Loading…

Machine learning and statistical approaches to assessing gait patterns of younger and older healthy adults climbing stairs

The following study explores the methods for activity recognition of younger and older adults climbing stairs. There is a correlation to health and the level of activity of an individual, which has captured interest in this field in computing science to determine the level of activity of an individu...

Full description

Saved in:
Bibliographic Details
Main Authors: Chan, Herman, Mingjing Yang, Huiru Zheng, Haiying Wang, Sterritt, R., McClean, S., Mayagoitia, Ruth E.
Format: Conference Proceeding
Language:English
Subjects:
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 592
container_issue
container_start_page 588
container_title
container_volume 1
creator Chan, Herman
Mingjing Yang
Huiru Zheng
Haiying Wang
Sterritt, R.
McClean, S.
Mayagoitia, Ruth E.
description The following study explores the methods for activity recognition of younger and older adults climbing stairs. There is a correlation to health and the level of activity of an individual, which has captured interest in this field in computing science to determine the level of activity of an individual. The focus of the study is the classification of younger and older gait patterns climbing up and down a set of 13 stairs. From using acceleration data from an accelerometer placed on the lumbro-sacral joint; 14 gait features are extracted and analysed. The machine learning algorithms focused in this study are Multilayer Perceptron (MLP), KStar and Support Vector Machine (SVM). An evaluation of performance among three machine learning algorithms was carried out. MLP was found to provide the highest in accuracy for classification. Accuracy of 95.7% was found for classifying a subject walking either up or down the stairs and an accuracy of 80.6% for classifying whether the subject was younger or older. An evaluation of individual features showed poor performance of classification for young and older subjects climbing up and down stairs, and at most cases failed to distinguish between the two classes. However, subsets of features were created using a sequential feature selection algorithm based on feature ranking and individual feature performance. The performance of each subset was recorded and a subset of the top four features achieved an accuracy of 81.7% for classification between young and older subjects. In comparison, 13 features were required to obtain the best performance of 95.7% to distinguish between up and down classes.
doi_str_mv 10.1109/ICNC.2011.6022097
format conference_proceeding
fullrecord <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_6022097</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>6022097</ieee_id><sourcerecordid>6022097</sourcerecordid><originalsourceid>FETCH-LOGICAL-i90t-add845cf4409093ef9dbd58cd37ef6584dd9ce37d67a8c6b12a510d131c2c2373</originalsourceid><addsrcrecordid>eNpVkLtOAzEURI0AiSjkAxCNf2DD9Wu9LtGKR6QATfroxvYmRs7uynaK8PUESEM1M9LMKYaQOwZzxsA8LNr3ds6BsXkNnIPRF2RmdMMkl9IYxevLfxn4FZlwpnRllFI3ZJbzJwAIprUGMyFfb2h3ofc0ekx96LcUe0dzwRJyCRYjxXFMw6nkMy0DxZx9zj-9LYZCRyzFpz7ToaPH4dBvffoFDNGd3M5jLLsjRXeIJVMbw37zMz3hQ8q35LrDmP3srFOyen5ata_V8uNl0T4uq2CgVOhcI5XtpAQDRvjOuI1TjXVC-65WjXTOWC-0qzU2tt4wjoqBY4JZbrnQYkru_7DBe78eU9hjOq7P54lv-QZjgQ</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Machine learning and statistical approaches to assessing gait patterns of younger and older healthy adults climbing stairs</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Chan, Herman ; Mingjing Yang ; Huiru Zheng ; Haiying Wang ; Sterritt, R. ; McClean, S. ; Mayagoitia, Ruth E.</creator><creatorcontrib>Chan, Herman ; Mingjing Yang ; Huiru Zheng ; Haiying Wang ; Sterritt, R. ; McClean, S. ; Mayagoitia, Ruth E.</creatorcontrib><description>The following study explores the methods for activity recognition of younger and older adults climbing stairs. There is a correlation to health and the level of activity of an individual, which has captured interest in this field in computing science to determine the level of activity of an individual. The focus of the study is the classification of younger and older gait patterns climbing up and down a set of 13 stairs. From using acceleration data from an accelerometer placed on the lumbro-sacral joint; 14 gait features are extracted and analysed. The machine learning algorithms focused in this study are Multilayer Perceptron (MLP), KStar and Support Vector Machine (SVM). An evaluation of performance among three machine learning algorithms was carried out. MLP was found to provide the highest in accuracy for classification. Accuracy of 95.7% was found for classifying a subject walking either up or down the stairs and an accuracy of 80.6% for classifying whether the subject was younger or older. An evaluation of individual features showed poor performance of classification for young and older subjects climbing up and down stairs, and at most cases failed to distinguish between the two classes. However, subsets of features were created using a sequential feature selection algorithm based on feature ranking and individual feature performance. The performance of each subset was recorded and a subset of the top four features achieved an accuracy of 81.7% for classification between young and older subjects. In comparison, 13 features were required to obtain the best performance of 95.7% to distinguish between up and down classes.