No Cover Image

Journal article 49 views 9 downloads

Wearable Sensors for Athletic Performance: A Comparison of Discrete and Continuous Feature Extraction Methods for Prediction Models

Mark White, Beatrice De Lazzari, Neil Bezodis Orcid Logo, Valentina Camomilla

Mathematics

Swansea University Authors: Mark White, Neil Bezodis Orcid Logo

DOI (Published version): 10.3390/math12121853

Abstract

Wearable sensors have become increasingly popular for assessing athletic performance, but the optimal methods for processing and analysing the data remain unclear. This study investigates the efficacy of discrete and continuous feature extraction methods, separately and in combination, for modelling...

Full description

Published in: Mathematics
Published:
URI: https://cronfa.swan.ac.uk/Record/cronfa66702
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2024-06-11T14:36:40Z
last_indexed 2024-06-11T14:36:40Z
id cronfa66702
recordtype SURis
fullrecord <?xml version="1.0" encoding="utf-8"?><rfc1807 xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema"><bib-version>v2</bib-version><id>66702</id><entry>2024-06-11</entry><title>Wearable Sensors for Athletic Performance: A Comparison of Discrete and Continuous Feature Extraction Methods for Prediction Models</title><swanseaauthors><author><sid>725158b503e2be11ce4cc531afe08990</sid><firstname>Mark</firstname><surname>White</surname><name>Mark White</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>534588568c1936e94e1ed8527b8c991b</sid><ORCID>0000-0003-2229-3310</ORCID><firstname>Neil</firstname><surname>Bezodis</surname><name>Neil Bezodis</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2024-06-11</date><deptcode>EAAS</deptcode><abstract>Wearable sensors have become increasingly popular for assessing athletic performance, but the optimal methods for processing and analysing the data remain unclear. This study investigates the efficacy of discrete and continuous feature extraction methods, separately and in combination, for modelling countermovement jump performance using wearable sensor data. We demonstrate that continuous features, particularly those derived from Functional Principal Component Analysis, outperform discrete features in terms of model performance, robustness to variations in data distribution and volume, and consistency across different datasets. Our findings underscore the importance of methodological choices, such as signal type, alignment methods, and model selection, in developing accurate and generalisable predictive models. We also highlight the potential pitfalls of relying solely on domain knowledge for feature selection and the benefits of data-driven approaches.Furthermore, we discuss the implications of our findings for the broader field of sports biomechanics and provide practical recommendations for researchers and practitioners aiming to leverage wearable sensor data for athletic performance assessment. Our results contribute to the development of more reliable and widely applicable predictive models, facilitating the use of wearable technology for optimising training and enhancing athletic outcomes across various sports disciplines.</abstract><type>Journal Article</type><journal>Mathematics</journal><volume/><journalNumber/><paginationStart/><paginationEnd/><publisher/><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic/><keywords/><publishedDay>0</publishedDay><publishedMonth>0</publishedMonth><publishedYear>0</publishedYear><publishedDate>0001-01-01</publishedDate><doi>10.3390/math12121853</doi><url/><notes/><college>COLLEGE NANME</college><department>Engineering and Applied Sciences School</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>EAAS</DepartmentCode><institution>Swansea University</institution><apcterm/><funders>This research was funded by Regione Lazio, Call: POR FESR Lazio 2014–2020 (Azione 1.2.1), grant number 20028AP000000095. 1.2.1), grant number 20028AP000000095. The APC was waived.</funders><projectreference/><lastEdited>2024-06-14T11:34:26.0003846</lastEdited><Created>2024-06-11T15:33:30.7540963</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Engineering and Applied Sciences - Sport and Exercise Sciences</level></path><authors><author><firstname>Mark</firstname><surname>White</surname><order>1</order></author><author><firstname>Beatrice De</firstname><surname>Lazzari</surname><order>2</order></author><author><firstname>Neil</firstname><surname>Bezodis</surname><orcid>0000-0003-2229-3310</orcid><order>3</order></author><author><firstname>Valentina</firstname><surname>Camomilla</surname><order>4</order></author></authors><documents><document><filename>66702__30644__de29812368ce4b66a2593117b473d611.pdf</filename><originalFilename>66702.pdf</originalFilename><uploaded>2024-06-14T11:34:19.4712818</uploaded><type>Output</type><contentLength>3101126</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><copyrightCorrect>false</copyrightCorrect></document></documents><OutputDurs/></rfc1807>
