Show simple item record

dc.contributor.authorMartinez, Matthew
dc.contributor.authorDe Leon, Phillip L.
dc.date.accessioned2017-06-15T23:05:40Z
dc.date.available2017-06-15T23:05:40Z
dc.date.issued2016-11
dc.identifier.issn0884-5123
dc.identifier.issn0074-9079
dc.identifier.urihttp://hdl.handle.net/10150/624183
dc.description.abstractAs the population ages, prediction of falls risk is becoming an increasingly important research area. Due to built-in inertial sensors and ubiquity, smartphones provide an at- tractive data collection and computing platform for falls risk prediction and continuous gait monitoring. One challenge in continuous gait monitoring is that signi cant signal variability exists between individuals with a high falls risk and those with low-risk. This variability increases the di cultly in building a universal system which segments and labels changes in signal state. This paper presents a method which uses unsu- pervised learning techniques to automatically segment a gait signal by computing the dissimilarity between two consecutive windows of data, applying an adaptive threshold algorithm to detect changes in signal state, and using a rule-based gait recognition al- gorithm to label the data. Using inertial data,the segmentation algorithm is compared against manually segmented data and is capable of achieving recognition rates greater than 71.8%.
dc.description.sponsorshipInternational Foundation for Telemeteringen
dc.language.isoen_USen
dc.publisherInternational Foundation for Telemeteringen
dc.relation.urlhttp://www.telemetry.org/en
dc.rightsCopyright © held by the author; distribution rights International Foundation for Telemeteringen
dc.subjectfalls risken
dc.subjectgaiten
dc.subjectaccelerometeren
dc.subjectmachine learningen
dc.subjectsmartphone appen
dc.titleUnsupervised Segmentation and Labeling for Smartphone Acquired Gait Dataen_US
dc.typetexten
dc.typeProceedingsen
dc.contributor.departmentNew Mexico State University, Klipsch School of Elec. & Comp. Eng.en
dc.contributor.departmentSandia National Laboratoriesen
dc.identifier.journalInternational Telemetering Conference Proceedingsen
dc.description.collectioninformationProceedings from the International Telemetering Conference are made available by the International Foundation for Telemetering and the University of Arizona Libraries. Visit http://www.telemetry.org/index.php/contact-us if you have questions about items in this collection.en
refterms.dateFOA2018-08-13T17:40:06Z
html.description.abstractAs the population ages, prediction of falls risk is becoming an increasingly important research area. Due to built-in inertial sensors and ubiquity, smartphones provide an at- tractive data collection and computing platform for falls risk prediction and continuous gait monitoring. One challenge in continuous gait monitoring is that signi cant signal variability exists between individuals with a high falls risk and those with low-risk. This variability increases the di cultly in building a universal system which segments and labels changes in signal state. This paper presents a method which uses unsu- pervised learning techniques to automatically segment a gait signal by computing the dissimilarity between two consecutive windows of data, applying an adaptive threshold algorithm to detect changes in signal state, and using a rule-based gait recognition al- gorithm to label the data. Using inertial data,the segmentation algorithm is compared against manually segmented data and is capable of achieving recognition rates greater than 71.8%.


Files in this item

Thumbnail
Name:
ITC_2016_16-03-01.pdf
Size:
415.5Kb
Format:
PDF
Description:
Conference Proceedings

This item appears in the following Collection(s)

Show simple item record