This project explores radar-based sensing as a non-invasive alternative to traditional vital sign monitoring, avoiding the discomfort and disruption of contact-based or wearable devices. Contactless monitoring is valuable across settings such as clinical care, elderly and home monitoring, where continuous observation shouldn’t interfere with movement or comfort. Approaches range from classical signal filtering to deep learning, applied to extract heart rate, respiration, movement, and other physiological signals from radar data. Goals vary accordingly: some efforts target detection and classification of normal versus pathological breathing for conditions like sleep apnea or COPD, while others focus on activity recognition or long-term monitoring. The shared aim is robust, accurate, contactless vital sign monitoring across diverse real-world applications.
We always have open topics for various types of projects/theses in our research area. The scope can be defined individually.
Requirements
- Strong background knowledge in biosignal analysis, machine learning, and deep learning
- Proficiency in Python programming language and familiarity with popular deep learning frameworks (e.g., PyTorch)
- English proficiency and independent working style
Tasks (dependent on project type)
- Reviewing the existing literature
- (Assistance in data collection)
- Data cleaning, filtering and further preprocessing
- Training and evaluation of Deep Learning models
- Application of the model to clinical recordings
- Documentation of the research process and insights in a comprehensive thesis/project report
If you are interested in working with us, please use the application form to apply. We will then get in contact with you.
