Abstract
Automatic human health diagnosis measuring living body signals is expected to play a very important role in an aged society. A dramatic progress of remote monitoring and wearable computer technology is considered to be the foundation of such a technology. Aiming at the development of automatic human health diagnosis systems, we start developing a nonlinear multivariate analysis method for living body signals using a multilayer neural network. As the first step, we discuss a neural network-based algorithm to capture time varying signal measured from a living body under a normal health condition.
