Facial reconstruction

Search LJMU Research Online

Browse Repository | Browse E-Theses

Adaptive structure radial basis function network model for processes with operating region migration

Tok, DKS, Yu, DL, Mathews, C, Zhao, D-Y and Zhu, Q-M (2014) Adaptive structure radial basis function network model for processes with operating region migration. Neurocomputing, 155. pp. 186-193. ISSN 0925-2312

[img]
Preview
Text
NEUCOM-S-14-01087.pdf - Accepted Version
Available under License Creative Commons Attribution Non-commercial No Derivatives.

Download (465kB) | Preview

Abstract

An adaptive structure radial basis function (RBF) network model is proposed in this paper to model nonlinear processes with operating region migration. The recursive orthogonal least squares algorithm is adopted to select new centers on-line, as well as to train the network weights. Based on the R matrix in the orthogonal decomposition, an initial center bank is formed and updated in each sample period. A new learning strategy is proposed to gain information from the new data for network structure adaptation. A center grouping algorithm is also developed to divide the centers into active and non-active groups, so that a structure with a smaller size is maintained in the final network model. The proposed RBF model is evaluated and compared to the two fixed-structure RBF networks by modeling a nonlinear time-varying numerical example. The results demonstrate that the proposed adaptive structure model is capable of adapting its structure to fit the operating region of the process effectively with a more compact structure and it significantly outperforms the two fixed structure RBF models.

Item Type: Article
Uncontrolled Keywords: 08 Information And Computing Sciences, 09 Engineering, 17 Psychology And Cognitive Sciences
Subjects: B Philosophy. Psychology. Religion > BF Psychology
Q Science > QA Mathematics > QA75 Electronic computers. Computer science
T Technology > T Technology (General)
Divisions: Electronics and Electrical Engineering
Maritime and Mechanical Engineering
Publisher: Elsevier
Related URLs:
Date Deposited: 06 Nov 2018 10:35
Last Modified: 06 Nov 2018 10:37
DOI or Identification number: 10.1016/j.neucom.2014.12.030
URI: http://researchonline.ljmu.ac.uk/id/eprint/2046

Actions (login required)

View Item View Item