Open Access

This thesis proposes a multi-label classification approach using the Multimodal Transformer (MulT) [80] to perform multi-modal emotion categorization on a dataset of oral histories archived at the Haus der Geschichte (HdG). Prior uni-modal emotion classification experiments conducted on the novel HdG dataset provided less than satisfactory results. They uncovered issues such as class imbalance, ambiguities in emotion perception between annotators, and lack of representative training data to perform transfer learning [28]. Hence, the objectives of this thesis were to achieve better results by performing a multi-modal fusion and resolving the problems arising from class imbalance and annotator-induced bias in emotion perception. A further objective was to assess the quality of the novel HdG dataset and benchmark the results using SOTA techniques. Through a literature survey on the challenges, models, and datasets related to multi-modal emotion recognition, we created a methodology utilizing the MulT along with a multi-label classification approach. This approach produced a considerable improvement in the overall emotion recognition by obtaining an average AUC of 0.74 and Balanced-accuracy of 0.70 on the HdG dataset, which is comparable to state-of-the-art (SOTA) results on other datasets. In this manner, we were also able to benchmark the novel HdG dataset as well as introduce a novel multi-annotator learning approach to understand each annotator’s relative strengths and weaknesses for emotion perception. Our evaluation results highlight the potential benefits of the novel multi-annotator learning approach in improving overall performance by resolving the problems arising from annotator-induced bias and variation in the perception of emotions. Complementing these results, we performed a further qualitative analysis of the HdG annotations with a psychologist to study the ambiguities found in the annotations. We conclude that the ambiguities in annotations may have resulted from a combination of several socio-psychological factors and systemic issues associated with the process of creating these annotations. As these problems are also present in most multi-modal emotion recognition datasets, we conclude that the domain could benefit from a set of annotation guidelines to create standardized datasets.

This paper presents a novel approach to address noise, vibration, and harshness (NVH) issues in electrically assisted bicycles (e-bikes) caused by the drive unit. By investigating and optimising the structural dynamics during early product development, NVH can decisively be improved and valuable resources can be saved, emphasising its significance for enhancing riding performance. The paper offers a comprehensive analysis of the e-bike drive unit’s mechanical interactions among relevant components, culminating—to the best of our knowledge—in the development of the first high-fidelity model of an entire e-bike drive unit. The proposed model uses the principles of elastic multi body dynamics (eMBD) to elucidate the structural dynamics in dynamic-transient calculations. Comparing power spectra between measured and simulated motion variables validates the chosen model assumptions. The measurements of physical samples utilise accelerometers, contactless laser Doppler vibrometry (LDV) and various test arrangements, which are replicated in simulations and provide accessibility to measure vibrations onto rotating shafts and stationary structures. In summary, this integrated system-level approach can serve as a viable starting point for comprehending and managing the NVH behaviour of e-bikes.

Auf der einen Seite wird audiovisuellen Medien die Möglichkeit zugeschrieben, ein Abbild der Wirklichkeit zu schaffen – ein Grund dafür, dass sie im Journalismus von zentraler Bedeutung sind. Auf der anderen Seite ermöglichen die technologischen Entwicklungen der letzten Jahre immer einfacher, kostengünstiger und schneller authentisch wirkende Manipulationen zu erstellen. Noch vor zehn Jahren war die Manipulation von Videomaterial, abgesehen von trivialen Operationen auf Bildebene, nur im Rahmen von Filmproduktionen möglich. Das ist inzwischen anders – synthetische Medien, auch als Deepfakes bekannt, sind in aller Munde. So stellen audiovisuelle Manipulationen Redaktionen vor eine zunehmend größere Herausforderung und schaffen es mitunter bereits als vermeintlich authentischer Inhalt in die Berichterstattung. Es stellt sich die Frage: Inwiefern ist und bleibt es möglich, die Authentizität audiovisuellen Materials in Redaktionen sicherzustellen? Auf der Grundlage von sieben geführten Experteninterviews mit Akteur:innen aus Wissenschaft und Praxis liefert die Arbeit zusätzlich zu einer aktuellen Beschreibung des technischen Sachstandes in Bezug auf Manipulations- und Verifikationsmöglichkeiten eine Beschreibung und Bewertung der existierenden Probleme und potenzieller Lösungen für Redaktionen, sowie eine Einschätzung der zukünftigen Entwicklung relevanter Technologien und den damit verbundenen Auswirkungen. Im Ergebnis zeigt sich, dass technische Hilfsmittel für Verifikationsprozesse in Redaktionen gebraucht werden, es aber kaum möglich ist, allein auf technologischer Ebene die Authentizität audiovisuellen Materials sicherzustellen. Damit einhergehend seien zurzeit nicht fehlende technische Hilfsmittel die größte Herausforderung für Redaktionen bei der Verifikation, sondern vielmehr der Mangel an Zeit. Interviewt wurden: Dr. Dominique Dresen – Bundesamt für Sicherheit in der Informationstechnik (BSI), Dr. Jutta Jahnel – Karlsruher Institut für Technologie (KIT), Dr. Christian Riess – FAU Erlangen-Nürnberg, Andrea Sauerbier – SPIEGEL, Jochen Spangenberg – u. a. DW Innovation, Johanna Wild – Bellingcat und Dr. Sascha Zmudzinski – Fraunhofer-Institut für Sichere Informationstechnologie (SIT).

