No Cover Image

Conference Paper/Proceeding/Abstract 1328 views

A Machine Learning Approach to Measure and Monitor Physical Activity in Children to Help Fight Overweight and Obesity

P. Fergus, A. Hussain, J. Hearty, S. Fairclough, L. Boddy, K. A. Mackintosh, G. Stratton, N. D. Ridgers, Naeem Radi, Gareth Stratton Orcid Logo, Kelly Mackintosh Orcid Logo

Intelligent Computing Theories and Methodologies, Volume: 9226, Pages: 676 - 688

Swansea University Authors: Gareth Stratton Orcid Logo, Kelly Mackintosh Orcid Logo

Full text not available from this repository: check for access using links below.

Check full text

DOI (Published version): 10.1007/978-3-319-22186-1_67

Abstract

Abstract. Physical Activity is important for maintaining healthy lifestyles.Recommendations for physical activity levels are issued by most governmentsas part of public health measures. As such, reliable measurement of physicalactivity for regulatory purposes is vital. This has lead research to expl...

Full description

Published in: Intelligent Computing Theories and Methodologies
ISBN: 978-3-319-22185-4 978-3-319-22186-1
ISSN: 0302-9743 1611-3349
Published: 2015
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa27049
first_indexed 2016-04-08T01:13:37Z
last_indexed 2019-06-26T13:53:46Z
id cronfa27049
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2019-06-26T10:49:11.5850971</datestamp><bib-version>v2</bib-version><id>27049</id><entry>2016-04-07</entry><title>A Machine Learning Approach to Measure and Monitor Physical Activity in Children to Help Fight Overweight and Obesity</title><swanseaauthors><author><sid>6d62b2ed126961bed81a94a2beba8a01</sid><ORCID>0000-0001-5618-0803</ORCID><firstname>Gareth</firstname><surname>Stratton</surname><name>Gareth Stratton</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>bdb20e3f31bcccf95c7bc116070c4214</sid><ORCID>0000-0003-0355-6357</ORCID><firstname>Kelly</firstname><surname>Mackintosh</surname><name>Kelly Mackintosh</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2016-04-07</date><deptcode>EAAS</deptcode><abstract>Abstract. Physical Activity is important for maintaining healthy lifestyles.Recommendations for physical activity levels are issued by most governmentsas part of public health measures. As such, reliable measurement of physicalactivity for regulatory purposes is vital. This has lead research to explorestandards for achieving this using wearable technology and artificial neuralnetworks that produce classifications for specific physical activity events.Applied from a very early age, the ubiquitous capture of physical activity datausing mobile and wearable technology may help us to understand how we cancombat childhood obesity and the impact that this has in later life. A supervisedmachine learning approach is adopted in this paper that utilizes data obtainedfrom accelerometer sensors worn by children in free-living environments. Thepaper presents a set of activities and features suitable for measuring physicalactivity and evaluates the use of a Multilayer Perceptron neural network toclassify physical activities by activity type. A rigorous reproducible data sciencemethodology is presented for subsequent use in physical activity research. Ourresults show that it was possible to obtain an overall accuracy of 96 % with 95 %for sensitivity, 99 % for specificity and a kappa value of 94 % when three andfour feature combinations were used.</abstract><type>Conference Paper/Proceeding/Abstract</type><journal>Intelligent Computing Theories and Methodologies</journal><volume>9226</volume><paginationStart>676</paginationStart><paginationEnd>688</paginationEnd><publisher/><isbnPrint>978-3-319-22185-4</isbnPrint><isbnElectronic>978-3-319-22186-1</isbnElectronic><issnPrint>0302-9743</issnPrint><issnElectronic>1611-3349</issnElectronic><keywords>Physical activity, Overweight, Obesity, Machine learning, Neural networks, Sensors</keywords><publishedDay>31</publishedDay><publishedMonth>12</publishedMonth><publishedYear>2015</publishedYear><publishedDate>2015-12-31</publishedDate><doi>10.1007/978-3-319-22186-1_67</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/><lastEdited>2019-06-26T10:49:11.5850971</lastEdited><Created>2016-04-07T11:11:41.4361549</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Sport and Exercise Sciences</level></path><authors><author><firstname>P.</firstname><surname>Fergus</surname><order>1</order></author><author><firstname>A.</firstname><surname>Hussain</surname><order>2</order></author><author><firstname>J.</firstname><surname>Hearty</surname><order>3</order></author><author><firstname>S.</firstname><surname>Fairclough</surname><order>4</order></author><author><firstname>L.</firstname><surname>Boddy</surname><order>5</order></author><author><firstname>K. A.</firstname><surname>Mackintosh</surname><order>6</order></author><author><firstname>G.</firstname><surname>Stratton</surname><order>7</order></author><author><firstname>N. D.</firstname><surname>Ridgers</surname><order>8</order></author><author><firstname>Naeem</firstname><surname>Radi</surname><order>9</order></author><author><firstname>Gareth</firstname><surname>Stratton</surname><orcid>0000-0001-5618-0803</orcid><order>10</order></author><author><firstname>Kelly</firstname><surname>Mackintosh</surname><orcid>0000-0003-0355-6357</orcid><order>11</order></author></authors><documents/><OutputDurs/></rfc1807>
