Proceedings of the IEEK Conference (대한전자공학회:학술대회논문집)

The Institute of Electronics and Information Engineers (대한전자공학회)
권호 표지

A Neuro-Fuzzy System Reconstructing Nonlinear functions from Chaotic Signals

  • Eguchi, Kei (Dept. of Information and Computer Sciences, Kumamoto National College of Technology) ;
  • Ueno, Fumio (Dept. of Information and Computer Sciences, Kumamoto National College of Technology) ;
  • Tabata, Toru (Dept. of Information and Computer Sciences, Kumamoto National College of Technology) ;
  • Zhu, Hong-Bin (Dept. of Information and Computer Engineering, Kumamoto University) ;
  • Nagahama, Kaeko (Dept. of Information and Computer Sciences, Kumamoto National College of Technology)
  • Published : 2000.07.01
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, a neuro-fuzzy system for quantitative characterization of chaotic signals is proposed. The proposed system is differ from the previous methods in that the nonlinear functions of the nonlinear dynamical systems are calculated as the invariant factor. In the proposed neuro-fuzzy system, the nonlinear functions are determined by supervised learning. From the reconstructed nonlinear functions, the proposed system can generate extrapolated chaotic signals. This feature will help the study of nonlinear dynamical systems which require large number of chaotic data. To confirm the validity of the proposed system, nonlinear functions are reconstructed from 1-dimensional and 2-dimensional chaotic signals.

Keywords