Predicting ratings of perceived exertion in youth soccer using decision tree models
The purpose of this study was to determine the effectiveness of white-box decision tree models (DTM) for predicting the rating of perceived exertion (RPE). The second aim was to examine the relationship between RPE and external measures of intensity in youth soccer training at the group and individu...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Termedia Publishing House
2021-04-01
|
| Series: | Biology of Sport |
| Subjects: | |
| Online Access: | https://www.termedia.pl/Predicting-ratings-of-perceived-exertion-in-youth-soccer-using-decision-tree-models,78,43328,1,1.html |
| _version_ | 1817983844310056960 |
|---|---|
| author | Jakub Marynowicz Mateusz Lango Damian Horna Karol Kikut Marcin Andrzejewski |
| author_facet | Jakub Marynowicz Mateusz Lango Damian Horna Karol Kikut Marcin Andrzejewski |
| author_sort | Jakub Marynowicz |
| collection | DOAJ |
| description | The purpose of this study was to determine the effectiveness of white-box decision tree models (DTM) for predicting the rating of perceived exertion (RPE). The second aim was to examine the relationship between RPE and external measures of intensity in youth soccer training at the group and individual level. Training load data from 18 youth soccer players were collected during an in-season competition period. A total of 804 training observations were undertaken, with a total of 43 ± 17 sessions per player (range 12–76). External measures of intensity were determined using a 10 Hz GPS and included total distance (TD, m/min), high-speed running distance (HSR, m/min), PlayerLoad (PL, n/min), impacts (n/min), distance in acceleration/ deceleration (TD ACC/TD DEC, m/min) and the number of accelerations/decelerations (ACC/DEC, n/min). Data were analysed with decision tree models. Global and individualized models were constructed. Aggregated importance revealed HSR as the strongest predictor of RPE with relative importance of 0.61. HSR was the most important factor in predicting RPE for half of the players. The prediction error (root mean square error [RMSE] 0.755 ± 0.014) for the individualized models waslowercompared to the population model (RMSE 1.621 ± 0.001). The findings demonstrate that individual models should be used for the assessment of players’ response to external load. Furthermore, the study demonstrates that DTM provide straightforward interpretation, with the possibility of visualization. This method can be used to prescribe daily training loads on the basis of predicted, desired player responses (exertion). |
| first_indexed | 2024-04-13T23:37:52Z |
| format | Article |
| id | doaj.art-369c3a64e3b746b481f4a9b1b83a74e1 |
| institution | Directory Open Access Journal |
| issn | 0860-021X 2083-1862 |
| language | English |
| last_indexed | 2024-04-13T23:37:52Z |
| publishDate | 2021-04-01 |
| publisher | Termedia Publishing House |
| record_format | Article |
| series | Biology of Sport |
| spelling | doaj.art-369c3a64e3b746b481f4a9b1b83a74e12022-12-22T02:24:38ZengTermedia Publishing HouseBiology of Sport0860-021X2083-18622021-04-0139224525210.5114/biolsport.2022.10372343328Predicting ratings of perceived exertion in youth soccer using decision tree modelsJakub MarynowiczMateusz LangoDamian HornaKarol KikutMarcin AndrzejewskiThe purpose of this study was to determine the effectiveness of white-box decision tree models (DTM) for predicting the rating of perceived exertion (RPE). The second aim was to examine the relationship between RPE and external measures of intensity in youth soccer training at the group and individual level. Training load data from 18 youth soccer players were collected during an in-season competition period. A total of 804 training observations were undertaken, with a total of 43 ± 17 sessions per player (range 12–76). External measures of intensity were determined using a 10 Hz GPS and included total distance (TD, m/min), high-speed running distance (HSR, m/min), PlayerLoad (PL, n/min), impacts (n/min), distance in acceleration/ deceleration (TD ACC/TD DEC, m/min) and the number of accelerations/decelerations (ACC/DEC, n/min). Data were analysed with decision tree models. Global and individualized models were constructed. Aggregated importance revealed HSR as the strongest predictor of RPE with relative importance of 0.61. HSR was the most important factor in predicting RPE for half of the players. The prediction error (root mean square error [RMSE] 0.755 ± 0.014) for the individualized models waslowercompared to the population model (RMSE 1.621 ± 0.001). The findings demonstrate that individual models should be used for the assessment of players’ response to external load. Furthermore, the study demonstrates that DTM provide straightforward interpretation, with the possibility of visualization. This method can be used to prescribe daily training loads on the basis of predicted, desired player responses (exertion).https://www.termedia.pl/Predicting-ratings-of-perceived-exertion-in-youth-soccer-using-decision-tree-models,78,43328,1,1.htmltraining load gps rpe training monitoring fatigue team sport |
| spellingShingle | Jakub Marynowicz Mateusz Lango Damian Horna Karol Kikut Marcin Andrzejewski Predicting ratings of perceived exertion in youth soccer using decision tree models Biology of Sport training load gps rpe training monitoring fatigue team sport |
| title | Predicting ratings of perceived exertion in youth soccer using decision tree models |
| title_full | Predicting ratings of perceived exertion in youth soccer using decision tree models |
| title_fullStr | Predicting ratings of perceived exertion in youth soccer using decision tree models |
| title_full_unstemmed | Predicting ratings of perceived exertion in youth soccer using decision tree models |
| title_short | Predicting ratings of perceived exertion in youth soccer using decision tree models |
| title_sort | predicting ratings of perceived exertion in youth soccer using decision tree models |
| topic | training load gps rpe training monitoring fatigue team sport |
| url | https://www.termedia.pl/Predicting-ratings-of-perceived-exertion-in-youth-soccer-using-decision-tree-models,78,43328,1,1.html |
| work_keys_str_mv | AT jakubmarynowicz predictingratingsofperceivedexertioninyouthsoccerusingdecisiontreemodels AT mateuszlango predictingratingsofperceivedexertioninyouthsoccerusingdecisiontreemodels AT damianhorna predictingratingsofperceivedexertioninyouthsoccerusingdecisiontreemodels AT karolkikut predictingratingsofperceivedexertioninyouthsoccerusingdecisiontreemodels AT marcinandrzejewski predictingratingsofperceivedexertioninyouthsoccerusingdecisiontreemodels |