Predicting Successful Throwing Technique in Judo from Factors of Kumite Posture Based on a Machine-Learning Approach

Identifying the key points of a movement performed by an expert is required for beginners who want to acquire motor skill. By repeating learning cycle, beginner tries movement, focusing on points. We can find many guiding methods adopting skills in fields coaching and training sports. However, strongly depend experience trainers coaches, need select appropriate different types athletes. Although based objective information obtained from videos sensors applicable individual movements have been proposed order overcome subjectivity these approaches, we cannot apply those that include external factors, such as pushing and/or attacks opponent, seen combat Furthermore, sports require fast feedback analysis athletes factors offensive/defensive techniques at site. Focusing judo throwing techniques, this paper proposes novel real-time prediction method called RT-XSM (Real-Time Extraction Successful Movements) predicts which technique most likely be successful Kumite posture just before throw. The uses logistic regression analyze datasets consisting (a standing when both players grip each other) classification. To validate method, also demonstrates experiments using acquired video scenes World Judo Championships.