Title

Data driven modeling based on dynamic parsimonious fuzzy neural network

Publication Type

Journal Article

Publication Date

6-2013

Abstract

In this paper, a novel fuzzy neural network termed as dynamic parsimonious fuzzy neural network (DPFNN) is proposed. DPFNN is a four layers network, which features coalescence between TSK (Takagi-Sugeno-Kang) fuzzy architecture and multivariate Gaussian kernels as membership functions. The training procedure is characterized by four aspects: (1) DPFNN may evolve fuzzy rules as new training datum arrives, which enables to cope with non-stationary processes. We propose two criteria for rule generation: system error and c-completeness reflecting both a performance and sample coverage of an existing rule base. (2) Insignificant fuzzy rules observed over time based on their statistical contributions are pruned to truncate the rule base complexity and redundancy. (3) The extended self organizing map (ESOM) theory is employed to dynamically update the centers of the ellipsoidal basis functions in accordance with input training samples. (4) The optimal fuzzy consequent parameters are updated by time localized least square (TLLS) method that exploits a concept of sliding window in order to reduce the computational burden of the least squares (LS) method. The viability of the new method is intensively investigated based on real-world and artificial problems as it is shown that our method not only arguably delivers more compact and parsimonious network structures, but also achieves lower predictive errors than state-of-the-art approaches.

Keywords

Dynamic parsimonious fuzzy neural network (DPFNN), Radial basis function (RBF), Self organizing map (SOM), Rule growing, Rule pruning

Discipline

Computer Sciences | Databases and Information Systems

Research Areas

Data Management and Analytics

Publication

Neurocomputing

Volume

110

First Page

18

Last Page

28

ISSN

0925-2312

Identifier

10.1016/j.neucom.2012.11.013

Publisher

Elsevier

Additional URL

http://dx.doi.org/10.1016/j.neucom.2012.11.013

This document is currently not available here.

Share

COinS