In-bed posture classification and limb identification
- 1 October 2014
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21634025,p. 133-136
Abstract
We propose an algorithm that uses pressure image data to detect a person's sleeping posture and identifies different body limbs. Our algorithm can be used in monitoring bed-bound patients and assessing the risk of pressure ulceration. We used a GMM-based clustering approach for concurrent posture classification and limb identification. Our proposed technique, applied on 9 healthy subjects instructed to sleep in 13 different postures, resulted in 98.4% classification accuracy in distinguishing three main stable sleeping postures. Additionally, 8 limbs in supine and 5 limbs in left/right side postures were identified with the overall accuracy of 91.6%.Keywords
This publication has 7 references indexed in Scilit:
- Detecting high-risk regions for pressure ulcer risk assessment2013
- A dense pressure sensitive bedsheet design for unobtrusive sleep posture monitoring2013
- A Resource-Efficient Planning for Pressure Ulcer PreventionIEEE Transactions on Information Technology in Biomedicine, 2012
- Continuous plantar pressure modeling using sparse sensors2012
- Finding and tracking people from the bottom up2003
- Hands-on Morphological Image Processing2003
- Speaker Verification Using Adapted Gaussian Mixture ModelsDigital Signal Processing, 2000