Your browser doesn't support javascript.
loading
Prediction of sports talent in young throwers using machine learning / Predicción del talento deportivo en jóvenes lanzadores utilizando machine learning
Fernández, E; Izquierdo, J. M; Zarauz, A; Redondo, J. C.
Affiliation
  • Fernández, E; University of León. Degree in Physical Activity and Sports Sciences. Spain
  • Izquierdo, J. M; University of León. Department of Physical Education and Sports. Physical Activity and Sport Sciences. Spain
  • Zarauz, A; University of Almeria. Mathematics. Spain
  • Redondo, J. C; University of León. Department of Physical Education and Sports. Physical Activity and Sport Sciences. Spain
Rev. int. med. cienc. act. fis. deporte ; 23(93): 185-199, nov.- dec. 2023. tab, graf
Article in En | IBECS | ID: ibc-230004
Responsible library: ES1.1
Localization: ES15.1 - BNCS
ABSTRACT
The objective of this study is to detect any performance factors in athletics throws between 1997 and 2015 in 662 throwers (15.67 ± 1.01 years of the National Program for Sports Technification of the Royal Spanish Athletics Federation using Machine Learning methods by means of algorithms (Logistic Regression, Random Forest and XG Boost). When examining the importance of the variables with reference to performance, the triple jump (0.20) stands out over the rest of the variables: backward overhead shot throw (0.14), arm span (0.11), vertical jump (0.10), body mass (0.20), height (0.07) and flexibility (0.03). In each discipline the triple jump takes the lead in shot put (0.20), discus (0.21) and hammer (0.29) throws, while backward overhead shot throw does in javelin, the variables rearranging themselves in a particular way depending on the discipline. These findings enable the early detection of potential talents as well as their subsequent sport specialization (AU)
RESUMEN
El estudio aborda la detección de factores de rendimiento en los lanzamientos atléticos utilizando técnicas de Machine Learning, en 662 lanzadores (15,67 ± 1,01 años) del Programa Nacional de Tecnificación Deportiva de la Real Federación Española de Atletismo entre 1997 y 2015, mediante diferentes algoritmos (Logistic Regression, Random Forest y XGBoost). Al medir la importancia de las variables en función del rendimiento, el triple salto (0,20) destaca sobre el resto de variables: lanzamiento dorsal (0,14), envergadura (0,11), salto vertical (0,10), masa corporal, estatura (0,07) y flexibilidad (0,03). En cada disciplina, el triple salto encabeza la importancia en los lanzamientos de peso (0,20), disco (0,21) y martillo (0,29), mientras que el lanzamiento dorsal lo hace en la jabalina (0,20). Las variables se reordenande forma particular modificando su importancia para cada disciplina. Estos hallazgos permiten mejorar la detección inicial de posibles talentos, así como su posterior especialización deportiva (AU)
Subject(s)
Key words

Full text: 1 Collection: 06-national / ES Database: IBECS Main subject: Aptitude / Athletic Performance / Athletes / Machine Learning / Youth Sports Limits: Adolescent / Female / Humans / Male Language: En Journal: Rev. int. med. cienc. act. fis. deporte Year: 2023 Document type: Article

Full text: 1 Collection: 06-national / ES Database: IBECS Main subject: Aptitude / Athletic Performance / Athletes / Machine Learning / Youth Sports Limits: Adolescent / Female / Humans / Male Language: En Journal: Rev. int. med. cienc. act. fis. deporte Year: 2023 Document type: Article