Background: It has been shown that the longitudinal bending stiffness of shoes influences running and sprinting performance. To maximize performance, this stiffness should not be set to maximum, but rather to an individual level.
While the optimal longitudinal bending stiffness differs between individual athletes, the target can not be linked to a single discrete parameter like athlete height, weight or shoe size.
This project aims to find a prediction of optimal longitudinal bending stiffness for sprinters using machine learning models while taking multiple anthropometrical and dynamic athlete parameters into account.
Tasks:
- Literature review
- Data pre-processing
- Machine learning training
- Model building
Timeline & Goals
The starting time is as soon as possible. The goal of this project is a publication within the intersection of Sport and ML. With the supporting data work, there is the possibility to continue the paper creation process and appear as a co-author.
Requirements:
- Very good knowledge of Python
- Interest in sports, specifically, in running
- Good knowledge of signal processing
- Good knowledge of statistics/evaluation (e.g., correlations)
- Independent working style
If you are interested in working with us, please use the application form to apply. We will then get in contact with you and together, we can identify a suitable topic for you.
Supervisor:
Rebecca Lennartz, M. Sc.
Department Artificial Intelligence in Biomedical Engineering (AIBE)
Lehrstuhl für Maschinelles Lernen und Datenanalytik
- Email: rebecca.lennartz@fau.de