Predictive modelling of the physical demands during training and competition in professional soccer players

Giménez, J. V., Jiménez-Linares, L., Leicht, A. S., and Gómez, M. A. (2020) Predictive modelling of the physical demands during training and competition in professional soccer players. Journal of Science and Medicine in Sport, 23 (6). pp. 603-608.

[img] PDF (Published version) - Published Version
Restricted to Repository staff only

View at Publisher Website: https://doi.org/10.1016/j.jsams.2019.12....
 
8
1


Abstract

Objectives: The present study aimed to predict the cut-off point-values that best differentiate the physical demands of training and competition tasks including friendly matches (FM), small sided games (SSG), large sided games (LSG), mini-goal games (MG) and ball circuit-training (CT) in professional soccer players.

Design: Experimental randomized controlled trial.

Methods: Fourteen professional players participated in all tasks with the CT, SSG and MG consisting of 8 repetitions of 4-min game play, interspersed by 2-min of active recovery. The training data were compared to the first 32-min of the LSG and two competitive FM per player. All movement patterns from walking to sprint running were recorded using 10 Hz GPS devices while player perception of exertion was recorded via a visual analogue scale, post-task. Decision tree induction was applied to the dataset to assess the cut-off point-values from four training drills (SSG, LSG, MG, and CT) and FM for every parameter combination.

Results: Distance covered during jogging (2.3-3.3m/s; >436m), number of decelerations (<= 730.5) and accelerations (<= 663), and maximum velocity reached (>5.48 m/s) characterized the physical demands during competition (FM) with great variability amongst training drills.

Conclusion: The use of these novel, cut-off points may aid coaches in the design and use of training drills to accurately prepare athletes for soccer competition. (C) 2019 Published by Elsevier Ltd on behalf of Sports Medicine Australia.

Item ID: 63415
Item Type: Article (Research - C1)
ISSN: 1878-1861
Keywords: GPS technology, Artificial intelligence, Decision tree, Performance assessment, Football
Copyright Information: © 2019 Published by Elsevier Ltd on behalf of Sports Medicine Australia.
Funders: Ministry of Education, Culture and Sport of Spain, James Cook University
Date Deposited: 10 Jun 2020 07:30
FoR Codes: 42 HEALTH SCIENCES > 4207 Sports science and exercise > 420799 Sports science and exercise not elsewhere classified @ 100%
SEO Codes: 97 EXPANDING KNOWLEDGE > 970111 Expanding Knowledge in the Medical and Health Sciences @ 100%
Downloads: Total: 1
More Statistics

Actions (Repository Staff Only)

Item Control Page Item Control Page