Εμφάνιση απλής εγγραφής

dc.creatorTasoulis, S. K.en
dc.creatorDoukas, C. N.en
dc.creatorMaglogiannis, I.en
dc.creatorPlagianakos, V. P.en
dc.date.accessioned2015-11-23T10:49:33Z
dc.date.available2015-11-23T10:49:33Z
dc.date.issued2011
dc.identifier10.1109/IEMBS.2011.6090632
dc.identifier.isbn9781424441211
dc.identifier.issn1557170X
dc.identifier.urihttp://hdl.handle.net/11615/33572
dc.description.abstractThe analysis of human motion data is interesting for the purpose of activity recognition or emergency event detection, especially in the case of elderly or disabled people living independently in their homes. Several techniques have been proposed for identifying such distress situations using either motion, audio or video sensors on the monitored subject (wearable sensors) or the surrounding environment. The output of such sensors is data streams that require real time recognition, especially in emergency situations, thus traditional classification approaches may not be applicable for immediate alarm triggering or fall prevention. This paper presents a statistical mining methodology that may be used for the specific problem of real time fall detection. Visual data captured from the user's environment, using overhead cameras along with motion data are collected from accelerometers on the subject's body and are fed to the fall detection system. The paper includes the details of the stream data mining methodology incorporated in the system along with an initial evaluation of the achieved accuracy in detecting falls. © 2011 IEEE.en
dc.source.urihttp://www.scopus.com/inward/record.url?eid=2-s2.0-84055198840&partnerID=40&md5=4fb8348149fb8119fe25f388c1c3b366
dc.subjectActivity recognitionen
dc.subjectAlarm triggeringen
dc.subjectAssistiveen
dc.subjectClassification approachen
dc.subjectData streamen
dc.subjectDisabled peopleen
dc.subjectEmergency situationen
dc.subjectEvent detectionen
dc.subjectFall detectionen
dc.subjectFall preventionen
dc.subjectHuman motion dataen
dc.subjectMotion dataen
dc.subjectReal timeen
dc.subjectReal time recognitionen
dc.subjectSpecific problemsen
dc.subjectStatistical datasen
dc.subjectStream data miningen
dc.subjectSurrounding environmenten
dc.subjectVideo sensorsen
dc.subjectVisual dataen
dc.subjectWearable sensorsen
dc.subjectAccelerometersen
dc.subjectData miningen
dc.subjectHandicapped personsen
dc.subjectSensorsen
dc.subjectAccident preventionen
dc.titleStatistical data mining of streaming motion data for fall detection in assistive environmentsen
dc.typeconferenceItemen


Αρχεία σε αυτό το τεκμήριο

ΑρχείαΜέγεθοςΤύποςΠροβολή

Δεν υπάρχουν αρχεία που να σχετίζονται με αυτό το τεκμήριο.

Αυτό το τεκμήριο εμφανίζεται στις ακόλουθες συλλογές

Εμφάνιση απλής εγγραφής