Academic Journals Database
Disseminating quality controlled scientific knowledge

A system for improving fall detection performance using critical phase fall signal and a neural network

Author(s): Patimakorn Jantaraprim | Pornchai Phukpattaranont | Chusak Limsakul | Booncharoen Wongkittisuksa

Journal: Songklanakarin Journal of Science and Technology
ISSN 0125-3395

Volume: 34;
Issue: 6;
Start page: 637;
Date: 2012;
VIEW PDF   PDF DOWNLOAD PDF   Download PDF Original page

Keywords: fall detection | critical phase | short time min-max feature | accelerometer | neural network

We present a system for improving fall detection performance using a short time min-max feature based on the specificsignatures of critical phase fall signal and a neural network as a classifier. Two subject groups were tested: Group A involvingfalls and activities by young subjects; Group B testing falls by young and activities by elderly subjects. The performance wasevaluated by comparing the short time min-max with a maximum peak feature using a feed-forward backpropagation networkwith two-fold cross validation. The results, obtained from 672 sequences, show that the proposed method offers a betterperformance for both subject groups. Group B’s performance is higher than Group A’s. The best performances are 98.2%sensitivity and 99.3% specificity for Group A, and 99.4% sensitivity and 100% specificity for Group B. The proposed systemuses one sensor for a body’s position, without a fixed threshold for 100% sensitivity or specificity and without additionalprocessing of posture after a fall.
RPA Switzerland

RPA Switzerland

Robotic process automation


Tango Rapperswil
Tango Rapperswil