The impact of different training load quantification and modelling methodologies on performance predictions in elite swimmers

Lachlan Jg Mitchell, Ben Rattray, John Fowlie, Philo U Saunders, David B Pyne

Research output: Contribution to journalArticle

Abstract

The use of rolling averages to analyse training data has been debated recently. We evaluated two training load quantification methods (five-zone, seven-zone) fitted to performances over two race distances (50 m and 100 m) using four separate longitudinal models (Banister, Busso. rolling averages and exponentially weighted rolling averages) for three swimmers ranked in the top 8 in the world. A total of 1610 daily load measures and 108 performances were collected. Banister (standard error of the estimate (SEE) 0.64 s & 0.62 s; five-zone & seven-zone quantification methods), Busso (SEE 0.73 s & 0.70) and exponentially weighted rolling averages (SEE 0.57 s & 0.63 s) models fitted more accurately (p < 0.001) than the rolling averages approach (SEE 1.32 s and 1.36 s). The seven-zone quantification method did not produce more accurate performance predictions than the five-zone method, despite being a more detailed form of training load quantification. Four neural network models were fitted and had lower error (SEE 0.38, 0.41, 0.35 and 0.60 s) than all longitudinal models but did not track as predictably over time. Exponentially weighted impulse-response models and exponentially weighted rolling averages appear more effective at predicting performance using training load data in elite swimmers than a rolling averages approach.

Original languageEnglish
Pages (from-to)1-10
Number of pages10
JournalEuropean Journal of Sport Science
DOIs
Publication statusE-pub ahead of print - Feb 2020

Fingerprint

Neural Networks (Computer)

Cite this

@article{6078d7088bc24be6ba6e59b0d1036fc8,
title = "The impact of different training load quantification and modelling methodologies on performance predictions in elite swimmers",
abstract = "The use of rolling averages to analyse training data has been debated recently. We evaluated two training load quantification methods (five-zone, seven-zone) fitted to performances over two race distances (50 m and 100 m) using four separate longitudinal models (Banister, Busso. rolling averages and exponentially weighted rolling averages) for three swimmers ranked in the top 8 in the world. A total of 1610 daily load measures and 108 performances were collected. Banister (standard error of the estimate (SEE) 0.64 s & 0.62 s; five-zone & seven-zone quantification methods), Busso (SEE 0.73 s & 0.70) and exponentially weighted rolling averages (SEE 0.57 s & 0.63 s) models fitted more accurately (p < 0.001) than the rolling averages approach (SEE 1.32 s and 1.36 s). The seven-zone quantification method did not produce more accurate performance predictions than the five-zone method, despite being a more detailed form of training load quantification. Four neural network models were fitted and had lower error (SEE 0.38, 0.41, 0.35 and 0.60 s) than all longitudinal models but did not track as predictably over time. Exponentially weighted impulse-response models and exponentially weighted rolling averages appear more effective at predicting performance using training load data in elite swimmers than a rolling averages approach.",
keywords = "exponentially weighted rolling averages, neural networks, training zones",
author = "Mitchell, {Lachlan Jg} and Ben Rattray and John Fowlie and Saunders, {Philo U} and Pyne, {David B}",
year = "2020",
month = "2",
doi = "10.1080/17461391.2020.1719211",
language = "English",
pages = "1--10",
journal = "European Journal of Sport Science",
issn = "1536-7290",
publisher = "Taylor and Francis Ltd.",

}

The impact of different training load quantification and modelling methodologies on performance predictions in elite swimmers. / Mitchell, Lachlan Jg; Rattray, Ben; Fowlie, John; Saunders, Philo U; Pyne, David B.

In: European Journal of Sport Science, 02.2020, p. 1-10.

Research output: Contribution to journalArticle

TY - JOUR

T1 - The impact of different training load quantification and modelling methodologies on performance predictions in elite swimmers

AU - Mitchell, Lachlan Jg

AU - Rattray, Ben

AU - Fowlie, John

AU - Saunders, Philo U

AU - Pyne, David B

PY - 2020/2

Y1 - 2020/2

N2 - The use of rolling averages to analyse training data has been debated recently. We evaluated two training load quantification methods (five-zone, seven-zone) fitted to performances over two race distances (50 m and 100 m) using four separate longitudinal models (Banister, Busso. rolling averages and exponentially weighted rolling averages) for three swimmers ranked in the top 8 in the world. A total of 1610 daily load measures and 108 performances were collected. Banister (standard error of the estimate (SEE) 0.64 s & 0.62 s; five-zone & seven-zone quantification methods), Busso (SEE 0.73 s & 0.70) and exponentially weighted rolling averages (SEE 0.57 s & 0.63 s) models fitted more accurately (p < 0.001) than the rolling averages approach (SEE 1.32 s and 1.36 s). The seven-zone quantification method did not produce more accurate performance predictions than the five-zone method, despite being a more detailed form of training load quantification. Four neural network models were fitted and had lower error (SEE 0.38, 0.41, 0.35 and 0.60 s) than all longitudinal models but did not track as predictably over time. Exponentially weighted impulse-response models and exponentially weighted rolling averages appear more effective at predicting performance using training load data in elite swimmers than a rolling averages approach.

AB - The use of rolling averages to analyse training data has been debated recently. We evaluated two training load quantification methods (five-zone, seven-zone) fitted to performances over two race distances (50 m and 100 m) using four separate longitudinal models (Banister, Busso. rolling averages and exponentially weighted rolling averages) for three swimmers ranked in the top 8 in the world. A total of 1610 daily load measures and 108 performances were collected. Banister (standard error of the estimate (SEE) 0.64 s & 0.62 s; five-zone & seven-zone quantification methods), Busso (SEE 0.73 s & 0.70) and exponentially weighted rolling averages (SEE 0.57 s & 0.63 s) models fitted more accurately (p < 0.001) than the rolling averages approach (SEE 1.32 s and 1.36 s). The seven-zone quantification method did not produce more accurate performance predictions than the five-zone method, despite being a more detailed form of training load quantification. Four neural network models were fitted and had lower error (SEE 0.38, 0.41, 0.35 and 0.60 s) than all longitudinal models but did not track as predictably over time. Exponentially weighted impulse-response models and exponentially weighted rolling averages appear more effective at predicting performance using training load data in elite swimmers than a rolling averages approach.

KW - exponentially weighted rolling averages

KW - neural networks

KW - training zones

UR - http://www.mendeley.com/catalogue/impact-different-training-load-quantification-modelling-methodologies-performance-predictions-elite

U2 - 10.1080/17461391.2020.1719211

DO - 10.1080/17461391.2020.1719211

M3 - Article

SP - 1

EP - 10

JO - European Journal of Sport Science

JF - European Journal of Sport Science

SN - 1536-7290

ER -