Nursing and Health Vol. 1(2), pp. 36 - 45
DOI: 10.13189/nh.2013.010204
Reprint (PDF) (947Kb)


Bed-Leaving Detection Using Piezoelectric Unrestrained Sensors and Its Measurement System Regarding QOL


Hirokazu Madokoro*, Nobuhiro Shimoi, Kazuhito Sato
Faculty of Systems Science and Technology, Akita Prefectural University, 84-4, Tsuchiya Aza Ebinokuchi, Yurihonjo City, Akita, 015-0055, Japan

ABSTRACT

This paper presents a sensor system that predicts behavior patterns that occur when a patient leaves a bed. We originally developed plate-shaped sensors using piezoelectric elements. Existing sensors such as clip sensors and mat sensors require that patients be restrained. The features of our sensors are that they require no power supply or patient restraint for privacy problems. Moreover, we developed machine-learning algorithms to predict behavior patterns without setting thresholds. We evaluated our system for ten subjects at an experimental environment constructed in reference to a clinical site. The mean recognition accuracy was 75.0% for seven behavior patterns. Especially, the recognition accuracies of lateral sitting and terminal sitting were 90.0% and 96.7%, respectively. We consider that these capabilities are useful for bed-leaving prediction in practical use.

KEYWORDS
Piezoelectric Elements, Bed-leaving Prediction, Self-Organizing Maps, Counter Propagation Networks

Cite This Paper in IEEE or APA Citation Styles
(a). IEEE Format:
[1] Hirokazu Madokoro , Nobuhiro Shimoi , Kazuhito Sato , "Bed-Leaving Detection Using Piezoelectric Unrestrained Sensors and Its Measurement System Regarding QOL," Nursing and Health, Vol. 1, No. 2, pp. 36 - 45, 2013. DOI: 10.13189/nh.2013.010204.

(b). APA Format:
Hirokazu Madokoro , Nobuhiro Shimoi , Kazuhito Sato (2013). Bed-Leaving Detection Using Piezoelectric Unrestrained Sensors and Its Measurement System Regarding QOL. Nursing and Health, 1(2), 36 - 45. DOI: 10.13189/nh.2013.010204.