By Topic

Design of an unobtrusive wireless sensor network for nighttime falls detection

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

5 Author(s)
Zhaonan Zhang ; Sch. of Electr. Eng., Univ. of New South Wales, Sydney, NSW, Australia ; Kapoor, U. ; Narayanan, M. ; Lovell, N.H.
more authors

A significant portion of government health care funding is spent treating falls-related injuries among older adults. This cost is set to rise due to population aging in developed societies. Wearable sensors systems, often comprised of triaxial accelerometers and/or gyroscopes, have proven useful for real-time falls detection. However, a large percentage of falls occur at home and many of those happen at nighttime, when the person is unlikely to be wearing such an ambulatory monitoring device. It is envisaged that systems utilizing unobtrusive wireless sensors can be employed to survey the living space and identify unusual activity patterns which may indicate that a fall has happened at nighttime. In this study, a nighttime falls detection system designed for a single individual living at home, based on the use of passive infrared and pressure mat sensors, is explored. This paper describes both the sensor and system design, and investigates the feasibility of performing nighttime falls detection through the use of scripted scenarios using a single healthy test volunteer. In addition to normal movement activity, falls with unconsciousness, falls with repeated failed attempts to recover, and falls with successful recovery, are considered. By analyzing the location of sensor activity, periods of sensor inactivity, and unusual sensor activation patterns in uncommon locations, a sensitivity and specificity of 88.89% and 100%, respectively, are obtained (excluding falls followed by complete recovery). This demonstrates a proof-of-principle that nighttime falls detection might be achieved using a low complexity and completely unobtrusive wireless sensor network in the home.

Published in:

Engineering in Medicine and Biology Society, EMBC, 2011 Annual International Conference of the IEEE

Date of Conference:

Aug. 30 2011-Sept. 3 2011