05 Fakultät Informatik, Elektrotechnik und Informationstechnik
Permanent URI for this collectionhttps://elib.uni-stuttgart.de/handle/11682/6
Browse
6 results
Search Results
Item Open Access Generating random knowledge graphs from rules(2024) Glaser, Gabriel TimonA knowledge graph is a datastructure that is capable of storing knowledge. Besides that, there are several methods that use knowledge graphs to derive more information. These methods need to be validated with example knowledge graphs. However, real data might not be available or not contain desired properties. Thus, there are use cases that benefit from the generation of synthetic knowledge graphs. To define a synthetic knowledge graph, there is the need of a characterization that expresses how the synthetic data should look. In this thesis, I use Horn clauses for this characterization because of their good balance of expressiveness and complexity, their use in the field of rule mining, and their base role in the logical language Datalog. As clauses are usually not represented perfectly in real data, the goal of this thesis is to generate a knowledge graph that does not perfectly fulfil given Horn clauses, but in a desired degree of fulfillment. During the thesis, I developed and implemented two modifiable algorithms to generate knowledge graphs. On the one hand, I adapted the general hill climbing technique to generate knowledge graphs. On the other hand, I implemented a greedy algorithm which orders a given set of Horn clauses using logical subsumptions between their bodies, and then add edges to fulfil one Horn clause after the other, in the computed order. Both algorithms aim to fulfil the goal of this thesis by generating synthetic knowledge graphs according to given Horn clauses, each with a degree of fulfilment. The degree of fulfilment of any Horn clauses is characterized by body support, the number of times the premise of the Horn clauses is fulfilled, and support, the number of times the premise and conclusion of the Horn clauses are fulfilled. Additionally, there is the confidence which is the fraction of support and body support, i.e., the percentage of cases the Horn clause is fulfilled. All code is published such that anyone can try it. During the evaluation, random sets of Horn clauses were produced and the implementations generated corresponding knowledge graphs. Generated knowledge graphs were compared by considering the difference between the expected and the actual degree of fulfilment for each Horn clause. The result is that generation variant hill climbing with the initial state set to the result of the greedy algorithm with rule order based on subsumption yields the best results. Also, the difficulty of generating a good knowledge graph increases along with the overlapping degree of the input set of Horn clauses. Note that the overlapping degree reflects how many relation names occur in how many Horn clauses of the set. Lastly, the state-of-the-art mining tool AMIE found many Horn clauses in the generated graphs which were not intended by the set given to the generator.Item Open Access End-to-End-Gebärdenspracherkennung durch Computer-Sehen(2024) Selim, Ziya CanWeltweit kommunizieren Menschen verbal in verschiedensten Sprachen. Dabei gibt es bereits schon dann Komplikationen, wenn zwei Personen verschiedene Sprachen sprechen. Dennoch gibt es auf der Welt mehrere Millionen Menschen, welche taub oder hörgeschädigt sind[WHO]. Damit sich Hörgeschädigte dennoch verständigen können, wird ein anderer Kommunikationskanal verwendet. Anstatt der gesprochenen Sprache verwendet man mithilfe der Zeichensprache den visuellen Kommunikationskanal. Für die Erleichterung der Kommunikation mit Gehörlosen benötigt man zunächst eine Möglichkeit, Handzeichen erkennen zu können, damit diese im Folgenden übersetzt werden können. Die Erkennung dieser Handzeichen lässt sich durch die Bilderkennung gut lösen. In dieser Arbeit wird erkundet, wie die Bild- und Videoerkennung eine Hilfe sein kann, die Kommunikation mit Hörgeschädigten zu erleichternItem Open Access Enhancing online lecture engagement through gaze and emotion feedback integration(2025) Horn, FrederikThe shift towards online meetings, seminars, and lectures has rapidly gained momentum in recent years, particularly accelerated by the events surrounding the COVID-19 pandemic. However, the absence of nonverbal cues such as eye contact and gestures in virtual settings presents significant challenges for effective communication. Existing frameworks for virtual meetings often fail to adequately address this issue, making it difficult for presenters to accurately assess audience engagement and comprehension. This thesis investigates these challenges by capturing participant attention and emotion in real-time and evaluating how presenters interact with live feedback. Through the implementation and study of a feedback system that visualizes gaze and emotional data, we aimed to bridge the gap between in-person and online lecture experiences. To ensure an informed approach, we conducted a requirement analysis prior to our experiment, identifying key factors for effective feedback integration. In the experiment, we collected data through our tool by logging meeting interactions and analyzing responses from a post-experiment questionnaire. Our findings provide insights into the impact of such feedback on presenter motivation, delivery adjustments, and engagement levels, ultimately contributing to the improvement of educational quality in virtual environments.Item Open Access Stochastic query synthesis for neural PDE solvers(2025) Ullrich, FinnPDEs are highly influential in physics and are describing