No Cover Image

E-Thesis 334 views 243 downloads

Generalisable FPCA-based Models for Predicting Peak Power in Vertical Jumping using Accelerometer Data / MARK WHITE

Swansea University Author: MARK WHITE

  • White_Mark_G_E_PhD_Thesis_Final_Redacted_Signature.pdf

    PDF | E-Thesis – open access

    Copyright: The author, Mark George Eric White, 2021.

    Download (9.82MB)

DOI (Published version): 10.23889/SUthesis.58286

Abstract

Peak power in the countermovement jump is correlated with various measures of sports performance and can be used to monitor athlete training. The gold standard method for determining peak power uses force platforms, but they are unsuitable for field-based testing favoured by practitioners. Alternati...

Full description

Published: Swansea 2021
Institution: Swansea University
Degree level: Doctoral
Degree name: Ph.D
Supervisor: Bezodis, Neil ; Neville, Jonathon ; Rees, Paul
URI: https://cronfa.swan.ac.uk/Record/cronfa58286
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2021-10-11T07:56:49Z
last_indexed 2021-10-12T03:24:28Z
id cronfa58286
recordtype RisThesis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2021-10-11T09:26:38.0757510</datestamp><bib-version>v2</bib-version><id>58286</id><entry>2021-10-11</entry><title>Generalisable FPCA-based Models for Predicting Peak Power in Vertical Jumping using Accelerometer Data</title><swanseaauthors><author><sid>51b0c5a3ebbb109f3e9d3092f53e4e3e</sid><firstname>MARK</firstname><surname>WHITE</surname><name>MARK WHITE</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2021-10-11</date><abstract>Peak power in the countermovement jump is correlated with various measures of sports performance and can be used to monitor athlete training. The gold standard method for determining peak power uses force platforms, but they are unsuitable for field-based testing favoured by practitioners. Alternatives include predicting peak power from jump flight times, or using Newtonian methods based on body-worn inertial sensor data, but so far neither has yielded sufficiently accurate estimates. This thesis aims to develop a generalisable model for predicting peak power based on Functional Principal Component Analysis applied to body-worn accelerometer data. Data was collected from 69 male and female adults, engaged in sports at recreational, club or national levels. They performed up to 16 countermovement jumps each, with and without arm swing, 696 jumps in total. Peak power criterion measures were obtained from force platforms, and characteristic features from accelerometer data were extracted from four sensors attached to the lower back, upper back and both shanks. The best machine learning algorithm, jump type and sensor anatomical location were determined in this context. The investigation considered signal representation (resultant, triaxial or a suitable transform), preprocessing (smoothing, time window and curve registration), feature selection and data augmentation (signal rotations and SMOTER). A novel procedure optimised the model parameters based on Particle Swarm applied to a surrogate Gaussian Process model. Model selection and evaluation were based on nested cross validation (Monte Carlo design). The final optimal model had an RMSE of 2.5 W&#xB7;kg-1, which compares favourably to earlier research (4.9 &#xB1; 1.7 W&#xB7;kg-1 for flight-time formulae and 10.7 &#xB1; 6.3 W&#xB7;kg-1 for Newtonian sensor-based methods). Whilst this is not yet sufficiently accurate for applied practice, this thesis has developed and comprehensively evaluated new techniques, which will be valuable to future biomechanical applications.</abstract><type>E-Thesis</type><journal/><volume/><journalNumber/><paginationStart/><paginationEnd/><publisher/><placeOfPublication>Swansea</placeOfPublication><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic/><keywords>Countermovement jump, peak power, machine learning, functional principal component analysis, nested cross validation, optimisation</keywords><publishedDay>11</publishedDay><publishedMonth>10</publishedMonth><publishedYear>2021</publishedYear><publishedDate>2021-10-11</publishedDate><doi>10.23889/SUthesis.58286</doi><url/><notes>ORCiD identifier https://orcid.org/0000-0001-5404-9289</notes><college>COLLEGE NANME</college><CollegeCode>COLLEGE CODE</CollegeCode><institution>Swansea University</institution><supervisor>Bezodis, Neil ; Neville, Jonathon ; Rees, Paul</supervisor><degreelevel>Doctoral</degreelevel><degreename>Ph.D</degreename><apcterm/><lastEdited>2021-10-11T09:26:38.0757510</lastEdited><Created>2021-10-11T08:53:59.8473918</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Engineering and Applied Sciences - Uncategorised</level></path><authors><author><firstname>MARK</firstname><surname>WHITE</surname><order>1</order></author></authors><documents><document><filename>58286__21129__c4899302f29f43c0bac0dd8f599bad60.pdf</filename><originalFilename>White_Mark_G_E_PhD_Thesis_Final_Redacted_Signature.pdf</originalFilename><uploaded>2021-10-11T09:24:24.8856389</uploaded><type>Output</type><contentLength>10294327</contentLength><contentType>application/pdf</contentType><version>E-Thesis &#x2013; open access</version><cronfaStatus>true</cronfaStatus><documentNotes>Copyright: The author, Mark George Eric White, 2021.</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language></document></documents><OutputDurs/></rfc1807>
