Application Foot Kick Classification in Taekwondo with Inertia Sensor and Machine Learning

Taekwondo is a sport that is quite popular in Indonesia. This can be seen from the number of taekwondo competitions held in Indonesia and the many achievements that Indonesia has in the Taekwondo sport. However, the emergence of the Covid-19 pandemic impacted the sport of taekwondo, especially in the implementation of the taekwondo competition. This is because the government limits all crowding activities so that activities are ultimately carried out online. This also applies to taekwondo competitions which are finally held online. Seeing this, a device was made that can classify the types of foot kick movements expected to assist the judges in making judgments when conducting taekwondo competitions. This device can classify foot kick foot and send the classification results using a smartphone so that the results can be seen directly. In this study, we seek for an appropriate feature extraction and machine learning technique to incorporate into the device to build a device that can categorize Taekwondo kicks. It trains several statistical feature extraction and machine learning methods. The best classifier for application is K-Nearest Neighbor for the right foot and Support Vector Machine for the left foot using kurtosis feature extraction. For the right foot, the results of the device testing on subject 1 resulted in an accuracy rate of 88.33%, on subject 2 of 68.33%, and on subject 3 of 73.66%. Meanwhile for the left foot, testing result on subject 1 resulted in an accuracy rate of 81.6%, on subject 2 of 60%, and on subject 3 of 73%. The existence of this device can be an example of implementing the use of human activity recognition in the field of sports.