For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Development of Non-Restraining and QOL Sensor Systems for Bed-Leaving Prediction
Hirokazu MADOKORO Nobuhiro SHIMOI Kazuhito SATO
D - Abstracts of IEICE TRANSACTIONS on Information and Systems (Japanese Edition)
Publication Date: 2013/12/01
Online ISSN: 1881-0225
Print ISSN: 1880-4535
Type of Manuscript: PAPER
bed-leaving, machine leaning, piezoelectric elements, accelerometer, quality of life,
Full Text(in Japanese): PDF(3.1MB)
>>Buy this Article
This paper present a complex multi-sensor system to predict behavior patterns that occur when patients leave their beds. Our system is consisted of three sensors: pad sensors installed under a bed mat, a pillow sensor to detect movements of the head, and a bolt vibration sensor bind a handrail to the bed. We used piezoelectric elements for pad sensors and a bolt vibration sensor and a tri-axial accelerometer for a pillow sensor. The features of these sensors are easy installation, low cost, high reliability, and toughness. Moreover, we developed a method to recognize bed-leaving behaviors using machine learning algorithms of two types from signals obtained using the sensors. We evaluated our system for three subject at an environment that represents a clinical site. The recognition accuracy for seven behavior patterns was 84.1%. Moreover, the recognition accuracies for longitudinal sitting, terminal sitting and complete leaved were 100%. In contrast, false recognized patterns were remained inside of respective categories of sleeping and sitting on the bed. We consider that our system can apply to an actual environment as a novel sensor system with no requirement of patient restraint.