心電図に対するニューロンネットワークの非線形予測能力の評価(一般講演1A)

抄録

Old drivers on vehicles of cars, trains and airplanes, etc. are increasing in our aged society advancing today. Therefore it's expected that the probability occurred of a serious accident by incapacitation of an old driver will be high. The analytical result of ECG is indispensable as the indicator to stop accidents of this kind from happening. The purpose of this paper is to estimate the model to solve general nonlinear predictability problems taking the case of an ECG. The models to evaluate comparison are a non-recursion type 1st-order Volterra neuron network (N1VNN) and a non-recursion type Volterra neuron network (NVNN) of discrete time. The result is which the NVNN is better than the N1 VNN.