Using a long short-term memory model to predict force values of Taekwon-do turning based on spatio-temporal parameters

• Autorzy: Mosler Dariusz , Błażkiewicz Michalina , Góra Tomasz , Bednarczuk Grzegorz , Wąsik Jacek

Identyfikatory

DOI

10.37190/ABB-02565-2024-02

• Języki publikacji: EN

Abstrakty

EN

The aim of this study was to investigate the feasibility of using Long Short-Term Memory (LSTM) neural networks to predict Taekwondo kick force from data obtained by inertial measurement unit (IMU) sensors, providing a cost-effective alternative to traditional force plates in sports biomechanics. Methods: IMU (Noraxon Ultium) data from 13 International Taekwon-do Federation (ITF) athletes (9 training, 4 validation) across genders and skill levels (expert in training, expert/advanced in validation) were collected. Sensors were attached to a foot, shank and tight of kicking leg. Athletes performed turning kicks in diverse stances towards a padded force plate (2000 Hz) attached to a wall. LSTM models were trained to predict kick force value, and trained on capturing the IMU data from sensors placed on the lower limb. Results: The trained LSTM models showed accuracy on the training data (R2 values in the range of 0.972–0.978). Feature validity analysis highlighted the importance of ankle dorsiflexion in shaping the model score. Model performance on the validation dataset was less consistent, ranging from good accuracy (RMSE 6.91) to poor accuracy (RMSE over 30), depending on the participant tested. Conclusions: This study demonstrated the potential of LSTM models combined with IMU data to predict Taekwondo kick forces. Although the validation performance indicated the need for further model refinement or the inclusion of additional input variables, the results highlighted the feasibility of predicting force values without relying on a force plate. This approach could enhance the accessibility of field studies conducted outside laboratory settings.

Słowa kluczowe

EN

taekwondo; Inertial Measurement Unit; machine learning; force analysis

• Wydawca: Oficyna Wydawnicza Politechniki Wrocławskiej
• Czasopismo: Acta of Bioengineering and Biomechanics
• Rocznik: 2025
• Tom: Vol. 27, no. 1
• Strony: 83--92
• Opis fizyczny: Bibliogr. 36 poz., rys., tab., wykr.

Twórcy

autor

Mosler Dariusz

• Institute of Physical Culture Sciences, Jan Długosz University in Częstochowa, Częstochowa, Poland.

autor

Błażkiewicz Michalina

• Faculty of Rehabilitation, The Józef Piłsudski University of Physical Education in Warsaw, Warsaw, Poland.

autor

Góra Tomasz

• Institute of Physical Culture Sciences, Jan Długosz University in Częstochowa, Częstochowa, Poland.

autor

Bednarczuk Grzegorz

• Faculty of Rehabilitation, The Józef Piłsudski University of Physical Education in Warsaw, Warsaw, Poland.

autor

Wąsik Jacek

• Institute of Physical Culture Sciences, Jan Długosz University in Częstochowa, Częstochowa, Poland.

