Skip to Main content Skip to Navigation
Journal articles

3DCane: a monitoring system for the elderly using a connected walking stick

Abstract : fall related injuries caused have become a leading cause of fatalities among the elderly. Lots of aging people rely on a cane as a help device to overcome such problems as balance loss and leg weakness, presumed to be at the origin of many fall incidents. In this respect, the internet of things may turn out to be critically helpful, by offering disabled people the assistance and support necessary for achieving a good quality of life and allowing them to participate in the social and economic activities. In this paper, a 3DCane design is depicted, with an implementation for the CANet project, a system whereby a comprehensive monitoring of disabled people can be maintained through the use of their connected walking stick. Actually, the 3Dcane is modeled through consideration of real-time movements for a thorough understanding of the concerned person's state, including fall detection. To note, the 3DCane applies a multi-stage thresholding framework based on an accelerometer. Experiments have revealed that the fall-detection algorithm appears to be robust in term of detection rate and false positive rate.
Complete list of metadatas

Cited literature [16 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01475038
Contributor : Open Archive Toulouse Archive Ouverte (oatao) <>
Submitted on : Thursday, February 23, 2017 - 2:15:11 PM
Last modification on : Thursday, November 12, 2020 - 10:26:03 AM
Long-term archiving on: : Wednesday, May 24, 2017 - 1:59:48 PM

File

lachtar_17144.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01475038, version 1
  • OATAO : 17144

Citation

Abdelfetteh Lachtar, Thierry Val, Abdennaceur Kachouri. 3DCane: a monitoring system for the elderly using a connected walking stick. International Journal of Computer Science and Information Security, IJCSIS, 2016, vol. 14 (n° 8), pp. 1-8. ⟨hal-01475038⟩

Share

Metrics

Record views

308

Files downloads

930