The application of unsupervised learning for determining essential physical fitness components in adolescent soccer players

In line with the rapid growth of information technology and sports, analyzing data to obtain useful information has become increasingly challenging. One of the problems faced by the researchers is lack of output variables for actual performance predicton. To this end, this study aims to ascertain th...

Full description

Bibliographic Details
Published in:AIP Conference Proceedings
Main Author: Mat-Rasid S.M.; Abdullah M.R.; Juahir H.; Ismail J.; Rusdiana A.; Musa R.M.; Maliki A.B.H.M.; Kosni N.A.
Format: Conference paper
Language:English
Published: American Institute of Physics 2024
Online Access:https://www.scopus.com/inward/record.uri?eid=2-s2.0-85189287826&doi=10.1063%2f5.0148546&partnerID=40&md5=c499c2251bb68b5a7db2f6f9a692d28f
id 2-s2.0-85189287826
spelling 2-s2.0-85189287826
Mat-Rasid S.M.; Abdullah M.R.; Juahir H.; Ismail J.; Rusdiana A.; Musa R.M.; Maliki A.B.H.M.; Kosni N.A.
The application of unsupervised learning for determining essential physical fitness components in adolescent soccer players
2024
AIP Conference Proceedings
2750
1
10.1063/5.0148546
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85189287826&doi=10.1063%2f5.0148546&partnerID=40&md5=c499c2251bb68b5a7db2f6f9a692d28f
In line with the rapid growth of information technology and sports, analyzing data to obtain useful information has become increasingly challenging. One of the problems faced by the researchers is lack of output variables for actual performance predicton. To this end, this study aims to ascertain the most essential fitness components for adolescent soccer players using unsupervised learning i.e. Principal Component Analysis (PCA). A total of 98 adolescent soccer players with mean and standard deviation age 13.5 ± 0.5 years underwent anthropometric measurement and fitness tests. The initial PCA identifies three components with a higher Eigenvalue (>1). Then, PCA after varimax rotation indicates three components containing three, two, and one varifactors (VF), respectively. The First VF revealed high factor loading on standing height (-0.881), basketball throw (0.864), and predicted VO2max(0.740) recognizes the need for anthropometric, upper body strength, and endurance. The second VF discloses high factor loading on standing broad jump (0.801) and sit and reach (0.849) proves the requirement for explosive power and flexibility in adolescent soccer players. The third VF discloses high factor loading on the 30-meter run representing high variability in speed among the studied group. The current study has successfully identified the most contributed physical fitness variables in the productive performance of soccer using unsupervised learning. It could then be postulated that soccer players during adolescence presented significant differences in terms of physique, upper and lower body power, flexibility, and speed. Thus, these findings could be employed by coaches and fitness trainers engaged in soccer training in the context of physical fitness assessment and talent identification. © 2024 Author(s).
American Institute of Physics
0094243X
English
Conference paper

author Mat-Rasid S.M.; Abdullah M.R.; Juahir H.; Ismail J.; Rusdiana A.; Musa R.M.; Maliki A.B.H.M.; Kosni N.A.
spellingShingle Mat-Rasid S.M.; Abdullah M.R.; Juahir H.; Ismail J.; Rusdiana A.; Musa R.M.; Maliki A.B.H.M.; Kosni N.A.
The application of unsupervised learning for determining essential physical fitness components in adolescent soccer players
author_facet Mat-Rasid S.M.; Abdullah M.R.; Juahir H.; Ismail J.; Rusdiana A.; Musa R.M.; Maliki A.B.H.M.; Kosni N.A.
author_sort Mat-Rasid S.M.; Abdullah M.R.; Juahir H.; Ismail J.; Rusdiana A.; Musa R.M.; Maliki A.B.H.M.; Kosni N.A.
title The application of unsupervised learning for determining essential physical fitness components in adolescent soccer players
title_short The application of unsupervised learning for determining essential physical fitness components in adolescent soccer players
title_full The application of unsupervised learning for determining essential physical fitness components in adolescent soccer players
title_fullStr The application of unsupervised learning for determining essential physical fitness components in adolescent soccer players
title_full_unstemmed The application of unsupervised learning for determining essential physical fitness components in adolescent soccer players
title_sort The application of unsupervised learning for determining essential physical fitness components in adolescent soccer players
publishDate 2024
container_title AIP Conference Proceedings
container_volume 2750
container_issue 1
doi_str_mv 10.1063/5.0148546
url https://www.scopus.com/inward/record.uri?eid=2-s2.0-85189287826&doi=10.1063%2f5.0148546&partnerID=40&md5=c499c2251bb68b5a7db2f6f9a692d28f
description In line with the rapid growth of information technology and sports, analyzing data to obtain useful information has become increasingly challenging. One of the problems faced by the researchers is lack of output variables for actual performance predicton. To this end, this study aims to ascertain the most essential fitness components for adolescent soccer players using unsupervised learning i.e. Principal Component Analysis (PCA). A total of 98 adolescent soccer players with mean and standard deviation age 13.5 ± 0.5 years underwent anthropometric measurement and fitness tests. The initial PCA identifies three components with a higher Eigenvalue (>1). Then, PCA after varimax rotation indicates three components containing three, two, and one varifactors (VF), respectively. The First VF revealed high factor loading on standing height (-0.881), basketball throw (0.864), and predicted VO2max(0.740) recognizes the need for anthropometric, upper body strength, and endurance. The second VF discloses high factor loading on standing broad jump (0.801) and sit and reach (0.849) proves the requirement for explosive power and flexibility in adolescent soccer players. The third VF discloses high factor loading on the 30-meter run representing high variability in speed among the studied group. The current study has successfully identified the most contributed physical fitness variables in the productive performance of soccer using unsupervised learning. It could then be postulated that soccer players during adolescence presented significant differences in terms of physique, upper and lower body power, flexibility, and speed. Thus, these findings could be employed by coaches and fitness trainers engaged in soccer training in the context of physical fitness assessment and talent identification. © 2024 Author(s).
publisher American Institute of Physics
issn 0094243X
language English
format Conference paper
accesstype
record_format scopus
collection Scopus
_version_ 1814778499823566848