The classification of limb trajectory data is often cumbersome in research into combat sports. Automatic classification using machine learning techniques has the potential to greatly increase efficiency and reliability of this type of research. We applied supervised classification algorithms on a dataset obtained through a kickboxing experiment and accurately classified over 80% of the strikes.
Beginner and expert kickboxers were asked to strike a boxing bag from several distances, producing a dataset of approximately 4000 strike trajectories. These trajectories were classified using the K-nearest neighbors (KNN) and multi-class linear support vector classification (SVC). We show that both of these algorithms are capable of correctly classifying the limb used for the strike with >99% prediction accuracy. Both algorithms could classify the techniques used with ~88% accuracy. The accuracy of technique classification was improved even further by applying hierarchical classification, classifying techniques separately for each limb. Only 10% of the dataset was required as training set to approach the observed prediction accuracy. Finally, KNN was capable of classifying the strikes by skill level with 82.3% accuracy. These findings demonstrate the potential of using supervised classification on complex limb trajectory datasets in combat sports.
Soekarjo, K.M., Orth, D., Warmerdam, E, & van der Kamp, J. (2018). Automatic classification of strike techniques using limb trajectory data. In U. Brefeld, J. Davis, J. van Haaren, & A. Zimmermann (Eds.), Machine Learning and Data Mining for Sports Analytics: Proceedings of the 5th Workshop on Machine Learning and Data Mining for Sports Analytics co-located with 2018 European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (pp. 137-148). Dublin. [full text]