Posture Estimation for Bed Monitoring System Using RFID
Kazuhisa Nakasho, Chiaki Kohama, Kenta Sawada, Katsumi Wasaki, Nobuhiro Shimoi · 2023
In Japan, the proportion of the population aged 65 or older has escalated to 28.8%, intensifying the issue of elderly wandering. Concurrently, there has been a surge in incidents involving seniors falling from their beds, necessitating prompt detection and intervention in the healthcare and nursing sectors. Various bed departure sensors and monitoring systems have been suggested to address this issue. In this study, we introduce an RFID-based bed monitoring system tailored for the elderly and delineate a methodology for classifying in-bed postures using machine learning. Our previous research indicated a decline in posture recognition accuracy when the individual in the training data differed from the one in the testing data. In this study, we examine inter-individual differences by projecting subject data onto a two-dimensional space, and explore the reasons behind the diminished recognition accuracy observed in prior research. Furthermore, we discuss future directions for enhancing the posture recognition rate.