Full metadata record
DC FieldValueLanguage
dc.contributor.authorLiu, Chien-Liangen_US
dc.contributor.authorLee, Chia-Hoangen_US
dc.contributor.authorLin, Ping-Minen_US
dc.date.accessioned2014-12-08T15:48:13Z-
dc.date.available2014-12-08T15:48:13Z-
dc.date.issued2010-10-01en_US
dc.identifier.issn0957-4174en_US
dc.identifier.urihttp://dx.doi.org/10.1016/j.eswa.2010.04.014en_US
dc.identifier.urihttp://hdl.handle.net/11536/32136-
dc.description.abstractThe main purpose of this paper is to use off-the-shelf devices to develop a fall detection system. In human body identification, human body silhouette is adopted to improve privacy protection, and vertical projection histograms of the silhouette image and statistical scheme are used to reduce the effect of human body upper limb activities. The kNN classification algorithm is used to classify the postures using the ratio and difference of human body silhouette bounding box height and width. Meanwhile, since time difference is a vital factor to differentiate fall incident event and lying down event, the critical time difference is obtained from the experiment and verified by statistical hypothesis testing. With the help of the kNN classifier and the critical time difference, a fall incident detection system is developed to detect fall incident events. The experiment shows that it could reduce the effect of upper limb activities and the system has a correct rate of 84.44% on fall detection and lying down event detection. (C) 2010 Elsevier Ltd. All rights reserved.en_US
dc.language.isoen_USen_US
dc.subjectArtificial intelligenceen_US
dc.subjectMachine learningen_US
dc.subjectkNNen_US
dc.subjectFall detectionen_US
dc.titleA fall detection system using k-nearest neighbor classifieren_US
dc.typeArticleen_US
dc.identifier.doi10.1016/j.eswa.2010.04.014en_US
dc.identifier.journalEXPERT SYSTEMS WITH APPLICATIONSen_US
dc.citation.volume37en_US
dc.citation.issue10en_US
dc.citation.spage7174en_US
dc.citation.epage7181en_US
dc.contributor.department資訊工程學系zh_TW
dc.contributor.departmentDepartment of Computer Scienceen_US
Appears in Collections:Articles


Files in This Item:

  1. 000279408200052.pdf