Improved Non Linear Time Series Forecasting Using Non Linear Analysis Techniques and RBF Neural Networks for MRS Signals and Chaotic Diode Resonator Circuits

Abstract

A novel non linear signal prediction method is presented using non linear signal analysis and deterministic chaos techniques in combination with Radial Basis Functions (RBF) Neural Networks for diode resonator chaotic circuits, used in industrial processes, as well as for Magnetic Resonance Spectroscopy (MRS) processes. The Time series analysis is performed by the method proposed by Grasberger and Procaccia, involving estimation of the correlation and minimum embedding dimension as well as of the corresponding Kolmogorov entropy. These parameters are used to construct the first stage of a one step / multistep predictor while an RBF Artificial Neural Network (ANN) is involved in the second stage to enhance prediction results. The novelty of the proposed two stage predictor lies on that the RBF ANN is employed as a second order predictor, that is, as an error predictor of the non-linear signal analysis stage application. This novel two stage predictor is evaluated through an extensive experimental study for both resonator circuits for industrial processes as well as for MRS signals in a preliminary stage of analysis. Different types of Neural Networks are compared as well.