The continuously increasing number of biomedical scholarly publications makes it challenging to construct document recommendation algorithms that can efficiently navigate through literature. Such algorithms would help researchers in finding similar, relevant, and related publications that align with their research interests. Natural Language Processing offers various alternatives to compare publications, ranging from entity recognition to document embeddings. In this paper, we present the results of a comparative analysis of vector-based approaches to assess document similarity in the RELISH corpus. We aim to determine the best approach that resembles relevance without the need for further training. Specifically, we employ five different techniques to generate vectors representing the text in the documents. These techniques employ a combination of various Natural Language Processing frameworks such as Word2Vec, Doc2Vec, dictionary-based Named Entity Recognition, and state-of-the-art models based on BERT. To evaluate the document similarity obtained by these approaches, we utilize different evaluation metrics that account for relevance judgment, relevance search, and re-ranking of the relevance search. Our results demonstrate that the most promising approach is an in-house version of document embeddings, starting with word embeddings and using centroids to aggregate them by document.

Recent findings in South Africa have once again underlined the fact that the oldest people in the world obviously came from Africa. Thus, historically, this continent has a very special significance. However, its history in more recent times, especially from the mid-19th century onwards, was strongly influenced by colonisation by European states. Many deep wounds from that time still have an impact on society as a whole today. However, the continent is currently also confronted with a greater number of challenges of a different nature. On the one hand, Africa is trying to strengthen internal cohesion by means of a number of regional organisations and the African Union as a globally active institution; on the other hand, the continent has been marked by political and military conflicts between neighbouring states over the past decades until the recent present. In addition, there are regular internal social upheavals in individual countries due to violent or manipulated political change. Yet the continent could well be on a good development path, since it has a large number of important raw materials - also in comparison to other continents. However, the individual African states - and especially their citizens - often do not benefit from this to an adequate extent. This results in a social imbalance in large parts of the continent (data collection until the end of June 2023), which leads to considerable internal tensions. To make matters worse, Africa is the continent most affected by climate change. A closer look at the partly very different economic, political and social situations of the large continent leads to an overall predominantly critical assessment of Africa's further development, which is explained in more detail in the final chapter with regard to the foreseeable consequences for the continent.

Smart heating systems are one of the core components of smart homes. A large portion of domestic energy consumption is derived from HVAC (heating, ventilation and air conditioning) systems, making them a relevant topic of the efforts to support an energy transition in private housing. For that reason, the technology has attracted attention both from the academic and the industry communities. User interfaces of smart heating systems have evolved from simple adjusting knobs to advanced data visualization interfaces, that allow for more advanced setting such as time tables and status information. With the advent of AI, we are interested in exploring how the interfaces will be evolving to build the connection between user needs and underlying AI system. Hence, this paper is targeted to provide early design implications towards an AI-based user interface for smart heating systems.

When dialogues with voice assistants (VAs) fall apart, users often become confused or even frustrated. To address these issues and related privacy concerns, Amazon recently introduced a feature allowing Alexa users to inquire about why it behaved in a certain way. But how do users perceive this new feature? In this paper, we present preliminary results from research conducted as part of a three-year project involving 33 German households. This project utilized interviews, fieldwork, and co-design workshops to identify common unexpected behaviors of VAs, as well as users’ needs and expectations for explanations. Our findings show that, contrary to its intended purpose, the new feature actually exacerbates user confusion and frustration instead of clarifying Alexa's behavior. We argue that such voice interactions should be characterized as explanatory dialogs that account for VA’s unexpected behavior by providing interpretable information and prompting users to take action to improve their current and future interactions.

The non-filarial and non-communicable disease podoconiosis affects around 4 million people and is characterized by severe leg lymphedema accompanied with painful intermittent acute inflammatory episodes, called acute dermatolymphangioadenitis (ADLA) attacks. Risk factors have been associated with the disease but the mechanisms of pathophysiology remain uncertain. Lymphedema can lead to skin lesions, which can serve as entry points for bacteria that may cause ADLA attacks leading to progression of the lymphedema. However, the microbiome of the skin of affected legs from podoconiosis individuals remains unclear. Thus, we analysed the skin microbiome of podoconiosis legs using next generation sequencing. We revealed a positive correlation between increasing lymphedema severity and non-commensal anaerobic bacteria, especially Anaerococcus provencensis, as well as a negative correlation with the presence of Corynebacterium, a constituent of normal skin flora. Disease symptoms were generally linked to higher microbial diversity and richness, which deviated from the normal composition of the skin. These findings show an association of distinct bacterial taxa with lymphedema stages, highlighting the important role of bacteria for the pathogenesis of podoconiosis and might enable a selection of better treatment regimens to manage ADLA attacks and disease progression.

