神经网络模型识别出的人类二氧化碳分压控制系统中的非线性。

Nonlinearity identified by neural network models in Pco2 control system in humans.

作者信息

Fukuoka Y, Noshiro M, Shindo H, Minamitani H, Ishikawa M

机构信息

Division of Electronic Engineering, Tokyo Medical and Dental University, Japan.

出版信息

Med Biol Eng Comput. 1997 Jan;35(1):33-9. doi: 10.1007/BF02510389.

DOI:10.1007/BF02510389

PMID:9136188

Abstract

The nonlinearity included in the PCO2 control system in humans is evaluated using the degree of nonlinearity based on a difference of residuals. An autoregressive moving average (ARMA) model and neural networks (linear and nonlinear) are employed to model the system, and three types of network (Jordan, Elman and fully interconnected) are compared. As the Jordan-type linear network cannot approximate respiratory data accurately, the other two types and the ARMA model are used for the evaluation of the nonlinearity. The results of the evaluation indicate that the linear assumption for the PCO2 control system is invalid for three subjects out of seven. In particular, strong nonlinearity was observed for two subjects.

摘要

利用基于残差差异的非线性度对人体PCO₂控制系统中的非线性进行评估。采用自回归移动平均（ARMA）模型和神经网络（线性和非线性）对该系统进行建模，并比较了三种类型的网络（乔丹型、埃尔曼型和全互连型）。由于乔丹型线性网络不能准确逼近呼吸数据，因此使用另外两种类型的网络和ARMA模型来评估非线性。评估结果表明，七名受试者中有三名受试者的PCO₂控制系统的线性假设无效。特别是，观察到两名受试者存在强非线性。