spelling 2019-06-26T10:49:11.5850971 v2 27049 2016-04-07 A Machine Learning Approach to Measure and Monitor Physical Activity in Children to Help Fight Overweight and Obesity 6d62b2ed126961bed81a94a2beba8a01 0000-0001-5618-0803 Gareth Stratton Gareth Stratton true false bdb20e3f31bcccf95c7bc116070c4214 0000-0003-0355-6357 Kelly Mackintosh Kelly Mackintosh true false 2016-04-07 EAAS Abstract. Physical Activity is important for maintaining healthy lifestyles.Recommendations for physical activity levels are issued by most governmentsas part of public health measures. As such, reliable measurement of physicalactivity for regulatory purposes is vital. This has lead research to explorestandards for achieving this using wearable technology and artificial neuralnetworks that produce classifications for specific physical activity events.Applied from a very early age, the ubiquitous capture of physical activity datausing mobile and wearable technology may help us to understand how we cancombat childhood obesity and the impact that this has in later life. A supervisedmachine learning approach is adopted in this paper that utilizes data obtainedfrom accelerometer sensors worn by children in free-living environments. Thepaper presents a set of activities and features suitable for measuring physicalactivity and evaluates the use of a Multilayer Perceptron neural network toclassify physical activities by activity type. A rigorous reproducible data sciencemethodology is presented for subsequent use in physical activity research. Ourresults show that it was possible to obtain an overall accuracy of 96 % with 95 %for sensitivity, 99 % for specificity and a kappa value of 94 % when three andfour feature combinations were used. Conference Paper/Proceeding/Abstract Intelligent Computing Theories and Methodologies 9226 676 688 978-3-319-22185-4 978-3-319-22186-1 0302-9743 1611-3349 Physical activity, Overweight, Obesity, Machine learning, Neural networks, Sensors 31 12 2015 2015-12-31 10.1007/978-3-319-22186-1_67 COLLEGE NANME Engineering and Applied Sciences School COLLEGE CODE EAAS Swansea University 2019-06-26T10:49:11.5850971 2016-04-07T11:11:41.4361549 Faculty of Science and Engineering School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Sport and Exercise Sciences P. Fergus 1 A. Hussain 2 J. Hearty 3 S. Fairclough 4 L. Boddy 5 K. A. Mackintosh 6 G. Stratton 7 N. D. Ridgers 8 Naeem Radi 9 Gareth Stratton 0000-0001-5618-0803 10 Kelly Mackintosh 0000-0003-0355-6357 11
title A Machine Learning Approach to Measure and Monitor Physical Activity in Children to Help Fight Overweight and Obesity
spellingShingle A Machine Learning Approach to Measure and Monitor Physical Activity in Children to Help Fight Overweight and Obesity
Gareth Stratton
Kelly Mackintosh
title_short A Machine Learning Approach to Measure and Monitor Physical Activity in Children to Help Fight Overweight and Obesity
title_full A Machine Learning Approach to Measure and Monitor Physical Activity in Children to Help Fight Overweight and Obesity
title_fullStr A Machine Learning Approach to Measure and Monitor Physical Activity in Children to Help Fight Overweight and Obesity
title_full_unstemmed A Machine Learning Approach to Measure and Monitor Physical Activity in Children to Help Fight Overweight and Obesity
title_sort A Machine Learning Approach to Measure and Monitor Physical Activity in Children to Help Fight Overweight and Obesity
author_id_str_mv 6d62b2ed126961bed81a94a2beba8a01
bdb20e3f31bcccf95c7bc116070c4214
author_id_fullname_str_mv 6d62b2ed126961bed81a94a2beba8a01_***_Gareth Stratton
bdb20e3f31bcccf95c7bc116070c4214_***_Kelly Mackintosh
author Gareth Stratton
Kelly Mackintosh
author2 P. Fergus
A. Hussain
J. Hearty
S. Fairclough
L. Boddy
K. A. Mackintosh
G. Stratton
N. D. Ridgers
Naeem Radi
Gareth Stratton
Kelly Mackintosh
format Conference Paper/Proceeding/Abstract
container_title Intelligent Computing Theories and Methodologies
container_volume 9226
container_start_page 676
publishDate 2015
institution Swansea University
isbn 978-3-319-22185-4
978-3-319-22186-1
issn 0302-9743
1611-3349
doi_str_mv 10.1007/978-3-319-22186-1_67
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 Aerospace, Civil, Electrical, General and Mechanical Engineering - Sport and Exercise Sciences{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Sport and Exercise Sciences
document_store_str 0
active_str 0
description Abstract. Physical Activity is important for maintaining healthy lifestyles.Recommendations for physical activity levels are issued by most governmentsas part of public health measures. As such, reliable measurement of physicalactivity for regulatory purposes is vital. This has lead research to explorestandards for achieving this using wearable technology and artificial neuralnetworks that produce classifications for specific physical activity events.Applied from a very early age, the ubiquitous capture of physical activity datausing mobile and wearable technology may help us to understand how we cancombat childhood obesity and the impact that this has in later life. A supervisedmachine learning approach is adopted in this paper that utilizes data obtainedfrom accelerometer sensors worn by children in free-living environments. Thepaper presents a set of activities and features suitable for measuring physicalactivity and evaluates the use of a Multilayer Perceptron neural network toclassify physical activities by activity type. A rigorous reproducible data sciencemethodology is presented for subsequent use in physical activity research. Ourresults show that it was possible to obtain an overall accuracy of 96 % with 95 %for sensitivity, 99 % for specificity and a kappa value of 94 % when three andfour feature combinations were used.
published_date 2015-12-31T18:53:29Z
_version_ 1821342128592125952
score 11.04748

Similar Items