A homotopy approach to improving PEM identification of ARMAX models

Authors:
Jinglu Hu;Kotaro Hirasawa;Kousuke Kumamaru
Affiliations:
Department of Electrical and Electronic Systems Engineering, Kyushu University, Hakozaki 6-10-1, Higashi-ku, Fukuoka 812-8581, Japan;Department of Electrical and Electronic Systems Engineering, Kyushu University, Hakozaki 6-10-1, Higashi-ku, Fukuoka 812-8581, Japan;Department of Control Engineering and Science, Kyushu Institute of Technology, Kawazu 680-4, Iizuka 820, Japan
Venue:
Automatica (Journal of IFAC)
Year:
2001

Citing 13
Cited 0

A hybrid algorithm for finding the global minimum of error function of neural networks and its applications

Neural Networks
Algorithm 652: HOMPACK: a suite of codes for globally convergent homotopy algorithms

ACM Transactions on Mathematical Software (TOMS)
Nonlinear black-box modeling in system identification: a unified overview

Automatica (Journal of IFAC) - Special issue on trends in system identification
On Tikhonov regularization, bias and variance in nonlinear system identification

Automatica (Journal of IFAC)
Genetic Algorithms in Search, Optimization and Machine Learning

Genetic Algorithms in Search, Optimization and Machine Learning
An unbiased equation error identifier and reduced-orderapproximations

IEEE Transactions on Signal Processing
Bias-remedy least mean square equation error algorithm for IIRparameter recursive estimation

IEEE Transactions on Signal Processing
Globally optimal rational approximation using homotopy continuationmethods

IEEE Transactions on Signal Processing
The composite regressor algorithm for IIR adaptive systems

IEEE Transactions on Signal Processing
A relationship between the recursive least squares update andhomotopy continuation methods

IEEE Transactions on Signal Processing
Hybrid methods using genetic algorithms for global optimization

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Artificial parameter homotopy methods for the DC operating point problem

IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
On a natural homotopy between linear and nonlinear single-layer networks

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	22.14

Visualization

Abstract

Homotopy methods are applied to the non-convex optimization problem that arises in prediction error estimation using ARMAX model structures. A concrete algorithm is proposed, and its performance is studied by Monte Carlo simulation.