Abstract
The use of machine learning (ML) in soccer allows for the management of a large amount of data deriving from the monitoring of sessions and matches. Although the rate of perceived exertion (RPE), training load (S-RPE), and global position system (GPS) are standard methodologies used in team sports to assess the internal and external workload; how the external workload affects RPE and S-RPE remains still unclear. This study explores the relationship between both RPE and S-RPE and the training workload through ML. Data were recorded from 22 elite soccer players, in 160 training sessions and 35 matches during the 2015/2016 season, by using GPS tracking technology. A feature selection process was applied to understand which workload features influence RPE and S-RPE the most. Our results show that the training workloads performed in the previous week have a strong effect on perceived exertion and training load. On the other hand, the analysis of our predictions shows higher accuracy for medium RPE and S-RPE values compared with the extremes. These results provide further evidence of the usefulness of ML as a support to athletic trainers and coaches in understanding the relationship between training load and individual-response in team sports.
Highlights
Monitoring training load is a fundamental process to maximize the physical capacity of athletes and to manage their fatigue throughout the season [1]
The exponential weighted moving average (EWMA) allows for weighting more workloads performed close to the current training session than workloads performed in days long before the current training session
Descriptive statistics of rate of perceived exertion (RPE), S-RPE, and the global position system (GPS) features are provided in Supplementary, Figures
Summary
Monitoring training load is a fundamental process to maximize the physical capacity of athletes and to manage their fatigue throughout the season [1]. The external training load represents the dose performed, while the internal training load reflects the psycho-physiological response of the athlete [2–5]. The game-based nature of team sports can generate inter-individual variation in external training load, resulting in different internal training loads [1,6]. In soccer the number of matches played during the season together with the inter-individual variation related to physical levels, role positions [7,8], and technical and tactical requirements can lead to a training imbalance, leaving some athletes at risk of overtraining and others failing to reach an adequate training stimulus that could potentially enhance the risk of injuries [9,10]. The implementation of monitoring models able to understand which specific training doses should be applied to individual athletes, and which markers of external load influence the athletes’ internal load should be studied [11,12]. Several studies show that the relationship between planned and perceived training load is weak: the training sessions designed
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
