Nonlinear modeling of physiological systems with multiple inputs

被引：0

作者：

Mitsis, GD ^{[1
]}

Marmarelis, VZ ^{[1
]}

机构：

[1] Univ So Calif, Dept Biomed Engn, Los Angeles, CA 90089 USA

来源：

SECOND JOINT EMBS-BMES CONFERENCE 2002, VOLS 1-3, CONFERENCE PROCEEDINGS: BIOENGINEERING - INTEGRATIVE METHODOLOGIES, NEW TECHNOLOGIES | 2002年

关键词：

Volterra models; nonlinear modeling; multiple-input systems;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Effective modeling of nonlinear dynamic systems can be achieved by employing Laguerre expansions and feedforward artificial neural networks in the form of the Laguerre-Volterra network (LVN). In this paper an extension of the LVN methodology to multiple-input systems is presented. Results from simulated systems show that this method can yield accurate nonlinear models of multiple-input Volterra systems, even when considerable noise is present.

引用

页码：21 / 22

页数：2

共 3 条

[1] IDENTIFICATION OF NONLINEAR BIOLOGICAL-SYSTEMS USING LAGUERRE EXPANSIONS OF KERNELS [J].

MARMARELIS, VZ .

ANNALS OF BIOMEDICAL ENGINEERING, 1993, 21 (06) :573-589

[2] Volterra models and three-layer perceptrons [J].

Marmarelis, VZ ;

Zhao, X .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1997, 8 (06) :1421-1433

[3] Modeling of nonlinear physiological systems with fast and slow dynamics. 1. Methodology [J].

Mitsis, GD ;

Marmarelis, VZ .

ANNALS OF BIOMEDICAL ENGINEERING, 2002, 30 (02) :272-281

← 1 →