Predicting peek readiness-to-train of soccer players using long short-term memory recurrent neural networks
Wiik, Theodor; Johansen, Håvard D.; Pettersen, Svein Arne; Matias Do Vale Baptista, Ivan Andre; Kupka, Tomas; Johansen, Dag; Riegler, Michael; Halvorsen, Pål
Conference object
Accepted version
Permanent lenke
https://hdl.handle.net/10642/8299Utgivelsesdato
2019Metadata
Vis full innførselSamlinger
Originalversjon
Wiik, Johansen HJ, Pettersen SA, Matias Do Vale Baptista IA, Kupka T, Johansen D, Riegler M, Halvorsen P: Predicting peek readiness-to-train of soccer players using long short-term memory recurrent neural networks. In: Gurrin CG, Jónsson BT, Peteri R, Rudinac, Marchand-Maillet S, Quénot, McGuinness, Guðmundsson, Little, Katsurai, Healy G. Proceedings of Content Based Multimedia Information (CBMI 2019), 2019. IEEE conference proceedings https://dx.doi.org/10.1109/cbmi.2019.8877406Sammendrag
We are witnessing the emergence of a myriad of hardware and software systems that quantifies sport and physical activities. These are frequently touted as game changers and important for future sport developments. The vast amount of generated data is often visualized in graphs and dashboards, for use by coaches and other sports professionals to make decisions on training and match strategies. Modern machine-learning methods has the potential to further fuel this process by deriving useful insights that are not easily observable in the raw data streams. This paper tackles the problem of deriving peaks in soccer players' ability to perform from subjective self-reported wellness data collected using the PMSys system. For this, we train a long short-term memory recurrent neural network model using data from two professional Norwegian soccer teams. We show that our model can predict performance peaks in most scenarios with a precision and recall of at least 90%. Equipped with such insight, coaches and trainers can better plan individual and team training sessions, and perhaps avoid over training and injuries.