A Human Condition Monitoring System using Fuzzified Neural Networks and MEMS Devices

Abstract

In this paper, we propose a human condition monitoring system using a small lightweight MEMS device. While MEMS device can measure several kinds of data, we use data from three-axis acceleration and ECG. Some of the measured data are used for training of fuzzified neural networks(FNN). Then long-term monitoring data are evaluated by the trained FNN. From the outputs of the trained FNN we estimate subject's physical condition.