Automated Classification of Woodball Swinging Phases from Inertial Measurement Unit Using Least Square Method

Woodball is a rising regular sport that garnered a lot of attention from people with different ages and genders due to its easy playstyles and adaptability to play it almost everywhere. Without any teaching and guides from professional, some of novice players may unconsciously practicing wrong swing postures which is the most important fundamental in woodball. Having a good swing posture helps players to dictate how the mallet swings around the body, promotes good balance and helps the body to turn correctly. In this study, we proposed and verified a simple regression method using a portable, miniature Inertial Measurement Unit (IMU) to classify swing phases to assist the novice players to have a correct swing postures as professional players does. The IMU was attached to the player’s left hand wrist to collect the angle, acceleration and angular velocity of the swing. The signal data were processed using second-order Butterworth filter with cutoff frequency of 10 Hz, estimated using 2nd order Least Square and the swing phases were classified automatically with labels. The proposed system yields high classification performance with average accuracy of 99% for all swing phases.