Continuous eight-posture classification for bed-bound patients

Abstract

Pressure ulcer is a prevalent complication for bed-bound patients who are not able to shift their body weights over time. Continuous monitoring of patient's postures in the bed can be helpful for caregivers in order to keep track of patient's movements and quality of their repositioning during a day. This information allows hospitals to plan an effective repositioning schedule for each patient. In this paper, a high speed and robust posture classification algorithm is proposed that can be employed in any pervasive patient's monitoring system. First, a whole-body pressure image is recorded using a commercial pressure mat system. Image enhancement is then applied to the raw pressure images and a binary signature for each different posture is constructed. Finally, using a binary pattern matching technique, a given posture can be classified to one of the known posture classes. Our extensive experiments show that the proposed algorithm is able to predict in-bed postures with more than 97% average accuracy.