Optimal accelerometer placement for fall detection of rehabilitation patients

Suriani, Nor Surayahani and Nor Rashid, Fadilla ‘Atyka and Yunos, Nur Yuzailin (2018) Optimal accelerometer placement for fall detection of rehabilitation patients. Journal of Telecommunication, Electronic and Computer Engineering, 10 (2-5). pp. 25-29. ISSN 2289-8131

Text AJ 2019 (52).pdf Restricted to Registered users only Download (434kB) | Request a copy

Abstract

The development of health monitoring system using wearable sensor has lots of potential in the field of rehabilitation and gained lots of attention in the scientific community and industry. The aim and motivation in this field are to focus on the application of wearable technology to monitor elderly or rehab patients in home-based settings to reduce resources and development cost. The wearable sensor such as accelerometer used to emphasise the clinical applications of fall detection during rehabilitation treatment. This paper is intended to determine the optimal sensor placement especially for lower limb activity during rehabilitation exercise. Accelerometer data were collected from three different body locations (hip, thigh, and foot). The lower limb activities involve normal movements such as walking, lifting, sit-to-stand, and stairs. Other unexpected activity such as falls might occur during normal lower limb exercise movement. Then, acceleration data for various lower limbs activities was classified using k-NN and SVM classifier. The result found that the hip was the best location to record data for lower limb activities including when fall occurs.

Item Type:	Article
Uncontrolled Keywords:	NIL
Subjects:	R Medicine > RC Internal medicine T Technology > TA Engineering (General). Civil engineering (General) > TA164 Bioengineering
Divisions:	Faculty of Electrical and Electronic Engineering > Department of Electronic Enngineering
Depositing User:	Miss Afiqah Faiqah Mohd Hafiz
Date Deposited:	16 Nov 2021 03:47
Last Modified:	16 Nov 2021 03:47
URI:	http://eprints.uthm.edu.my/id/eprint/2875

Actions (login required)

View Item