</description><identifier>ISSN: 2157-9555</identifier><identifier>ISBN: 9781424499502</identifier><identifier>ISBN: 142449950X</identifier><identifier>EISBN: 9781424499526</identifier><identifier>EISBN: 1424499534</identifier><identifier>EISBN: 9781424499533</identifier><identifier>EISBN: 1424499526</identifier><identifier>DOI: 10.1109/ICNC.2011.6022097</identifier><language>eng</language><publisher>IEEE</publisher><subject>Accelerometers ; Accuracy ; activity recognition ; classification ; Feature extraction ; gait patterns ; Legged locomotion ; Machine learning ; Predictive models ; statistical analysis ; Support vector machines</subject><ispartof>2011 Seventh International Conference on Natural Computation, 2011, Vol.1, p.588-592</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/6022097$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,27925,54555,54920,54932</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/6022097$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Chan, Herman</creatorcontrib><creatorcontrib>Mingjing Yang</creatorcontrib><creatorcontrib>Huiru Zheng</creatorcontrib><creatorcontrib>Haiying Wang</creatorcontrib><creatorcontrib>Sterritt, R.</creatorcontrib><creatorcontrib>McClean, S.</creatorcontrib><creatorcontrib>Mayagoitia, Ruth E.</creatorcontrib><title>Machine learning and statistical approaches to assessing gait patterns of younger and older healthy adults climbing stairs</title><title>2011 Seventh International Conference on Natural Computation</title><addtitle>ICNC</addtitle><description>The following study explores the methods for activity recognition of younger and older adults climbing stairs. There is a correlation to health and the level of activity of an individual, which has captured interest in this field in computing science to determine the level of activity of an individual. The focus of the study is the classification of younger and older gait patterns climbing up and down a set of 13 stairs. From using acceleration data from an accelerometer placed on the lumbro-sacral joint; 14 gait features are extracted and analysed. The machine learning algorithms focused in this study are Multilayer Perceptron (MLP), KStar and Support Vector Machine (SVM). An evaluation of performance among three machine learning algorithms was carried out. MLP was found to provide the highest in accuracy for classification. Accuracy of 95.7% was found for classifying a subject walking either up or down the stairs and an accuracy of 80.6% for classifying whether the subject was younger or older. An evaluation of individual features showed poor performance of classification for young and older subjects climbing up and down stairs, and at most cases failed to distinguish between the two classes. However, subsets of features were created using a sequential feature selection algorithm based on feature ranking and individual feature performance. The performance of each subset was recorded and a subset of the top four features achieved an accuracy of 81.7% for classification between young and older subjects. In comparison, 13 features were required to obtain the best performance of 95.7% to distinguish between up and down classes.</description><subject>Accelerometers</subject><subject>Accuracy</subject><subject>activity recognition</subject><subject>classification</subject><subject>Feature extraction</subject><subject>gait patterns</subject><subject>Legged locomotion</subject><subject>Machine learning</subject><subject>Predictive models</subject><subject>statistical analysis</subject><subject>Support vector machines</subject><issn>2157-9555</issn><isbn>9781424499502</isbn><isbn>142449950X</isbn><isbn>9781424499526</isbn><isbn>1424499534</isbn><isbn>9781424499533</isbn><isbn>1424499526</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2011</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNpVkLtOAzEURI0AiSjkAxCNf2DD9Wu9LtGKR6QATfroxvYmRs7uynaK8PUESEM1M9LMKYaQOwZzxsA8LNr3ds6BsXkNnIPRF2RmdMMkl9IYxevLfxn4FZlwpnRllFI3ZJbzJwAIprUGMyFfb2h3ofc0ekx96LcUe0dzwRJyCRYjxXFMw6nkMy0DxZx9zj-9LYZCRyzFpz7ToaPH4dBvffoFDNGd3M5jLLsjRXeIJVMbw37zMz3hQ8q35LrDmP3srFOyen5ata_V8uNl0T4uq2CgVOhcI5XtpAQDRvjOuI1TjXVC-65WjXTOWC-0qzU2tt4wjoqBY4JZbrnQYkru_7DBe78eU9hjOq7P54lv-QZjgQ</recordid><startdate>201107</startdate><enddate>201107</enddate><creator>Chan, Herman</creator><creator>Mingjing Yang</creator><creator>Huiru Zheng</creator><creator>Haiying Wang</creator><creator>Sterritt, R.</creator><creator>McClean, S.</creator><creator>Mayagoitia, Ruth E.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>201107</creationdate><title>Machine learning and statistical approaches to assessing gait patterns of younger and older healthy adults climbing stairs</title><author>Chan, Herman ; Mingjing Yang ; Huiru Zheng ; Haiying Wang ; Sterritt, R. ; McClean, S. ; Mayagoitia, Ruth E.