In this study, an inertial measurement unit (IMU) sensor module and software algorithm were developed to identify anomalous kicks that should not be given scores in Taekwondo competitions. The IMU sensor module was manufactured with dimensions of 3 cm × 3 cm × 1.5 cm and consists of a high-g sensor for high acceleration measurement, a 9-DOF sensor, and a Wi-Fi module for wireless communication. In the experiment, anomalous kicks and normal kicks were collected by the IMU sensor module, and an AI model was trained. The anomalous kick determination accuracy of the trained AI model was found to be 97.5%. In addition, in order to check whether the strength of a blow can be distinguished using the IMU sensor module, an impact test was performed with a pendulum under the same test conditions as the impact sensor installed in the impact test setup, and the correlation coefficient was 0.99. This study is expected to contribute to improving scoring reliability by suggesting the possibility of discriminating anomalous kicks, which were difficult to judge in Taekwondo competitions, through the analysis of Taekwondo kicks using inertial data and impulses.
Keywords: IMU sensor; Taekwondo; accelerometer; anomalous kick; artificial intelligence; impact.