spelling v2 66702 2024-06-11 Wearable Sensors for Athletic Performance: A Comparison of Discrete and Continuous Feature Extraction Methods for Prediction Models 725158b503e2be11ce4cc531afe08990 Mark White Mark White true false 534588568c1936e94e1ed8527b8c991b 0000-0003-2229-3310 Neil Bezodis Neil Bezodis true false 2024-06-11 EAAS Wearable sensors have become increasingly popular for assessing athletic performance, but the optimal methods for processing and analysing the data remain unclear. This study investigates the efficacy of discrete and continuous feature extraction methods, separately and in combination, for modelling countermovement jump performance using wearable sensor data. We demonstrate that continuous features, particularly those derived from Functional Principal Component Analysis, outperform discrete features in terms of model performance, robustness to variations in data distribution and volume, and consistency across different datasets. Our findings underscore the importance of methodological choices, such as signal type, alignment methods, and model selection, in developing accurate and generalisable predictive models. We also highlight the potential pitfalls of relying solely on domain knowledge for feature selection and the benefits of data-driven approaches.Furthermore, we discuss the implications of our findings for the broader field of sports biomechanics and provide practical recommendations for researchers and practitioners aiming to leverage wearable sensor data for athletic performance assessment. Our results contribute to the development of more reliable and widely applicable predictive models, facilitating the use of wearable technology for optimising training and enhancing athletic outcomes across various sports disciplines. Journal Article Mathematics 0 0 0 0001-01-01 10.3390/math12121853 COLLEGE NANME Engineering and Applied Sciences School COLLEGE CODE EAAS Swansea University This research was funded by Regione Lazio, Call: POR FESR Lazio 2014–2020 (Azione 1.2.1), grant number 20028AP000000095. 1.2.1), grant number 20028AP000000095. The APC was waived. 2024-06-14T11:34:26.0003846 2024-06-11T15:33:30.7540963 Faculty of Science and Engineering School of Engineering and Applied Sciences - Sport and Exercise Sciences Mark White 1 Beatrice De Lazzari 2 Neil Bezodis 0000-0003-2229-3310 3 Valentina Camomilla 4 66702__30644__de29812368ce4b66a2593117b473d611.pdf 66702.pdf 2024-06-14T11:34:19.4712818 Output 3101126 application/pdf Version of Record true false
title Wearable Sensors for Athletic Performance: A Comparison of Discrete and Continuous Feature Extraction Methods for Prediction Models
spellingShingle Wearable Sensors for Athletic Performance: A Comparison of Discrete and Continuous Feature Extraction Methods for Prediction Models
Mark White
Neil Bezodis
title_short Wearable Sensors for Athletic Performance: A Comparison of Discrete and Continuous Feature Extraction Methods for Prediction Models
title_full Wearable Sensors for Athletic Performance: A Comparison of Discrete and Continuous Feature Extraction Methods for Prediction Models
title_fullStr Wearable Sensors for Athletic Performance: A Comparison of Discrete and Continuous Feature Extraction Methods for Prediction Models
title_full_unstemmed Wearable Sensors for Athletic Performance: A Comparison of Discrete and Continuous Feature Extraction Methods for Prediction Models
title_sort Wearable Sensors for Athletic Performance: A Comparison of Discrete and Continuous Feature Extraction Methods for Prediction Models
author_id_str_mv 725158b503e2be11ce4cc531afe08990
534588568c1936e94e1ed8527b8c991b
author_id_fullname_str_mv 725158b503e2be11ce4cc531afe08990_***_Mark White
534588568c1936e94e1ed8527b8c991b_***_Neil Bezodis
author Mark White
Neil Bezodis
author2 Mark White
Beatrice De Lazzari
Neil Bezodis
Valentina Camomilla
format Journal article
container_title Mathematics
institution Swansea University
doi_str_mv 10.3390/math12121853
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 - Sport and Exercise Sciences{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Engineering and Applied Sciences - Sport and Exercise Sciences
document_store_str 1
active_str 0
description Wearable sensors have become increasingly popular for assessing athletic performance, but the optimal methods for processing and analysing the data remain unclear. This study investigates the efficacy of discrete and continuous feature extraction methods, separately and in combination, for modelling countermovement jump performance using wearable sensor data. We demonstrate that continuous features, particularly those derived from Functional Principal Component Analysis, outperform discrete features in terms of model performance, robustness to variations in data distribution and volume, and consistency across different datasets. Our findings underscore the importance of methodological choices, such as signal type, alignment methods, and model selection, in developing accurate and generalisable predictive models. We also highlight the potential pitfalls of relying solely on domain knowledge for feature selection and the benefits of data-driven approaches.Furthermore, we discuss the implications of our findings for the broader field of sports biomechanics and provide practical recommendations for researchers and practitioners aiming to leverage wearable sensor data for athletic performance assessment. Our results contribute to the development of more reliable and widely applicable predictive models, facilitating the use of wearable technology for optimising training and enhancing athletic outcomes across various sports disciplines.
published_date 0001-01-01T11:34:41Z
_version_ 1801832398824931328
score 11.013148

Similar Items