Automatic Recognition of Motor Skills in Triathlon: A Novel Tool for Measuring Movement Cadence and Cycling Tasks

<b>Background/Objectives</b>: The purpose of this research was to create a peak detection algorithm and machine learning model for use in triathlon. The algorithm and model aimed to automatically measure movement cadence in all three disciplines of a triathlon using data from a single in...

Full description

Saved in:
Bibliographic Details
Main Authors: Stuart M. Chesher, Carlo Martinotti, Dale W. Chapman, Simon M. Rosalie, Paula C. Charlton, Kevin J. Netto
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Journal of Functional Morphology and Kinesiology
Subjects:
Online Access:https://www.mdpi.com/2411-5142/9/4/269
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850050328437719040
author Stuart M. Chesher
Carlo Martinotti
Dale W. Chapman
Simon M. Rosalie
Paula C. Charlton
Kevin J. Netto
author_facet Stuart M. Chesher
Carlo Martinotti
Dale W. Chapman
Simon M. Rosalie
Paula C. Charlton
Kevin J. Netto
author_sort Stuart M. Chesher
collection DOAJ
description <b>Background/Objectives</b>: The purpose of this research was to create a peak detection algorithm and machine learning model for use in triathlon. The algorithm and model aimed to automatically measure movement cadence in all three disciplines of a triathlon using data from a single inertial measurement unit and to recognise the occurrence and duration of cycling task changes. <b>Methods</b>: Six triathletes were recruited to participate in a triathlon while wearing a single trunk-mounted measurement unit and were filmed throughout. Following an initial analysis, a further six triathletes were recruited to collect additional cycling data to train the machine learning model to more effectively recognise cycling task changes. <b>Results</b>: The peak-counting algorithm successfully detected 98.7% of swimming strokes, with a root mean square error of 2.7 swimming strokes. It detected 97.8% of cycling pedal strokes with a root mean square error of 9.1 pedal strokes, and 99.4% of running strides with a root mean square error of 1.2 running strides. Additionally, the machine learning model was 94% (±5%) accurate at distinguishing between ‘in-saddle’ and ‘out-of-saddle’ riding, but it was unable to distinguish between ‘in-saddle’ riding and ‘coasting’ based on tri-axial acceleration and angular velocity. However, it displayed poor sensitivity to detect ‘out-of-saddle’ efforts in uncontrolled conditions which improved when conditions were further controlled. <b>Conclusions</b>: A custom peak detection algorithm and machine learning model are effective tools to automatically analyse triathlon performance.
format Article
id doaj-art-33b5ad9604ae4e02a5274c0e3869c7f6
institution DOAJ
issn 2411-5142
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Journal of Functional Morphology and Kinesiology
spelling doaj-art-33b5ad9604ae4e02a5274c0e3869c7f62025-08-20T02:53:30ZengMDPI AGJournal of Functional Morphology and Kinesiology2411-51422024-12-019426910.3390/jfmk9040269Automatic Recognition of Motor Skills in Triathlon: A Novel Tool for Measuring Movement Cadence and Cycling TasksStuart M. Chesher0Carlo Martinotti1Dale W. Chapman2Simon M. Rosalie3Paula C. Charlton4Kevin J. Netto5Curtin School of Allied Health, Curtin University, Kent Street, Bentley, Perth, WA 6102, AustraliaCurtin Institute for Computation, Curtin University, Kent Street, Bentley, Perth, WA 6102, AustraliaCurtin School of Allied Health, Curtin University, Kent Street, Bentley, Perth, WA 6102, AustraliaSR Performance, Gairloch Drive, Frankston, Melbourne, VIC 3199, AustraliaAustralian Institute of Sport, Leverrier Street, Bruce, Canberra, ACT 2617, AustraliaCurtin School of Allied Health, Curtin University, Kent Street, Bentley, Perth, WA 6102, Australia<b>Background/Objectives</b>: The purpose of this research was to create a peak detection algorithm and machine learning model for use in triathlon. The algorithm and model aimed to automatically measure movement cadence in all three disciplines of a triathlon using data from a single inertial measurement unit and to recognise the occurrence and duration of cycling task changes. <b>Methods</b>: Six triathletes were recruited to participate in a triathlon while wearing a single trunk-mounted measurement unit and were filmed throughout. Following an initial analysis, a further six triathletes were recruited to collect additional cycling data to train the machine learning model to more effectively recognise cycling task changes. <b>Results</b>: The peak-counting algorithm successfully detected 98.7% of swimming strokes, with a root mean square error of 2.7 swimming strokes. It detected 97.8% of cycling pedal strokes with a root mean square error of 9.1 pedal strokes, and 99.4% of running strides with a root mean square error of 1.2 running strides. Additionally, the machine learning model was 94% (±5%) accurate at distinguishing between ‘in-saddle’ and ‘out-of-saddle’ riding, but it was unable to distinguish between ‘in-saddle’ riding and ‘coasting’ based on tri-axial acceleration and angular velocity. However, it displayed poor sensitivity to detect ‘out-of-saddle’ efforts in uncontrolled conditions which improved when conditions were further controlled. <b>Conclusions</b>: A custom peak detection algorithm and machine learning model are effective tools to automatically analyse triathlon performance.https://www.mdpi.com/2411-5142/9/4/269machine learningpeak detectioncycling taskcadencemotor performanceinertial measurement
spellingShingle Stuart M. Chesher
Carlo Martinotti
Dale W. Chapman
Simon M. Rosalie
Paula C. Charlton
Kevin J. Netto
Automatic Recognition of Motor Skills in Triathlon: A Novel Tool for Measuring Movement Cadence and Cycling Tasks
Journal of Functional Morphology and Kinesiology
machine learning
peak detection
cycling task
cadence
motor performance
inertial measurement
title Automatic Recognition of Motor Skills in Triathlon: A Novel Tool for Measuring Movement Cadence and Cycling Tasks
title_full Automatic Recognition of Motor Skills in Triathlon: A Novel Tool for Measuring Movement Cadence and Cycling Tasks
title_fullStr Automatic Recognition of Motor Skills in Triathlon: A Novel Tool for Measuring Movement Cadence and Cycling Tasks
title_full_unstemmed Automatic Recognition of Motor Skills in Triathlon: A Novel Tool for Measuring Movement Cadence and Cycling Tasks
title_short Automatic Recognition of Motor Skills in Triathlon: A Novel Tool for Measuring Movement Cadence and Cycling Tasks
title_sort automatic recognition of motor skills in triathlon a novel tool for measuring movement cadence and cycling tasks
topic machine learning
peak detection
cycling task
cadence
motor performance
inertial measurement
url https://www.mdpi.com/2411-5142/9/4/269
work_keys_str_mv AT stuartmchesher automaticrecognitionofmotorskillsintriathlonanoveltoolformeasuringmovementcadenceandcyclingtasks
AT carlomartinotti automaticrecognitionofmotorskillsintriathlonanoveltoolformeasuringmovementcadenceandcyclingtasks
AT dalewchapman automaticrecognitionofmotorskillsintriathlonanoveltoolformeasuringmovementcadenceandcyclingtasks
AT simonmrosalie automaticrecognitionofmotorskillsintriathlonanoveltoolformeasuringmovementcadenceandcyclingtasks
AT paulaccharlton automaticrecognitionofmotorskillsintriathlonanoveltoolformeasuringmovementcadenceandcyclingtasks
AT kevinjnetto automaticrecognitionofmotorskillsintriathlonanoveltoolformeasuringmovementcadenceandcyclingtasks