spelling 2021-10-11T09:26:38.0757510 v2 58286 2021-10-11 Generalisable FPCA-based Models for Predicting Peak Power in Vertical Jumping using Accelerometer Data 51b0c5a3ebbb109f3e9d3092f53e4e3e MARK WHITE MARK WHITE true false 2021-10-11 Peak power in the countermovement jump is correlated with various measures of sports performance and can be used to monitor athlete training. The gold standard method for determining peak power uses force platforms, but they are unsuitable for field-based testing favoured by practitioners. Alternatives include predicting peak power from jump flight times, or using Newtonian methods based on body-worn inertial sensor data, but so far neither has yielded sufficiently accurate estimates. This thesis aims to develop a generalisable model for predicting peak power based on Functional Principal Component Analysis applied to body-worn accelerometer data. Data was collected from 69 male and female adults, engaged in sports at recreational, club or national levels. They performed up to 16 countermovement jumps each, with and without arm swing, 696 jumps in total. Peak power criterion measures were obtained from force platforms, and characteristic features from accelerometer data were extracted from four sensors attached to the lower back, upper back and both shanks. The best machine learning algorithm, jump type and sensor anatomical location were determined in this context. The investigation considered signal representation (resultant, triaxial or a suitable transform), preprocessing (smoothing, time window and curve registration), feature selection and data augmentation (signal rotations and SMOTER). A novel procedure optimised the model parameters based on Particle Swarm applied to a surrogate Gaussian Process model. Model selection and evaluation were based on nested cross validation (Monte Carlo design). The final optimal model had an RMSE of 2.5 W·kg-1, which compares favourably to earlier research (4.9 ± 1.7 W·kg-1 for flight-time formulae and 10.7 ± 6.3 W·kg-1 for Newtonian sensor-based methods). Whilst this is not yet sufficiently accurate for applied practice, this thesis has developed and comprehensively evaluated new techniques, which will be valuable to future biomechanical applications. E-Thesis Swansea Countermovement jump, peak power, machine learning, functional principal component analysis, nested cross validation, optimisation 11 10 2021 2021-10-11 10.23889/SUthesis.58286 ORCiD identifier https://orcid.org/0000-0001-5404-9289 COLLEGE NANME COLLEGE CODE Swansea University Bezodis, Neil ; Neville, Jonathon ; Rees, Paul Doctoral Ph.D 2021-10-11T09:26:38.0757510 2021-10-11T08:53:59.8473918 Faculty of Science and Engineering School of Engineering and Applied Sciences - Uncategorised MARK WHITE 1 58286__21129__c4899302f29f43c0bac0dd8f599bad60.pdf White_Mark_G_E_PhD_Thesis_Final_Redacted_Signature.pdf 2021-10-11T09:24:24.8856389 Output 10294327 application/pdf E-Thesis – open access true Copyright: The author, Mark George Eric White, 2021. true eng
title Generalisable FPCA-based Models for Predicting Peak Power in Vertical Jumping using Accelerometer Data
spellingShingle Generalisable FPCA-based Models for Predicting Peak Power in Vertical Jumping using Accelerometer Data
MARK WHITE
title_short Generalisable FPCA-based Models for Predicting Peak Power in Vertical Jumping using Accelerometer Data
title_full Generalisable FPCA-based Models for Predicting Peak Power in Vertical Jumping using Accelerometer Data
title_fullStr Generalisable FPCA-based Models for Predicting Peak Power in Vertical Jumping using Accelerometer Data
title_full_unstemmed Generalisable FPCA-based Models for Predicting Peak Power in Vertical Jumping using Accelerometer Data
title_sort Generalisable FPCA-based Models for Predicting Peak Power in Vertical Jumping using Accelerometer Data
author_id_str_mv 51b0c5a3ebbb109f3e9d3092f53e4e3e
author_id_fullname_str_mv 51b0c5a3ebbb109f3e9d3092f53e4e3e_***_MARK WHITE
author MARK WHITE
author2 MARK WHITE
format E-Thesis
publishDate 2021
institution Swansea University
doi_str_mv 10.23889/SUthesis.58286
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Engineering and Applied Sciences - Uncategorised{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Engineering and Applied Sciences - Uncategorised
document_store_str 1
active_str 0
description Peak power in the countermovement jump is correlated with various measures of sports performance and can be used to monitor athlete training. The gold standard method for determining peak power uses force platforms, but they are unsuitable for field-based testing favoured by practitioners. Alternatives include predicting peak power from jump flight times, or using Newtonian methods based on body-worn inertial sensor data, but so far neither has yielded sufficiently accurate estimates. This thesis aims to develop a generalisable model for predicting peak power based on Functional Principal Component Analysis applied to body-worn accelerometer data. Data was collected from 69 male and female adults, engaged in sports at recreational, club or national levels. They performed up to 16 countermovement jumps each, with and without arm swing, 696 jumps in total. Peak power criterion measures were obtained from force platforms, and characteristic features from accelerometer data were extracted from four sensors attached to the lower back, upper back and both shanks. The best machine learning algorithm, jump type and sensor anatomical location were determined in this context. The investigation considered signal representation (resultant, triaxial or a suitable transform), preprocessing (smoothing, time window and curve registration), feature selection and data augmentation (signal rotations and SMOTER). A novel procedure optimised the model parameters based on Particle Swarm applied to a surrogate Gaussian Process model. Model selection and evaluation were based on nested cross validation (Monte Carlo design). The final optimal model had an RMSE of 2.5 W·kg-1, which compares favourably to earlier research (4.9 ± 1.7 W·kg-1 for flight-time formulae and 10.7 ± 6.3 W·kg-1 for Newtonian sensor-based methods). Whilst this is not yet sufficiently accurate for applied practice, this thesis has developed and comprehensively evaluated new techniques, which will be valuable to future biomechanical applications.
published_date 2021-10-11T04:14:42Z
_version_ 1763753991691304960
score 11.012678

Similar Items