Eine Überprüfung der Leistungsentwicklung im Radsport geht bis heute mit der Durchführung einer spezifischen Leistungsdiagnostik unter Verwendung vorgegebener Testprotokolle einher. Durch die zwischenzeitlich stark gestiegene Popularität von »wearable devices« ist es gleichzeitig heutzutage sehr einfach, die Herzfrequenz im Alltag und bei sportlichen Aktivitäten aufzuzeichnen. Doch eine geeignete Modellierung der Herzfrequenz, die es ermöglicht, Rückschlüsse über die Leistungsentwicklung ziehen zu können, fehlt bislang. Die Herzfrequenzaufzeichnungen in Kombination mit einer phänomenologisch interpretierbaren Modellierung zu nutzen, um auf möglichst direkte Weise und ohne spezifische Anforderungen an die Trainingsfahrten Rückschlüsse über die Leistungsentwicklung ziehen zu können, bietet die Chance, sowohl im professionellen Radsport wie auch in der ambitionierten Radsportpraxis den Erkenntnisgewinn über die eigene Leistungsentwicklung maßgeblich zu vereinfachen. In der vorliegenden Arbeit wird ein neuartiges und phänomenologisch interpretierbares Modell zur Simulation und Prädiktion der Herzfrequenz beim Radsport vorgestellt und im Rahmen einer empirischen Studie validiert. Dieses Modell ermöglicht es, die Herzfrequenz (sowie andere Beanspruchungsparameter aus Atemgasanalysen) mit adäquater Genauigkeit zu simulieren und bei vorgegebener Wattbelastung zu prognostizieren. Weiterhin wird eine Methode zur Reduktion der Anzahl der kalibrierbaren freien Modellparameter vorgestellt und in zwei empirischen Studien validiert. Nach einer individualisierten Parameterreduktion kann das Modell mit lediglich einem einzigen freien Parameter verwendet werden. Dieser verbleibende freie Parameter bietet schließlich die Möglichkeit, im zeitlichen Verlauf mit dem Verlauf der Leistungsentwicklung verglichen zu werden. In zwei unterschiedlichen Studien zeigt sich, dass der freie Modellparameter grundsätzlich in der Lage zu sein scheint, den Verlauf der Leistungsentwicklung über die Zeit abzubilden.

This thesis investigates the benefit of rubrics for grading short answers using an active learning mechanism. Automating short answer grading using Natural Language Processing (NLP) is one of the active research areas in the education domain. This could save time for the evaluator and invest more time in preparing for the lecture. Most of the research on short answer grading was treated as a similarity task between reference and student answers. However, grading based on reference answers does not account for partial grades and does not provide feedback. Also, the grading is automatic that tries to replace the evaluator. Hence, using rubrics for short answer grading with active learning eliminates the drawbacks mentioned earlier. Initially, the proposed approach is evaluated on the Mohler dataset, popularly used to benchmark the methodology. This phase is used to determine the parameters for the proposed approach. Therefore, the approach with the selected parameter exceeds the performance of current State-Of-The-Art (SOTA) methods resulting in the Pearson correlation value of 0.63 and Root Mean Square Error (RMSE) of 0.85. The proposed approach has surpassed the SOTA methods by almost 4%. Finally, the benchmarked approach is used to grade the short answer based on rubrics instead of reference answers. The proposed approach evaluates short answers from Autonomous Mobile Robot (AMR) dataset to provide scores and feedback (formative assessment) based on the rubrics. The average performance of the dataset results in the Pearson correlation value of 0.61 and RMSE of 0.83. Thus, this research has proven that rubrics-based grading achieves formative assessment without compromising performance. In addition, the rubrics have the advantage of generalizability to all answers.

BSG, Urteil vom 28.06.2022, Az. B 2 U 16/20 R

Wenn von Nachrichtenauswahl und Thematisierungsfunktion der Medien die Rede ist, fällt schnell das Fachwort Agenda-Setting. Der gegenteilige Begriff, das Agenda-Cutting, ist dagegen viel seltener Gegenstand von wissenschaftlichen oder gesellschaftlichen Diskussionen. Dabei ist das Agenda-Cutting eine weitflächig geübte Praxis in Medien, Politik und Gesellschaft, bei der Themen bewusst oder unbewusst aus den gesellschaftlichen Diskursen entfernt oder herausgehalten werden. Die Initiative Nachrichtenaufklärung beschäftigt sich schon lange intensiv mit der Frage der Vernachlässigung von Themen und Nachrichten. Mit diesem Sammelband wird erstmals das Thema wissenschaftlich tiefgehend von verschiedenen Seiten aus betrachtet.