Elman network with embedded memory for system identification

KALINLI A., Sagiroglu S.

JOURNAL OF INFORMATION SCIENCE AND ENGINEERING, vol.22, no.6, pp.1555-1568, 2006 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 22 Issue: 6
  • Publication Date: 2006
  • Journal Name: JOURNAL OF INFORMATION SCIENCE AND ENGINEERING
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.1555-1568
  • Keywords: Elman network, Jordan network, dynamic system identification, multi-system identification, embedded memory, RECURRENT NEURAL-NETWORKS
  • Middle East Technical University Affiliated: No

Abstract

This paper presents a new recurrent neural network (RNN) structure called ENEM for dynamic system identification. ENEM structure is based on Elman network and NARX neural network. In order to show the performance of ENEM for system identification, the results were also compared to the results of Elman network, Jordan network and their modified models. The identification results of linear and nonlinear systems have shown that the proposed ENEM structure is better than the other results of RNN models.