Preliminary results on the effect of sensor position on unobtrusive rollover detection for sleep monitoring in smart homes

Annu Int Conf IEEE Eng Med Biol Soc. 2009;2009:6135-8. doi: 10.1109/IEMBS.2009.5334690.


Older adults experience increased sleep movement disorders and sleep fragmentation, and these are associated with serious health consequences such as falls. Monitoring sleep fragmentation and restlessness in older adults can reveal information about their daily and long-term health status. Long-term home monitoring is only realistic within the contact of unobtrusive, non-contact sensors. This paper presents exploratory work using the pressure sensor array as an instrument for rollover detection. The sensor output is used to calculate a center of gravity signal, from which five features are extracted. These features are used in a decision tree to classify detected movements in two categories; rollovers and other movements. Rollovers were detected with a sensitivity and specificity of 82% and 100% respectively, and a Mathew's correlation coefficient of 0.86 when data from all sensor positions were included. Intrapositional and interpositional effects of movements on sensors placed throughout the bed are described.

Publication types

  • Comparative Study
  • Evaluation Study
  • Research Support, Non-U.S. Gov't

MeSH terms

  • Accidental Falls / prevention & control*
  • Actigraphy / instrumentation*
  • Actigraphy / methods
  • Equipment Design
  • Equipment Failure Analysis
  • Humans
  • Pilot Projects
  • Polysomnography / instrumentation*
  • Polysomnography / methods
  • Reproducibility of Results
  • Sensitivity and Specificity
  • Transducers*