Running Theses
The goal of this thesis is to investigate and define stakeholder engagement and involvement within the lifecycle of sensor-based MLOps. While MLOps principles streamline the deployment and maintenance of machine learning (ML) models, ensuring proper stakeholder involvement remains a challenge. Different stakeholders must collaborate effectively across various lifecycle stages to ensure model reliability, fairness, and ...
Creating the Digital Nervous System for the Internet of Sustainable Production
AutoML automates machine learning pipelines, making model training accessible without deep expertise. Recent advancements use LLM-based agents to optimize pipeline steps, but existing solutions often require large-scale models with high computational costs. Smaller, open-source models provide a more accessible alternative, especially when combined with domain-specific pre-trained models. However, integrating these models into AutoML via agent ...
Sensor data is often unstructured and while available datasets show some clear use cases, for example calculating energy consumption over time, relationships between measurements can often go unnoticed without a thorough examination of the data. While exploratory data analysis can reveal connections, without a clear analytical direction the results may be limited to general information, ...
With the increasing popularity of personalized tourism experiences, recommendation systems play a crucial role in helping travelers discover destinations, activities, and itineraries that match their preferences. Traditional recommendation models often rely on collaborative filtering or content-based filtering, which may struggle with cold-start issues, lack of contextual awareness, and limited adaptability to dynamic tourism trends.
Knowledge graphs ...
Radiology report generation is a critical task in medical imaging analysis, where accurate and comprehensive descriptions of medical scans (such as X-ray, CT, or MRI) are required for diagnosis and treatment planning. Vision-language models (VLMs) have recently gained attention for automating this process by generating textual reports from medical images. However, standard VLMs often suffer ...
With the increasing complexity of industrial control systems (ICS) in smart grids, the risk of cyber-attacks is also rising. To enhance the security and resilience of these systems, new approaches are needed for detecting and mitigating cyber incidents. This thesis develops a decision support system (DSS) designed to assess and recommend effective countermeasures against cyber ...
We are looking for a highly motivated master’s student to work on an innovative project for their master’s thesis as soon as possible. The project involves investigating existing decentralized oracle networks (DONs) for verifiable credential (VC) verification and evaluating their integration with Self-Sovereign Identity (SSI) infrastructure.
The growing adoption of electric vehicles (EVs) is reshaping power grids by introducing cybersecurity challenges that could be exploited to target both the EV and the power grid. This thesis focuses on vulnerabilities associated with EV charging and the effects of cyberattacks on grid stability and resilience. Of particular interest is the Open Charge Point ...
Exploring the potential of Solid Pods for the cultural sector offers an exciting opportunity to address challenges in data management, privacy, and interoperability. Solid Pods, a technology framework designed to enable individuals to store and control their data, promises transformative applications in the cultural sector. This thesis investigates how Solid Pods can be applied to ...
The aim of this thesis is to evaluate and extend a developing ontology of explainable data principles, an ongoing work aimed at establishing a structured framework for Data Explainability in AI systems. The current version of this ontology is in its early stages, primarily focused on defining key principles of Data Explainability and exploring their ...
The aim of this thesis is to extend the existing latency analysis of a psychomotor feedback engine within our existing MLOps pipeline . Building upon preliminary latency estimations, this thesis will focus on systematically evaluating each processing step in the pipeline, assessing both theoretical and practical contributions to the overall latency and throughput. By ...
This project aims to develop a methodology for the systematic selection and implementation of identifier systems in manufacturing, with a focus on ultrashort-pulsed (UKP) laser systems. By creating a robust identification framework tailored to manufacturing environments, the project will enhance data traceability, interoperability, and reusability within data-driven feedback loops, particularly in highly automated settings. The ...
This master’s thesis builds on the Psychomotor Feedback Engine (PFE) and the IMPECT framework , aiming to improve the graphical user interface that teachers use to implement rules and feedback elements in psychomotor learning.
This thesis aims to address those usability issues by redesigning the teacher interface and integrating the IMPECT framework to ...
Code-Based API Generation and Integration for Graph Analysis Algorithms
This project aims to develop a comprehensive knowledge graph that represents German law documents, including cases and statutes. By creating an ontology tailored to the legal domain and leveraging automated annotation techniques, the project will transform unstructured legal text into structured data that can be queried. This knowledge graph will support legal research, enhance information ...
This thesis investigates the application of federated learning (FL) to the Personal Health Train (PHT) paradigm, exploring how FL can be better adapted to improve privacy-preserving data analysis in healthcare. The research examines how PHT can facilitate secure, distributed machine learning on sensitive medical data across different institutions, while ensuring data privacy and compliance with ...
This research investigates hallucination in vision-language models, focusing on the role of the attention mechanism in contributing to and potentially mitigating hallucinations. The work explores how attention layers influence the integration of visual and textual information and identifies techniques for reducing the generation of inaccurate or irrelevant outputs. A critical research question is understanding how ...
This thesis focuses on designing an Agentic Graph Retrieval-Augmented Generation (RAG) system specifically for question answering in oral maxillofacial surgery (OMS) guidelines. By leveraging graph-based knowledge representation and advanced language models, the system aims to improve accuracy and efficiency in accessing and interpreting surgical guidelines. Key research areas include the integration of graph databases, ontology-based ...
This thesis explores the application of diffusion models for the segmentation of brain tumors in 3D MRI images. By leveraging the robust generative capabilities of diffusion models, the research investigates how these models can accurately identify and segment tumor regions in volumetric MRI data. The study focuses on enhancing tumor detection accuracy and addressing challenges ...
This thesis aims to develop a single-cell-centric biomedical foundation model that leverages the capabilities of generative pre-trained transformers to enhance the analysis of single-cell RNA data. The model will address critical tasks in single-cell biology, such as cell-type annotation, perturbation prediction, identification of pathogenic cells, and gene network inference.
This thesis is co-supervised by Sikander Hayat ...
We are looking for a highly motivated master student to work on an innovative project for their master’s thesis as soon as possible. The project involves the implementation and evaluation of a programmable money approach utilizing verifiable credentials and zero knowledge proofs.
A Natural Language Interface for the Semantic Data Lake system (SEDAR) via LLMs
As universities strive to enhance the effectiveness of their lecture exercises, there arises a need for diverse and realistic test user scenarios to evaluate the understandability and usefulness of educational materials. However, in creating such scenarios a number of challenges arise: Real world students can rarely be used for testing, they are likely inexperienced or ...
