Unsupervised machine-learning method for improving the performance of ambulatory fall-detection systems.

DSpace/Manakin Repository

Search OPUS

Advanced Search


My Account

Show simple item record

dc.contributor.author Yuwono, M
dc.contributor.author Moulton, BD
dc.contributor.author Su, SW
dc.contributor.author Celler, BG
dc.contributor.author Nguyen, HT
dc.date.accessioned 2012-10-12T03:33:58Z
dc.date.issued 2012
dc.identifier.citation Biomedical engineering online, 2012, 11 pp. 9 - ?
dc.identifier.other C1 en_US
dc.identifier.uri http://hdl.handle.net/10453/18373
dc.description.abstract BACKGROUND: Falls can cause trauma, disability and death among older people. Ambulatory accelerometer devices are currently capable of detecting falls in a controlled environment. However, research suggests that most current approaches can tend to have insufficient sensitivity and specificity in non-laboratory environments, in part because impacts can be experienced as part of ordinary daily living activities. METHOD: We used a waist-worn wireless tri-axial accelerometer combined with digital signal processing, clustering and neural network classifiers. The method includes the application of Discrete Wavelet Transform, Regrouping Particle Swarm Optimization, Gaussian Distribution of Clustered Knowledge and an ensemble of classifiers including a multilayer perceptron and Augmented Radial Basis Function (ARBF) neural networks. RESULTS: Preliminary testing with 8 healthy individuals in a home environment yields 98.6% sensitivity to falls and 99.6% specificity for routine Activities of Daily Living (ADL) data. Single ARB and MLP classifiers were compared with a combined classifier. The combined classifier offers the greatest sensitivity, with a slight reduction in specificity for routine ADL and an increased specificity for exercise activities. In preliminary tests, the approach achieves 100% sensitivity on in-group falls, 97.65% on out-group falls, 99.33% specificity on routine ADL, and 96.59% specificity on exercise ADL. CONCLUSION: The pre-processing and feature-extraction steps appear to simplify the signal while successfully extracting the essential features that are required to characterize a fall. The results suggest this combination of classifiers can perform better than MLP alone. Preliminary testing suggests these methods may be useful for researchers who are attempting to improve the performance of ambulatory fall-detection systems.
dc.format Electronic
dc.language eng
dc.relation.isbasedon 10.1186/1475-925x-11-9
dc.title Unsupervised machine-learning method for improving the performance of ambulatory fall-detection systems.
dc.type Journal Article
dc.description.version Published
dc.parent Biomedical engineering online
dc.journal.volume 11
dc.journal.number en_US
dc.publocation Bethesda MD USA en_US
dc.identifier.startpage 1 en_US
dc.identifier.endpage en_US
dc.identifier.endpage 11 en_US
dc.cauo.name FEIT.School of Elec, Mech and Mechatronic Systems en_US
dc.conference Verified OK en_US
dc.for 0903 Biomedical Engineering
dc.personcode 840115
dc.personcode 997723
dc.personcode 010755
dc.personcode 112628
dc.percentage 100 en_US
dc.classification.name Biomedical Engineering en_US
dc.classification.type FOR-08 en_US
dc.edition en_US
dc.custom en_US
dc.date.activity en_US
dc.location.activity en_US
dc.description.keywords Humans
dc.description.keywords Monitoring, Ambulatory
dc.description.keywords Sensitivity and Specificity
dc.description.keywords Accidental Falls
dc.description.keywords Artificial Intelligence
dc.description.keywords Signal Processing, Computer-Assisted
dc.description.keywords Adult
dc.description.keywords Acceleration
dc.description.keywords Activities of Daily Living
dc.description.keywords Movement
dc.description.keywords Algorithms
dc.description.keywords Neural Networks (Computer)
dc.description.keywords Female
dc.description.keywords Male
pubs.embargo.period Not known
pubs.organisational-group /University of Technology Sydney
pubs.organisational-group /University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group /University of Technology Sydney/Faculty of Engineering and Information Technology/School of Elec, Mech and Mechatronic Systems
pubs.organisational-group /University of Technology Sydney/Strength - Health Technologies
utslib.copyright.status Open Access
utslib.copyright.date 2015-04-15 12:23:47.074767+10
pubs.consider-herdc true
utslib.collection.history General (ID: 2)

Files in this item

This item appears in the following Collection(s)

Show simple item record