Loading…

Differentiating assisted and unassisted bed exits using ultrasonic sensor

Monitoring bed exits is critical for establishing the mobility trend of a person. Sensors such as pressure sensitive mats have been used to monitor symmetry and timing of a sit to stand transfer to establish a mobility trend. In an uncontrolled setting, the timing and symmetry measurements for sit-t...

Full description

Saved in:
Bibliographic Details
Main Authors: Pouliot, M., Joshi, V., Chauvin, J., Goubran, R., Knoefel, F.
Format: Conference Proceeding
Language:English
Subjects:
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Monitoring bed exits is critical for establishing the mobility trend of a person. Sensors such as pressure sensitive mats have been used to monitor symmetry and timing of a sit to stand transfer to establish a mobility trend. In an uncontrolled setting, the timing and symmetry measurements for sit-to-stand transfers may be affected by friends, family and caregivers providing assistance during such transfer. It is of significant importance to differentiate assisted and unassisted transfers in order to accurately establish a mobility trend. This paper will use unobtrusive ultrasound sensors in order to monitor the presence of another person during the sit-to-stand transition. This paper will examine different sensor placements in order to optimize the detection area and minimize the undetected cases. A lab simulation was performed in a controlled setting comparing the different configurations. The optimal solution was verified in a hospital setting to maximize the detection of assisted vs. unassisted transfers. The results show an 86.2% coverage of the hospital room and an 80% successful detection rate of a third party. This allows for detection of assisted sit-to-stand transfer if the third party is present within this coverage area. We also demonstrate how passive infrared sensors (PIR) can be integrated in the proposed system to enhance room entry and exit detection.
ISSN:1091-5281
DOI:10.1109/I2MTC.2012.6229388