AI-based analysis of athlete time-series data

Interested in sports? Technology used by real athletes? Analysing wellness and training load data is important to avoid injuries and increase performance. Here, the aim is to build a system to automatically analyse and predict outcomes ...
Master

Interested in sports? Technology used by real athletes? We have for a long time researched sports technology for performing performance monitoring for better results and injury avoidance. We developed running systems and tested them on real users. Want to be part of our research group and improve current systems? We are currently collecting a lot of data with respect to training load, wellness and injuries from elite clubs and the entire Norwegian superliga. This system uses a mobile app and servers in the cloud for storage and processing. This gives large opportunities to make systems to automatically analyze these data to see if we can improve how athletes train, avoid overuse injuries or how to select the best athletes for a competition.

We have for example started to look at machine learning approaches to give predictions, presenting the data and processing results to the trainers/coaches, how to add data from external equipment and physical tests, and system related aspects to improve performance and secure the users’ privacy. However, there are a lot of open questions and issues to address. Do you want to be a part of this? Contact us, and let’s see if we can find a thesis topic that matches your interests!

We collaborate with the leagues and elite clubs in Norway, Denmark and Portugal, the future female football center in Tromsø, the football associations, Forzasys (system provider) and several international partners.

Goal

Build a machine learning based analysis component for wellness and training load data.

Learning outcome

  • interdisciplinary research
  • time-series data analysis
  • machine learning / AI
  • data visualization
  • building systems

Qualifications

Hard working, motivated
Some machine learning knowledge would be nice
Interested in learning (the rest can be learned during the thesis work)

Supervisors

  • Pål Halvorsen
  • Michael Riegler

Collaboration partners

ForzaSys AS

References

home.simula.no/~paalh/publications/files/cbmi2019-PMSYS.pdf
forzasys.com/pmSys.html
uit.no/research/ffc

Contact person