Fall detection by a SVM-based cloud system with motion sensorsd

Chien Hui Liao*, Kuan Wei Lee, Ting Hua Chen, Che Chen Chang, Charles H.P. Wen

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Scopus citations

Abstract

Recently, fall detection has become a popular research topic to take care of the increasing aging population. Many previous works used cameras, acceler-ometers and gyroscopes as sensor devices to collect motion data of human beings and then to distinguish falls from other normal behaviors of human beings. However, these techniques encountered some challenges such as privacy, accuracy, convenience and data-processing time. In this paper, a motion sensor which can compress motion data into skeleton points effectively meanwhile providing privacy and convenience are chosen as the sensor devices for detecting falls. Furthermore, to achieve high accuracy of fall detection, support vector machine (SVM) is employed in the proposed cloud system. Experimental results show that, under the best setting, the accuracy of our fall-detection SVM model can be greater than 99.90 %. In addition, the detection time of falls only takes less than 10- 3 s. Therefore, the proposed SVM-based cloud system with motion sensors successfully enables fall detection at real time with high accuracy.

Original languageEnglish
Title of host publicationAdvanced Technologies, Embedded and Multimedia for Human-Centric Computing, HumanCom and EMC 2013
Pages37-45
Number of pages9
DOIs
StatePublished - 17 Feb 2014
EventAdvanced Technologies, Embedded and Multimedia for Human-Centric Computing, HumanCom and EMC 2013 - , Taiwan
Duration: 23 Aug 201325 Aug 2013

Publication series

NameLecture Notes in Electrical Engineering
Volume260 LNEE
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Conference

ConferenceAdvanced Technologies, Embedded and Multimedia for Human-Centric Computing, HumanCom and EMC 2013
CountryTaiwan
Period23/08/1325/08/13

Keywords

  • Cloud computing
  • Fall detection
  • Kinect
  • Support vector machine (SVM)

Fingerprint Dive into the research topics of 'Fall detection by a SVM-based cloud system with motion sensorsd'. Together they form a unique fingerprint.

  • Cite this

    Liao, C. H., Lee, K. W., Chen, T. H., Chang, C. C., & Wen, C. H. P. (2014). Fall detection by a SVM-based cloud system with motion sensorsd. In Advanced Technologies, Embedded and Multimedia for Human-Centric Computing, HumanCom and EMC 2013 (pp. 37-45). (Lecture Notes in Electrical Engineering; Vol. 260 LNEE). https://doi.org/10.1007/978-94-007-7262-55