Thesis Projects
Information about Diploma/Master thesis process
Open Theses
An evaluation methodology for cyber security on (smart) grid systems
Overhead of security-by-design requirements on current power grid systems
Anomaly detection on encrypted data in industrial control systems
Anomaly detection on encrypted data in industrial control systemsFurther development of a cyber-physical co-simulation environment to investigate the architecture and control of smart grids
Further development of a cyber-physical co-simulation environment to investigate the architecture and control of smart grids
Running Theses
Predict privacy risk score
Mastering the Game of Contract Bridge: Strategy Optimization via Deep Reinforcement Learning and Knowledge Representation and Reasoning
This thesis aims to explore Deep Reinforcement Learning based methods for strategy optimization in the Contract Bridge game, such as Multi-agent Reinforcement Learning, Value-based Learning, and Policy-based Learning, as well as Knowledge Representation and Reasoning based methods such as Multi-agent Epistemic Situation CalculusAdversarial Attacks against Face Detection Systems
Adversarial Attacks against Face Detection SystemsOffloading of IoT Workloads in Peer-to-Peer Networks using WebAssembly
Edge computing offers a framework for offloading the computational effort required by IoT applications.However, privacy issues and cost constraints for cloud infrastructures pose substantial difficulties to IoT service deployment. We wish to look at the possibilities of Peer-to-Peer networks and WebAssembly for IoT task offloading. As a result, a comparison of existing offloading tactics and ...Sensor Based Human Motion Comparison
The aim of this thesis is to build a MLOps-based system to compare the variations in the motions executed while performing various sports-related movements. In essence, we are interested in comparing movements across multiple sensor-suit based recording sessions.
Completed Theses
Improved Bottom-up Deep Learning Approach for Neuronal Cell Instance Segmentation
Improved Bottom-up Deep Learning Approach for Neuronal Cell Instance SegmentationBridging the gap between design and deployment of statistical analyses in Distributed Analytics
Bridging the gap between design and deployment of statistical analyses in Distributed AnalyticsDefense against Data Poisoning Attacks in Federated Learning
Defense against Data Poisoning Attacks in Federated LearningEnhancing the Community Application Editor with Automated Tests & DevOpsUse Bots
Research interest in DevOps bots has increased in recent years, but only a few bots currently support end-user participation in the DevOps approach. Using wireframes and model-driven software development approaches allows end-users to take part in the development process.Development of a metadata model for the storage of data streams in data lakes in the context of industrial production
Development of a metadata model for the storage of data streams in data lakes in the context of industrial production