key Quality Indicators (KQI). The following tools will be used to develop the concept: R-Studio for Machine Learning, Apache Spark, SparkSQL for data processing and clicData for Visualization. / Electrical and Mining Engineering / M. Tech (Electrical Engineering)

The amount of data available and consumed by people globally is growing. To reduce mental fatigue and increase the general ability to gain insight into complex texts or documents, we have developed an application to aid in this task. The application allows users to upload documents and ask domain-specific questions about them using our web application. A summarized version of each document is presented to the user, which could further facilitate their understanding of the document and guide them towards what types of questions could be relevant to ask. Our application allows users flexibility with the types of documents that can be processed, it is publicly available, stores no user data, and uses state-of-the-art models for its summaries and answers. The result is an application that yields near human-level intuition for answering questions in certain isolated cases, such as Wikipedia and news articles, as well as some scientific texts. The application shows a decrease in reliability and its prediction as to the complexity of the subject, the number of words in the document, and grammatical inconsistency in the questions increases. These are all aspects that can be improved further if used in production. / Mängden data som är tillgänglig och konsumeras av människor växer globalt. För att minska den mentala trötthet och öka den allmänna förmågan att få insikt i komplexa, massiva texter eller dokument, har vi utvecklat en applikation för att bistå i de uppgifterna. Applikationen tillåter användare att ladda upp dokument och fråga kontextspecifika frågor via vår webbapplikation. En sammanfattad version av varje dokument presenteras till användaren, vilket kan ytterligare förenkla förståelsen av ett dokument och vägleda dem mot vad som kan vara relevanta frågor att ställa. Vår applikation ger användare möjligheten att behandla olika typer av dokument, är tillgänglig för alla, sparar ingen personlig data, och använder de senaste modellerna inom språkbehandling för dess sammanfattningar och svar. Resultatet är en applikation som når en nära mänsklig intuition för vissa domäner och frågor, som exempelvis Wikipedia- och nyhetsartiklar, samt viss vetensaplig text. Noterade undantag för tillämpningen härrör från ämnets komplexitet, grammatiska korrekthet för frågorna och dokumentets längd. Dessa är områden som kan förbättras ytterligare om den används i produktionen.

In this thesis, the robustness of deep learning techniques in the field of visual odometry is investigated, with a specific focus on the impact of motion blur. A comparative study is conducted, evaluating the performance of state-of-the-art deep convolutional neural network methods, namely DF-VO and DytanVO, against ORB-SLAM3, a well-established non-deep-learning technique for visual simultaneous localization and mapping. The objective is to quantitatively assess the performance of these models as a function of motion blur. The evaluation is carried out on a custom synthetic dataset, which simulates a camera navigating through a forest environment. The dataset includes trajectories with varying degrees of motion blur, caused by camera translation, and optionally, pitch and yaw rotational noise. The results demonstrate that deep learning-based methods maintained robust performance despite the challenging conditions presented in the test data, while excessive blur lead to tracking failures in the geometric model. This suggests that the ability of deep neural network architectures to automatically learn hierarchical feature representations and capture complex, abstract features may enhance the robustness of deep learning-based visual odometry techniques in challenging conditions, compared to their geometric counterparts.

This thesis addresses the challenge of denoising microscopy images captured under low-light conditionswith varying intensity levels. The study compares three deep learning models — N2V, CARE, andRCAN — against the collaborative filter BM4D, which serves as a reference point. The models weretrained on two distinct datasets: Endoplasmic Reticulum and Mitochondria datasets, both acquired witha lattice light-sheet microscope.Results show that BM4D maintains stable performance metrics and delivers superior visual quality,when compared to the noisy input. In contrast, the deep learning models exhibit poor performance onnoisy test images when trained on datasets with non-uniform noise levels. Additionally, a sensitivitycomparison of neural parameter between the same models was made. Revealing that supervised modelsare data-specific to some extent, whereas the self-supervised N2V demonstrates consistent neuralparameters, suggesting lower data specificity. / Denna uppsats tar upp problemet med att reducera brus i mikroskopibilder tagna under svagaljusförhållanden med varierande intensitetsnivåer. Studien jämför tre djupinlärningsmodeller – N2V,CARE och RCAN – mot det kollaborativa filtret BM4D, vilket agerar som en referenspunkt.Modellerna tränades på två olika dataset: Endoplasmic Reticulum och Mitochondria, båda tagna meden selektiv planbelysningsmikroskop (lattice light-sheet microscope).Resultaten visar att BM4D behåller stabila prestationsmått och levererar bättre visuell kvalitet, jämförtmed den brusiga input. Däremot visar djupinlärningsmodellerna bristande prestanda på brusigatestbilder när de tränats på data med icke-enhetliga brusnivåer. Dessutom gjordes enkänslighetsjämförelse av neurala parametrar mellan samma modeller. Detta visade att de övervakademodellerna är specifika för data i viss utsträckning, medan den självövervakade N2V-modellen visarlika neurala parametrar, vilket tyder på lägre dataspecificitet

Many, if not all people have online social accounts (OSAs) on an online community (OC) such as Facebook (Meta), Twitter (X), Instagram (Meta), Mastodon, Nostr. OCs enable quick and easy interaction with friends, family, and even online communities to share information about. There is also a dark side to Ocs, where users with malicious intent join OC platforms with the purpose of criminal activities such as spreading fake news/information, cyberbullying, propaganda, phishing, stealing, and unjust enrichment. These criminal activities are especially concerning when harming minors. Detection and mitigation are needed to protect and help OCs and stop these criminals from harming others. Many solutions exist; however, they are typically focused on a single category of malicious intent detection rather than an all-encompassing solution. To answer this challenge, we propose the first steps of a framework for analyzing and identifying malicious intent in OCs that we refer to as malicious mntent detection framework (MIDF). MIDF is an extensible proof-of-concept that uses machine learning techniques to enable detection and mitigation. The framework will first be used to detect malicious users using solely relationships and then can be leveraged to create a suite of malicious intent vector detection models, including phishing, propaganda, scams, cyberbullying, racism, spam, and bots for open-source online social networks, such as Mastodon, and Nostr.