Application of an Artificial Neural Network to Automate the Measurement of Kinematic Characteristics of Punches in Boxing

This work aimed to study the automation of measuring speed punches boxers during shadow boxing using inertial measurement units (IMUs) based on an artificial neural network (ANN). In boxing, for effective development athlete, constant control punch is required. However, even when modern means kinematic parameters, it necessary record circumstances under which was performed: The type (jab, cross, hook, or uppercut) and activity (shadow single punch, series punches). Therefore, eliminate errors accelerate process, that is, automate measurements, use ANN in form a multilayer perceptron (MLP) proposed. During experiments, IMUs were installed boxers’ wrists. input parameters absolute acceleration angular velocity. experiment conducted three groups with different levels training. developed model showed high level recognition all groups, can be concluded significantly accelerates collection data kinetic characteristics allows this process automated.