Bibliografia

• [1] BARBOSA P., CUNHA P., CARVALHO V., SOARES F., Classification of Taekwondo Techniques using Deep Learning Methods: First Insights, 2021, 201–208.
• [2] BARBOSA P., CUNHA P., CARVALHO V., SOARES F., Deep Learning in Taekwondo Techniques Recognition System: A Preliminary Approach, 2022, 280–291.
• [3] CAMPOS F., BERTUZZI R., DOURADO A., FERREIRA SANTOS V., FRANCHINI E., Energy demands in Taekwondo athletes during combat simulation, European Journal of Applied Physiology, 2011, 1121221-1228.
• [4] CENANOVIC N., KEVRIC J., Mixed Martial Arts Bout Prediction Using Artificial Intelligence, 2022, 452–468.
• [5] Cherifi N., Johnson J., Chin S.-T., Expertise development of elite Taekwondo coaches, Physical Activity Review, 2023, 11131–11145.
• [6] DUKI M., SHAPIEE M., ABDULLAH M.A., MOHD KHAIRUDDIN I., RAZMAN A., P P ABDUL MAJEED A., The Classification of Taekwondo Kicks Via Machine Learning: A feature selection investigation, Mekatronika, 2021, 361–367.
• [7] ESTEVAN I., FALCO C., Mechanical analysis of the roundhouse kick according to height and distance in taekwondo, Biology of Sport, 2013, 30 (4), 275–279.
• [8] ESTEVAN I., FALCO C., SILVERNAIL J.F., JANDACKA D., Comparison of Lower Limb Segments Kinematics in a Taekwondo Kick. An Approach to the Proximal to Distal Motion, J. Hum. Kinet., 2015, 4741–4749.
• [9] FALCO C., ALVAREZ O., CASTILLO I., ESTEVAN I., MARTOS J., MUGARRA F., IRADI A., Influence of the distance in a roundhouse kick’s execution time and impact force in Taekwondo, J. Biomech., 2009, 42 (3), 242–248.
• [10] FALCO C., MOLINA-GARCÍA J., ALVAREZ O., ESTEVAN I., Effects of target distance on select biomechanical parameters in taekwondo roundhouse kick, Sports Biomechanics, 2013, 12 (4), 381–388.
• [11] GÓRA T., MOSLER D., ORTENBURGER D., WĄSIK J., Sex differences in utilizing effective mass among taekwon-do athletes performing turning and side kick, Physical Activity Review, 2024.
• [12] HUI B., Visualization system of martial arts training action based on artificial intelligence algorithm, 2023.
• [13] JAYA I.G.P., DHARMMESTA R.A., RIZAL A., ISTIQOMAH. Application Foot Kick Classification in Taekwondo with Inertia Sensor and Machine Learning, in 2022 IEEE Asia Pacific Conference on Wireless and Mobile (APWiMob). 2022.
• [14] JUNEAU P., BADDOUR N., BURGER H., BAVEC A., LEMAIRE E.D., Comparison of Decision Tree and Long Short-Term Memory Approaches for Automated Foot Strike Detection in Lower Extremity Amputee Populations, Sensors (Basel, Switzerland), 2021, 21 (21).
• [15] KIM J.W., KWON M.S., YENUGA S.S., KWON Y.H., The effects of target distance on pivot hip, trunk, pelvis, and kicking leg kinematics in Taekwondo roundhouse kicks, Sports Biomechanics, 2010, 9 (2), 98–114.92 D. MOSLER et al.
• [16] LANDEO R.A., MCINTOSH A.S., Kinetic and kinematic differences between target and free kicking in taekwondo, 2008. [17] LAPKOVÁ D., ADAMEK M., Using information technologies in self-defense education, 2016, 1–5.
• [18] LENETSKY S., NATES R.J., BRUGHELLI M., HARRIS N.K., Is effective mass in combat sports punching above its weight?, Human Movement Science, 2015, 4089–4097.
• [19] LI C., ZHAO M., ZHAO X., Status Quo and Influence of Martial Arts Fitness in Pursuit of Health Using LSTM Recurrent Neural Network Algorithm, International Journal of Computational Intelligence Systems, 2023, 16 (1), 61.
• [20] LI S., LIU C., YUAN G., Martial Arts Training Prediction Model Based on Big Data and MEMS Sensors, Scientific Programming, 2021, 2021 (1), 9993916.
• [21] LIU Y., KONG J., WANG X., SHAN G., Biomechanical analysis of Yang’s spear turning-stab technique in Chinese martial arts, Physical Activity Review, 2020, 816–822.
• [22] MONTILLA J.A., LATORRE ROMÁN P., SERRANO-HUETE V., LINARES J.C., LOZANO E., JIMÉNEZ P., Differences in the Force-Velocity profile between Judoist and freestyle wrestlers, Physical Activity Review, 2022, 102022.
• [23] MOREIRA P.V., FRANCHINI E., ERVILHA U., GOETHEL M., CARDOZO A., GONÇALVES M., Relationships of the expertise level of taekwondo athletes with electromyographic, kinematic and ground reaction force performance indicators during the dolho chagui kick, Archives of Budo., 2018, 14.
• [24] MOREIRA P.V., PAULA L., VELOSO A., Segmental kick velocity is correlated with kick specific and nonspecific strength performance in a proximodistal sequence, Archives of Budo., 2015, 11271–11283.
• [25] MOREIRA P.V.S., FALCO C., MENEGALDO L.L., GOETHEL M.F., DE PAULA L.V., GONÇALVES M., Are isokinetic leg torques and kick velocity reliable predictors for competitive success in taekwondo athletes?, bioRxiv, 20202020.2006.2019.161158.
• [26] MOREIRA P.V.S., FALCO C., MENEGALDO L.L., GOETHEL M.F., DE PAULA L.V., GONÇALVES M., Are isokinetic leg torques and kick velocity reliable predictors of competitive level in taekwondo athletes?, PLoS One, 2021, 16 (6), e0235582.
• [27] OH Y., CHO Y.-J., Relationship Between Autonomy Support Coaching Perceived by Taekwondo Athletes and Interruption Intention: Mediating Role of Emotional Intelligence, Physical Activity Review, 2023, 1160–1168.
• [28] PAVLOVA I., ZIKRACH D., MOSLER D., ORTENBURGER D., GÓRA T., WĄSIK J., Determinants of anxiety levels among young males in a threat of experiencing military conflict – Applying a machine-learning algorithm in a psychosociological study, PLoS One, 2020, 15 (10), e0239749.
• [29] WAGNER J., SZYMAŃSKI M., BŁAŻKIEWICZ M., KACZMARCZYK K., Methods for Spatiotemporal Analysis of Human Gait Based on Data from Depth Sensors, Sensors, 2023, 23 (3), 1218.
• [30] WĄSIK J., Kinematic analysis of the side kick in Taekwon-do, Acta Bioeng. Biomech., 13 (4), 71–75.
• [31] WĄSIK J., MOSLER D., GÓRA T., ORTENBURGER D., CHALIMONIUK M., LANGFORT J., Kinematic Differences between Traditional and Sport Version of Roundhouse Kick Executed by Male Taekwon-do Masters, Journal of Men’s Health, 2022, 18 (6), 1–7.
• [32] WĄSIK J., MOSLER D., GÓRA T., SCUREK R., Conception of effective mass and effect of force – measurement of taekwondo master, Physical Activity Review, 2023, 1111–1116.
• [33] WĄSIK J., MOSLER D., ORTENBURGER D., GÓRA T., CHOLEWA J., Kinematic Effects of the Target on the Velocity of Taekwon-Do Roundhouse Kicks, J. Hum. Kinet., 2021, 8061–8069.
• [34] XIANG L., GU Y., GAO Z., YU P., SHIM V., WANG A., FERNANDEZ J., Integrating an LSTM framework for predicting ankle joint biomechanics during gait using inertial sensors, Computers in Biology and Medicine, 2024, 170108016.
• [35] YAMANAKA S., SHIMA K., MUTOH A., MORIYAMA K., MATSUI T., INUZUKA N., Evaluation System for Martial Arts Demonstration from Smartphone Sensor Data Using Deep Neural Networks on Noisy Labels, 2023, 1–5.
• [36] ZHOU S., Biomechanical analysis of the danger of the whipleg striking maneuver in martial arts sparring bouts, Applied Mathematics and Nonlinear Sciences, 2024, 9.