various phenomena in the world, from wave movement to electro-magnetics. The problem arises when one tries to solve them, which requires enormous computing power for a numerical solution. To overcome the limitiations, neural PDE solvers have been proposed, using neural networks to approximate the solution trajectories. However, neural PDE solvers require training data from an computationally expensive numerical solver. Therefore, Musekamp et al. created a benchmark, which investigates active learning for neural PDE solvers. Active learning can reduce the amount of data required, while keeping the same performance. In this work, we will demonstrate a new strategy of selecting samples called stochastic query synthesis. Following this, we will remove the pool currently used and rather create a Markov chain directly from the input space containing unlabeled instances. The transition probability is based on the unadjusted Langevin algorithm, allowing us to sample by exploiting gradient information. To retrieve a better result, instead of just one chain, we will create multiple parallel chains, and only take the last state as input. We will show that this approach is equally effective as the currently implemented pool-based implementation. However, there are still performance problems that need to be solved in the future, to make it viable in practice.Item Open Access Linear transformers for solving parametric partial differential equations(2024) Hagnberger, JanThe simulation of physical phenomena relies on solving Partial Differential Equations (PDEs), and Machine Learning models have increasingly addressed this task in recent years. PDEs often involve parameters influencing their evolution, prompting the development of models that consider these parameters as additional input. These parameter-conditioned models aim to generalize across different PDE parameters, replacing the need for multiple models trained on specific ones. Transformer models have been achieving great success in Natural Language Processing (NLP), Speech Processing, and even in domains such as Computer Vision. Due to their ability to effectively model long-range dependencies in sequential data, their field of application is steadily increasing. Calculating attention via Scaled Dot-Product Attention in Vanilla Transformers is computationally expensive and scales quadratically with the input length. This leads to a bottleneck for very long sequences. To address this challenge, Linear Transformers have been introduced, substituting the Scaled Dot-Product Attention to achieve linear time and space complexity. Consequently, Linear Transformers have shown promising potential for processing very long sequences efficiently. We investigate two approaches of utilizing Linear Transformers for solving PDEs and their associated problems. Moreover, we conduct a comprehensive comparison between our proposed transformer-based models and state-of-the-art models for solving parametric PDEs. The evaluation criteria include accuracy for short and long rollouts, memory consumption, and inference times. The results demonstrate that our proposed models perform competitively with the current state-of-the-art models, providing an efficient solution for PDE solving.Item Open Access Machine learning-based metabolic rate estimation from wearable sensors(2025) Olschewski, MarieAdaptive devices such as exoskeletons and prostheses can enhance human physical capabilities or replace the functionality of missing body parts. However, adjusting these devices for the specific needs of an individual remains a time-consuming and costly procedure. A key objective in optimizing these devices is minimizing the user’s energy expenditure (EE), a metric closely related to metabolic cost. Traditional methods for estimating metabolic cost, such as indirect calorimetry, are performed in controlled environments, limiting real-world applicability. This study aims to bridge this gap by exploring the use of traditional machine learning (ML) methods to estimate metabolic cost in real-time environments, utilizing wearable sensors integrated into adaptive devices. Using the dataset from Ingraham et al. (2019), which includes data from ten healthy subjects performing various exercises, the study investigates how different sensor combinations impact prediction accuracy. This thesis evaluated multiple ML models, including Random Forest (RF), Support Vector Machines (SVM), Linear Regression (LR), Decision Trees (DT), and Multilayer Perceptrons (MLP), within two cross-validation methods: Leave-One-Subject-Out (LOSO) and Leave-One-Time-Out (LOTO). Key findings from this evaluation include: In the LOSO setting, RF outperformed other models, achieving the lowest RMSE in several sensor regions, including Hexoskin, EMG Pants, and Best Combination, with the ’Best Combination’ region showing the best results. In contrast, MLP performed well in the LOTO setting, with its strongest performance observed in the ’Best Combination’ region. SVM demonstrated robust performance when all sensor data was combined, emphasizing the potential of multimodal sensor fusion. Hyperparameter tuning and sensor feature selection were crucial factors in optimizing model performance, particularly for more complex models like RF and MLP. The results suggest that while traditional ML methods can estimate EE effectively, challenges remain in refining preprocessing techniques, tuning hyperparameters, and optimizing sensor combinations. This thesis outlines the importance of model selection, sensor fusion, and parameter optimization in developing more accurate and real-time energy expenditure prediction systems for wearable technologies.