Key point selection and clustering of swimmer coordination through Sparse Fisher-EM

John Komar (1, 2, 3) , Romain Hérault (4, 5, 2, 6) , Ludovic Seifert (1, 2, 3)

1 CETAPS - Centre d’études des transformations des activités physiques et sportives
2 NU - Normandie Université
3 UNIROUEN - Université de Rouen Normandie
4 DocApp - LITIS - Equipe Apprentissage
5 LITIS - Laboratoire d'Informatique, de Traitement de l'Information et des Systèmes
6 INSA Rouen Normandie - Institut national des sciences appliquées Rouen Normandie

To answer the existence of optimal swimmer learning/teaching strategies, this work introduces a two-level clustering in order to analyze temporal dynamics of motor learning in breaststroke swimming. Each level have been performed through Sparse Fisher-EM, a unsupervised framework which can be applied efficiently on large and correlated datasets. The induced sparsity selects key points of the coordination phase without any prior knowledge.

Domains: Statistics [stat]; Machine Learning [stat.ML]

John Komar, Romain Hérault, Ludovic Seifert. Key point selection and clustering of swimmer coordination through Sparse Fisher-EM. ECML/PKDD 2013 Workshop on Machine Learning and Data Mining for Sports Analytics (MLSA2013), Sep 2013, Praha, Czech Republic. ⟨hal-02351767⟩