Join Fraunhofer-Gesellschaft as a student researcher in Locomotion Mode Classification. You will develop a machine learning model based on acceleration sensor data to extend the application range of knee force estimation models. The goal is to create an integrated classification and model pipeline for personalized healthcare recommendations.
What You'll Do
- Identify and define relevant locomotion modes in the context of knee load.
- Develop a machine learning model for the classification of time series data.
- Integrate the classification into a load-specific model selection or adaptive extension of an existing regression model.
- Validate and evaluate the model regarding accuracy, robustness, and real-time capability.
- Investigate how the results can be used to derive personalized recommendations for action.
What We're Looking For
- Valid enrollment at a German university or college.
- Studies in computer science, biomechanics, medical technology, or a comparable degree program.
- Experience in the field of Machine Learning, ideally with Deep Learning for time series data.
- Good programming skills in Python, preferably with frameworks like TensorFlow or PyTorch.
- Interest in data-driven modeling with direct application relevance in patient-centered healthcare.
Technical Stack
- Python
- TensorFlow
- PyTorch
- Deep Learning
- Time Series Data
Team & Environment
You will collaborate in an interdisciplinary team from movement analysis, simulation, control, and data-driven modeling.
Benefits & Compensation
- Exciting research environment at the intersection of computer science, biomechanics, and medical technology.
- Collaboration in an interdisciplinary team.
- Practice-oriented research with clear application relevance in patient-centered healthcare.
- Professional supervision with weekly feedback meetings and support for scientific publication.
We value and promote the diversity of our employees' skills and welcome all applications—regardless of age, gender, nationality, ethnic and social origin, religion, worldview, disability, sexual orientation and identity. Severely disabled persons will be given preferential consideration if equally qualified.