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i90t-add845cf4409093ef9dbd58cd37ef6584dd9ce37d67a8c6b12a510d131c2c2373</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2011</creationdate><topic>Accelerometers</topic><topic>Accuracy</topic><topic>activity recognition</topic><topic>classification</topic><topic>Feature extraction</topic><topic>gait patterns</topic><topic>Legged locomotion</topic><topic>Machine learning</topic><topic>Predictive models</topic><topic>statistical analysis</topic><topic>Support vector machines</topic><toplevel>online_resources</toplevel><creatorcontrib>Chan, Herman</creatorcontrib><creatorcontrib>Mingjing Yang</creatorcontrib><creatorcontrib>Huiru Zheng</creatorcontrib><creatorcontrib>Haiying Wang</creatorcontrib><creatorcontrib>Sterritt, R.</creatorcontrib><creatorcontrib>McClean, S.</creatorcontrib><creatorcontrib>Mayagoitia, Ruth E.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEL</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Chan, Herman</au><au>Mingjing Yang</au><au>Huiru Zheng</au><au>Haiying Wang</au><au>Sterritt, R.</au><au>McClean, S.</au><au>Mayagoitia, Ruth E.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Machine learning and statistical approaches to assessing gait patterns of younger and older healthy adults climbing stairs</atitle><btitle>2011 Seventh International Conference on Natural Computation</btitle><stitle>ICNC</stitle><date>2011-07</date><risdate>2011</risdate><volume>1</volume><spage>588</spage><epage>592</epage><pages>588-592</pages><issn>2157-9555</issn><isbn>9781424499502</isbn><isbn>142449950X</isbn><eisbn>9781424499526</eisbn><eisbn>1424499534</eisbn><eisbn>9781424499533</eisbn><eisbn>1424499526</eisbn><abstract>The following study explores the methods for activity recognition of younger and older adults climbing stairs. There is a correlation to health and the level of activity of an individual, which has captured interest in this field in computing science to determine the level of activity of an individual. The focus of the study is the classification of younger and older gait patterns climbing up and down a set of 13 stairs. From using acceleration data from an accelerometer placed on the lumbro-sacral joint; 14 gait features are extracted and analysed. The machine learning algorithms focused in this study are Multilayer Perceptron (MLP), KStar and Support Vector Machine (SVM). An evaluation of performance among three machine learning algorithms was carried out. MLP was found to provide the highest in accuracy for classification. Accuracy of 95.7% was found for classifying a subject walking either up or down the stairs and an accuracy of 80.6% for classifying whether the subject was younger or older. An evaluation of individual features showed poor performance of classification for young and older subjects climbing up and down stairs, and at most cases failed to distinguish between the two classes. However, subsets of features were created using a sequential feature selection algorithm based on feature ranking and individual feature performance. The performance of each subset was recorded and a subset of the top four features achieved an accuracy of 81.7% for classification between young and older subjects. In comparison, 13 features were required to obtain the best performance of 95.7% to distinguish between up and down classes.</abstract><pub>IEEE</pub><doi>10.1109/ICNC.2011.6022097</doi><tpages>5</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier ISSN: 2157-9555
ispartof 2011 Seventh International Conference on Natural Computation, 2011, Vol.1, p.588-592
issn 2157-9555
language eng
recordid cdi_ieee_primary_6022097
source IEEE Electronic Library (IEL) Conference Proceedings
subjects Accelerometers
Accuracy
activity recognition
classification
Feature extraction
gait patterns
Legged locomotion
Machine learning
Predictive models
statistical analysis
Support vector machines
title Machine learning and statistical approaches to assessing gait patterns of younger and older healthy adults climbing stairs
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-04T03%3A20%3A46IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Machine%20learning%20and%20statistical%20approaches%20to%20assessing%20gait%20patterns%20of%20younger%20and%20older%20healthy%20adults%20climbing%20stairs&rft.btitle=2011%20Seventh%20International%20Conference%20on%20Natural%20Computation&rft.au=Chan,%20Herman&rft.date=2011-07&rft.volume=1&rft.spage=588&rft.epage=592&rft.pages=588-592&rft.issn=2157-9555&rft.isbn=9781424499502&rft.isbn_list=142449950X&rft_id=info:doi/10.1109/ICNC.2011.6022097&rft.eisbn=9781424499526&rft.eisbn_list=1424499534&rft.eisbn_list=9781424499533&rft.eisbn_list=1424499526&rft_dat=%3Cieee_6IE%3E6022097%3C/ieee_6IE%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i90t-add845cf4409093ef9dbd58cd37ef6584dd9ce37d67a8c6b12a510d131c2c2373%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=6022097&rfr_iscdi=true