Automatic Calibration of Bed-Leaving Sensor Signals Based on Genetic Evolutionary Learning
Daiju Hiramatsu, Hirokazu Madokoro, Kazuhito Sato, Kazuhisa Nakasho, Nobuhiro Shimoi · International Conference on Control, Automation and Systems · 2018
This paper presents a method to generate filters for shaping sensor signals using genetic network programming (GNP) for automatic calibration to absorb individual differences. In our previous study, we developed a prototype that incorporates bed-leaving detection sensors using piezoelectric films and a machine-learning-based behavior recognition method using counter-propagation networks (CPNs). The system can learn topology and relations between input features and teaching signals. However, our method based on CPNs was insufficient to address individual differences in parameters such as weight and height used for bed-learning behavior recognition. For this study, we actualize automatic calibration of sensor signals for invariance relative to these body parameters. This paper presents two experimentally obtained results obtained using sensor signals obtained in our previous study. For the preliminary experiment, we optimized the original sensor signals to approximate high-accuracy ideal sensor signals using generated filters. We used fitness to assess the difference between original signal patterns and ideal signal patterns. For the application experiment, we used fitness calculated from the recognition accuracy of CPNs. The experimentally obtained results reveal that the mean accuracy improved 6.53 percentage point for three datasets.