medigraphic.com
ISSN 2992-779X (Electronic)
ISSN 2007-6452 (Print)

2023, Number 3

<< Back Next >>

Investigación en Discapacidad 2023; 9 (3)

Principal components analysis for the identification of sensitive variables in the execution of the motor gesture and the development of an artificial neural network as an auxiliary tool in the classification of sports performance in elite taekwondo athletes from Mexico City

Franco-Sánchez JG, Pegueros-Pérez A, Puig-Hernández HR, Mirabent-Amor D, Figueroa-Cavero F, Vega-Martínez G, Bueyes-Roiz V, Anaya-Campos LE, Velasco-Acosta PJ, Quiñones-Urióstegui I

Language: Spanish
References: 13
Page: 91-101
PDF size: 313.96 Kb.


ABSTRACT

Introduction: sports classification is a daily task in the athlete's life. It is important to relate the results of the tests performed on a taekwondoin with the efficiency of the execution of their fundamental motor gesture, the kick, which represents 80% of the activity in competition. Objective: the aim is to have a tool that allows to identify and classify the most sensitive variables (anthropometric and physiological) and relate them to the sports efficiency of a sample of taekwondo athletes from Mexico City. Material and methods: descriptive cross-sectional study for the analysis of 202 variables gathered from 74 evaluations towards the identification of those with the greatest variability, to stratify the population using principal component analysis and to classify it into four levels of aptitude, using an artificial neural network. Results: athletes characterization, identifying weaknesses and strengths, was performed by the representation of more than 50% of the information contained in 19 parameters that are obtained from the data to represent the study population and limit points with statistical significance. Classification efficiency was 87.5%. Conclusion: the use of technology tools in the analysis of data and classification based on artificial intelligence is a different proposal that seeks to emulate the work done by coaches in the process of classifying athletes.


REFERENCES

  1. Besson T, Macchi R, Rossi J, Morio CYM, Kunimasa Y, Nicol C et al. Sex differences in endurance running. Sports Med. 2022; 52 (6): 1235-1257.

  2. Tharawadeepimuk K, Wongsawat Y. Quantitative EEG in sports: performance level estimation of professional female soccer players. Health Inf Sci Syst. 2021; 9 (1): 14.

  3. Burke LM. Nutritional approaches to counter performance constraints in high-level sports competition. Exp Physiol. 2021; 106 (12): 2304-2323.

  4. McHugh C, Hind K, O'Halloran A, Davey D, Farrell G, Wilson F. Body mass and body composition changes over 7 years in a male professional rugby union team. Int J Sports Med. 2021; 42 (13): 1191-1198.

  5. El-Ashker S, Chaabene H, Prieske O. Maximal isokinetic elbow and knee flexor-extensor strength measures in combat sports athletes: the role of movement velocity and limb side. BMC Sports Sci Med Rehabil. 2022; 14 (1): 40.

  6. Blanco Ortega A, Isidro Godoy J, Szwedowicz Wasik DS, Martínez Rayón E, Cortés García C, Ramón Azcaray Rivera H et al. Biomechanics of the upper limbs: a review in the sports combat ambit highlighting wearable sensors. Sensors (Basel). 2022; 22 (13): 4905.

  7. Zemková E, Zapletalová L. The role of neuromuscular control of postural and core stability in functional movement and athlete performance. Front Physiol. 2022; 13: 796097.

  8. Richter K, Mushett CA, Ferrara MS, McCann C. Integrated classification: a faulted system. Adapt Phys Activ Q. 1992; 9: 5-13.

  9. Bridge CA, Ferreira da Silva Santos J, Chaabene H, Pieter W, Franchini E. Physical and physiological profiles of taekwondo athletes. Sports Med. 2014; 44 (6): 713-733.

  10. Hailong L. Role of artificial intelligence algorithm for taekwondo teaching effect evaluation model. 2021; 40 (2): 3239-3250.

  11. Weian L, Xiaotao L. Application and analysis of taekwondo techniques, tactics, and movement trajectories based on multi-intelligent decision making. Math Probl Eng. 2022; 8411550.

  12. Dharmmesta RA, Jaya IGP, Rizal A, Istiqomah. Classification of foot kicks in taekwondo using SVM (support vector machine) and KNN (K-nearest neighbors) algorithms. 2022 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT). Bali, Indonesia: 2022. pp. 36-41.

  13. Ke Y. Research on the application of artificial intelligence in taekwondo sport. 2021 2nd International Conference on Big Data & Artificial Intelligence & Software Engineering (ICBASE). Zhuhai, China: 2021. pp. 571-574.




2020     |     www.medigraphic.com