Journal article
Two-Stage Mixed Discrete-Continuous Identification of Radial Basis Function (RBF) Neural Models for Nonlinear Systems
IEEE transactions on circuits and systems. I, Regular papers, Vol.56(3), pp.630-643
03/2009
DOI: 10.1109/TCSI.2008.2002545
Abstract
The identification of nonlinear dynamic systems using radial basis function (RBF) neural models is studied in this paper. Given a model selection criterion, the main objective is to effectively and efficiently build a parsimonious compact neural model that generalizes well over unseen data. This is achieved by simultaneous model structure selection and optimization of the parameters over the continuous parameter space. It is a mixed-integer hard problem, and a unified analytic framework is proposed to enable an effective and efficient two-stage mixed discrete-continuous identification procedure. This novel framework combines the advantages of an iterative discrete two-stage subset selection technique for model structure determination and the calculus-based continuous optimization of the model parameters. Computational complexity analysis and simulation studies confirm the efficacy of the proposed algorithm.
Details
- Title: Subtitle
- Two-Stage Mixed Discrete-Continuous Identification of Radial Basis Function (RBF) Neural Models for Nonlinear Systems
- Creators
- Kang Li - Sch. of Electron., Queen's Univ. Belfast, BelfastJian-Xun Peng - Sch. of Electron., Queen's Univ. Belfast, BelfastEr-Wei Bai - Dept. of Electr. & Comput. Eng., Univ. of Iowa, Iowa City, IA
- Resource Type
- Journal article
- Publication Details
- IEEE transactions on circuits and systems. I, Regular papers, Vol.56(3), pp.630-643
- Publisher
- IEEE
- DOI
- 10.1109/TCSI.2008.2002545
- ISSN
- 1549-8328
- eISSN
- 1558-0806
- Language
- English
- Date published
- 03/2009
- Academic Unit
- Electrical and Computer Engineering
- Record Identifier
- 9984083222502771
Metrics
12 Record Views