Search Results

You are looking at 1 - 5 of 5 items for

  • Author: Arne Jaspers x
Clear All Modify Search
Restricted access

Peter Catteeuw, Bart Gilis, Arne Jaspers, Johan Wagemans and Werner Helsen

This study investigates the effect of two off-field training formats to improve offside decision making. One group trained with video simulations and another with computer animations. Feedback after every offside situation allowed assistant referees to compensate for the consequences of the flash-lag effect and to improve their decision-making accuracy. First, response accuracy improved and flag errors decreased for both training groups implying that training interventions with feedback taught assistant referees to better deal with the flash-lag effect. Second, the results demonstrated no effect of format, although assistant referees rated video simulations higher for fidelity than computer animations. This implies that a cognitive correction to a perceptual effect can be learned also when the format does not correspond closely with the original perceptual situation. Off-field offside decision-making training should be considered as part of training because it is a considerable help to gain more experience and to improve overall decision-making performance.

Restricted access

Matthew C. Varley, Arne Jaspers, Werner F. Helsen and James J. Malone


Sprints and accelerations are popular performance indicators in applied sport. The methods used to define these efforts using athlete-tracking technology could affect the number of efforts reported. This study aimed to determine the influence of different techniques and settings for detecting high-intensity efforts using global positioning system (GPS) data.


Velocity and acceleration data from a professional soccer match were recorded via 10-Hz GPS. Velocity data were filtered using either a median or an exponential filter. Acceleration data were derived from velocity data over a 0.2-s time interval (with and without an exponential filter applied) and a 0.3-second time interval. High-speed-running (≥4.17 m/s2), sprint (≥7.00 m/s2), and acceleration (≥2.78 m/s2) efforts were then identified using minimum-effort durations (0.1–0.9 s) to assess differences in the total number of efforts reported.


Different velocity-filtering methods resulted in small to moderate differences (effect size [ES] 0.28–1.09) in the number of high-speed-running and sprint efforts detected when minimum duration was <0.5 s and small to very large differences (ES –5.69 to 0.26) in the number of accelerations when minimum duration was <0.7 s. There was an exponential decline in the number of all efforts as minimum duration increased, regardless of filtering method, with the largest declines in acceleration efforts.


Filtering techniques and minimum durations substantially affect the number of high-speed-running, sprint, and acceleration efforts detected with GPS. Changes to how high-intensity efforts are defined affect reported data. Therefore, consistency in data processing is advised.

Restricted access

James J. Malone, Arne Jaspers, Werner Helsen, Brenda Merks, Wouter G.P. Frencken and Michel S. Brink

The purpose of this investigation was to (1) quantify the training load practices of a professional soccer goalkeeper and (2) investigate the relationship between the training load observed and the subsequent self-reported wellness response. One male goalkeeper playing for a team in the top league of the Netherlands participated in this case study. Training load data were collected across a full season using a global positioning system device and session-RPE (rating of perceived exertion). Data were assessed in relation to the number of days to a match (MD− and MD+). In addition, self-reported wellness response was assessed using a questionnaire. Duration, total distance, average speed, PlayerLoad™, and load (derived from session-RPE) were highest on MD. The lowest values for duration, total distance, and PlayerLoad™ were observed on MD−1 and MD+1. Total wellness scores were highest on MD and MD−3 and were lowest on MD+1 and MD−4. Small to moderate correlations between training load measures (duration, total distance covered, high deceleration efforts, and load) and the self-reported wellness response scores were found. This exploratory case study provides novel data about the physical load undertaken by a goalkeeper during 1 competitive season. The data suggest that there are small to moderate relationships between training load indicators and self-reported wellness response. This weak relation indicates that the association is not meaningful. This may be due to the lack of position-specific training load parameters that practitioners can currently measure in the applied context.

Restricted access

Tim Op De Beéck, Arne Jaspers, Michel S. Brink, Wouter G.P. Frencken, Filip Staes, Jesse J. Davis and Werner F. Helsen

Purpose: The influence of preceding load and future perceived wellness of professional soccer players is unexamined. This paper simultaneously evaluates the external load (EL) and internal load (IL) for different time frames in combination with presession wellness to predict future perceived wellness using machine learning techniques. Methods: Training and match data were collected from a professional soccer team. The EL was measured using global positioning system technology and accelerometry. The IL was obtained using the rating of perceived exertion multiplied by duration. Predictive models were constructed using gradient-boosted regression trees (GBRT) and one naive baseline method. The individual predictions of future wellness items (ie, fatigue, sleep quality, general muscle soreness, stress levels, and mood) were based on a set of EL and IL indicators in combination with presession wellness. The EL and IL were computed for acute and cumulative time frames. The GBRT model’s performance on predicting the reported future wellness was compared with the naive baseline’s performance by means of absolute prediction error and effect size. Results: The GBRT model outperformed the baseline for the wellness items such as fatigue, general muscle soreness, stress levels, and mood. In addition, only the combination of EL, IL, and presession perceived wellness resulted in nontrivial effects for predicting future wellness. Including the cumulative load did not improve the predictive performances. Conclusions: The findings may indicate the importance of including both acute load and presession perceived wellness in a broad monitoring approach in professional soccer.

Restricted access

Arne Jaspers, Tim Op De Beéck, Michel S. Brink, Wouter G.P. Frencken, Filip Staes, Jesse J. Davis and Werner F. Helsen

Purpose: Machine learning may contribute to understanding the relationship between the external load and internal load in professional soccer. Therefore, the relationship between external load indicators (ELIs) and the rating of perceived exertion (RPE) was examined using machine learning techniques on a group and individual level. Methods: Training data were collected from 38 professional soccer players over 2 seasons. The external load was measured using global positioning system technology and accelerometry. The internal load was obtained using the RPE. Predictive models were constructed using 2 machine learning techniques, artificial neural networks and least absolute shrinkage and selection operator (LASSO) models, and 1 naive baseline method. The predictions were based on a large set of ELIs. Using each technique, 1 group model involving all players and 1 individual model for each player were constructed. These models’ performance on predicting the reported RPE values for future training sessions was compared with the naive baseline’s performance. Results: Both the artificial neural network and LASSO models outperformed the baseline. In addition, the LASSO model made more accurate predictions for the RPE than did the artificial neural network model. Furthermore, decelerations were identified as important ELIs. Regardless of the applied machine learning technique, the group models resulted in equivalent or better predictions for the reported RPE values than the individual models. Conclusions: Machine learning techniques may have added value in predicting RPE for future sessions to optimize training design and evaluation. These techniques may also be used in conjunction with expert knowledge to select key ELIs for load monitoring.