How can machine learning and AI-supported processes help in elite sports? Which playing strategies are helpful in which situations in beach volleyball? And what are the actual benefits of analysing opponents' so-called "key plays" to prepare for badminton competitions?
The Chair of Performance Analysis and Sports Informatics deals with these and similar questions. As part of the annual application process for research projects of the Munich Data Science Institute (MDSI) and the Federal Institute of Sports Science, Prof. Dr. Daniel Link was successful with funding applications in data sciences, beach volleyball, and badminton.
The joint projects are being carried out with various partner institutions. They are intended to help ensure the competitiveness of German elite sport but also to provide new findings in the field of basic training science research. "We are very pleased that we were successful with our applications," says Prof Link. "This shows the important role that our Department Health and Sport Sciences plays in German elite sport and the Scientific Network for Competitive Sport." The three projects are being funded with a total of around 170,000 euros.
Joint project with the TUM School of Computation, Information and Technology
The MDSI project "Advancing spatiotemporal pattern analysis using top-level sports data (ASPAS)", which is being carried out together with the Data Analytics and Machine Learning Group (Prof. Dr. Stephan Günnemann) at the TUM School of Computation, Information and Technology, aims to develop new AI-supported methods for processing and analyzing spatiotemporal movement data in sport. "Top-class sport is an extremely interesting field of application for data science," says Prof. Link, explaining the cooperation with computer science: "Here, human behaviour can be investigated in a natural, highly competitive situation, but also in a space that is reduced in complexity by the rules."
Playing strategies in beach volleyball
Looking for a direct point win on a serve or would you rather put the ball safely into play? There are many variations in beach volleyball, just when serving. The research project examines the question of when game strategies should be adapted during a competition and whether top athletes recognize these times correctly. "When, for example, the serve strategy should be changed and how much risk should be taken has not yet been scientifically proven, meaning that various subjective beliefs have formed on the part of sports practitioners," explains Steffen Lang, who is supervising the project. The two-year project was initiated together with the German Volleyball Federation and is being carried out in collaboration with the Institute of Psychology at the German Sport University Cologne (Prof. Dr. Dr. Markus Raab).
Scientific support for the national badminton teams
When the Olympic and Paralympic Games begin in Paris in 2024, the German badminton and para-badminton athletes will again compete for the coveted medals. In order to prepare the players in the best possible way, two BISp projects, which are being carried out together with the German Badminton Association and the German Disabled Sports Association, are creating performance profiles of potential opponents. The analysis is based on the paradigm of so-called "keyplays". Project team member Fabian Hammes, Research Associate at the Chair of Performance Analysis and Sports Informatics and former national badminton player, explains: "Keyplays are actions that change the balance in a rally in favour of one player. Analyzing these keyplays makes it possible to identify the strengths and weaknesses of upcoming opponents and thus support competition preparation."
To the homepage of the Chair of Performance Analysis and Sports Informatics
To the homepage of the Munich Data Science Institute
Contact:
Prof. Dr. Daniel Link
Chair of Performance Analysis and Sports Informatics
Munich Data Science Institute
Georg-Brauchle-Ring 60/62
80992 Munich
phone: 089 289 24498
e-Mail: Daniel.Link(at)tum.de
Steffen Lang
Chair of Performance Analysis and Sports Informatics
Georg-Brauchle-Ring 60/62
80992 Munich
phone: 089 289 24503
e-Mail: Steffen.Lang(at)tum.de
Fabian Hammes
Chair of Performance Analysis and Sports Informatics
Georg-Brauchle-Ring 60/62
80992 Munich
phone: 089 289 24503
e-Mail: Fabian.Hammes(at)tum.de
Text: Bastian Daneyko
Photos: RedBull Media House/private