Automatic Calibration of Piezoelectric Bed-Leaving Sensor Signals Using Genetic Network Programming Algorithms

This paper presents a filter generating method that modifies sensor signals using genetic network programming (GNP) for automatic calibration to absorb individual differences. For our earlier study, we developed prototype incorporates bed-leaving detection sensors piezoelectric films and machine-learning-based behavior recognition counter-propagation networks (CPNs). Our learns topology relations between input features teaching signals. Nevertheless, CPNs have been insufficient address differences in parameters such as weight height used bed-learning recognition. this actualize of invariance relative these body parameters. two experimentally obtained results from study. They were low-accuracy the preliminary experiment, optimized original approximate high-accuracy ideal generated filters. We fitness assess signal patterns patterns. application experiments, calculated accuracy CPNs. The reveal improved mean accuracies three datasets.