Applications of waist segment kinematic measurement using accelerometry for an autonomous fall-detection system during continuous activities
Applications of waist segment kinematic measurement using accelerometry for an autonomous fall-detection system during continuous activities
- Author(s): A.K. Bourke ; P. van de Ven ; M. Gamble ; R. O'Connor ; K. Murphy ; E. Bogan ; E. McQuade ; P. Finucane ; G. ÓLaighin ; J. Nelson
- DOI: 10.1049/cp.2010.0512
For access to this article, please select a purchase option:
Buy conference paper PDF
Buy Knowledge Pack
IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.
IET Irish Signals and Systems Conference (ISSC 2010) — Recommend this title to your library
Thank you
Your recommendation has been sent to your librarian.
- Author(s): A.K. Bourke ; P. van de Ven ; M. Gamble ; R. O'Connor ; K. Murphy ; E. Bogan ; E. McQuade ; P. Finucane ; G. ÓLaighin ; J. Nelson Source: IET Irish Signals and Systems Conference (ISSC 2010), 2010 p. 198 – 203
- Conference: IET Irish Signals and Systems Conference (ISSC 2010)
- DOI: 10.1049/cp.2010.0512
- ISBN: 978 1 84919 252 1
- Location: Cork, Ireland
- Conference date: 23-24 June 2010
- Format: PDF
Through the measurement and thresholding of different kinematic and angular signals, from the waist using accelerometry, distinguishing between simulated falls and normal scripted and continuous, unscripted activates was performed and evaluated using these signals. Different combinations of individual signal thresholding algorithms were used to compile a suite of Fall-detection algorithms suitable for an autonomous waist worn system. The suite of algorithms were tested against a comprehensive data-set recorded from 10 young healthy subjects performing 240 falls and 120 activities of daily living and 10 elderly healthy subjects performing 240 scripted and 52.4 hours of continuous unscripted normal activities. Results show that using a simple algorithm employing IMPACT+POSTURE+VELOCITY can achieve a low false-positive rate of less than 1 FP/day (0.94FPs/day) with a sensitivity of 94.6% and a specificity of 100%. The algorithms were tested using continuous unsupervised activities performed by elderly healthy subjects, which is the target environment for a fall detection device.
Inspec keywords: anthropometry; accelerometers; biomechanics; biomedical measurement
Subjects: Velocity, acceleration and rotation measurement; Velocity, acceleration and rotation measurement; Biomedical engineering; Biomedical measurement and imaging; Biomechanics, biorheology, biological fluid dynamics
Related content
content/conferences/10.1049/cp.2010.0512
pub_keyword,iet_inspecKeyword,pub_concept
6
6