Accelerometer and Camera-Based Strategy for Improved Human Fall Detection

Handle URI:
http://hdl.handle.net/10754/622168
Title:
Accelerometer and Camera-Based Strategy for Improved Human Fall Detection
Authors:
Zerrouki, Nabil; Harrou, Fouzi; Sun, Ying ( 0000-0001-6703-4270 ) ; Houacine, Amrane
Abstract:
In this paper, we address the problem of detecting human falls using anomaly detection. Detection and classification of falls are based on accelerometric data and variations in human silhouette shape. First, we use the exponentially weighted moving average (EWMA) monitoring scheme to detect a potential fall in the accelerometric data. We used an EWMA to identify features that correspond with a particular type of fall allowing us to classify falls. Only features corresponding with detected falls were used in the classification phase. A benefit of using a subset of the original data to design classification models minimizes training time and simplifies models. Based on features corresponding to detected falls, we used the support vector machine (SVM) algorithm to distinguish between true falls and fall-like events. We apply this strategy to the publicly available fall detection databases from the university of Rzeszow’s. Results indicated that our strategy accurately detected and classified fall events, suggesting its potential application to early alert mechanisms in the event of fall situations and its capability for classification of detected falls. Comparison of the classification results using the EWMA-based SVM classifier method with those achieved using three commonly used machine learning classifiers, neural network, K-nearest neighbor and naïve Bayes, proved our model superior.
KAUST Department:
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Citation:
Zerrouki N, Harrou F, Sun Y, Houacine A (2016) Accelerometer and Camera-Based Strategy for Improved Human Fall Detection. Journal of Medical Systems 40. Available: http://dx.doi.org/10.1007/s10916-016-0639-6.
Publisher:
Springer Nature
Journal:
Journal of Medical Systems
KAUST Grant Number:
OSR-2015-CRG4-2582.
Issue Date:
29-Oct-2016
DOI:
10.1007/s10916-016-0639-6
Type:
Article
ISSN:
0148-5598; 1573-689X
Sponsors:
We would like to thank the reviewers of this article for their insightful comments, which helped us to greatly improve its quality. The authors (Nabil Zerrouki and Amrane Houacine) would like to thank the LCPTS laboratory, Faculty of Electronics and Informatics, University of Sciences and Technology HOUARI BOUMEDIENE (USTHB) for the continued support during the research. This publication is based upon work supported by King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research (OSR) under Award No: OSR-2015-CRG4-2582.
Additional Links:
http://link.springer.com/article/10.1007%2Fs10916-016-0639-6
Appears in Collections:
Articles; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorZerrouki, Nabilen
dc.contributor.authorHarrou, Fouzien
dc.contributor.authorSun, Yingen
dc.contributor.authorHouacine, Amraneen
dc.date.accessioned2017-01-02T08:42:35Z-
dc.date.available2017-01-02T08:42:35Z-
dc.date.issued2016-10-29en
dc.identifier.citationZerrouki N, Harrou F, Sun Y, Houacine A (2016) Accelerometer and Camera-Based Strategy for Improved Human Fall Detection. Journal of Medical Systems 40. Available: http://dx.doi.org/10.1007/s10916-016-0639-6.en
dc.identifier.issn0148-5598en
dc.identifier.issn1573-689Xen
dc.identifier.doi10.1007/s10916-016-0639-6en
dc.identifier.urihttp://hdl.handle.net/10754/622168-
dc.description.abstractIn this paper, we address the problem of detecting human falls using anomaly detection. Detection and classification of falls are based on accelerometric data and variations in human silhouette shape. First, we use the exponentially weighted moving average (EWMA) monitoring scheme to detect a potential fall in the accelerometric data. We used an EWMA to identify features that correspond with a particular type of fall allowing us to classify falls. Only features corresponding with detected falls were used in the classification phase. A benefit of using a subset of the original data to design classification models minimizes training time and simplifies models. Based on features corresponding to detected falls, we used the support vector machine (SVM) algorithm to distinguish between true falls and fall-like events. We apply this strategy to the publicly available fall detection databases from the university of Rzeszow’s. Results indicated that our strategy accurately detected and classified fall events, suggesting its potential application to early alert mechanisms in the event of fall situations and its capability for classification of detected falls. Comparison of the classification results using the EWMA-based SVM classifier method with those achieved using three commonly used machine learning classifiers, neural network, K-nearest neighbor and naïve Bayes, proved our model superior.en
dc.description.sponsorshipWe would like to thank the reviewers of this article for their insightful comments, which helped us to greatly improve its quality. The authors (Nabil Zerrouki and Amrane Houacine) would like to thank the LCPTS laboratory, Faculty of Electronics and Informatics, University of Sciences and Technology HOUARI BOUMEDIENE (USTHB) for the continued support during the research. This publication is based upon work supported by King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research (OSR) under Award No: OSR-2015-CRG4-2582.en
dc.publisherSpringer Natureen
dc.relation.urlhttp://link.springer.com/article/10.1007%2Fs10916-016-0639-6en
dc.subjectFall detection and classificationen
dc.subjectVisiosurvaillanceen
dc.subjectTri axial accelerometeren
dc.subjectAnomaly detectionen
dc.subjectSupport vector machineen
dc.titleAccelerometer and Camera-Based Strategy for Improved Human Fall Detectionen
dc.typeArticleen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.identifier.journalJournal of Medical Systemsen
dc.contributor.institutionLCPTS, Faculty of Electronics and Computer ScienceUniversity of Sciences and Technology Houari Boumédienne (USTHB)AlgiersAlgeriaen
kaust.authorHarrou, Fouzien
kaust.authorSun, Yingen
kaust.grant.numberOSR-2015-CRG4-2582.en
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.