Intelligent optimal recursive neural network method of time series prediction

A recursive neural network and intelligent optimization technology, applied in biological neural network models, reasoning methods, neural architectures, etc., can solve problems such as unrealistic long-term predictions and limit the effect of long-term predictions, and achieve the effect of expanding diversity

Inactive Publication Date: 2015-08-19
XIAMEN UNIV
View PDF0 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Chaos prediction theory holds that: on the one hand, the deterministic characteristics of chaos make many seemingly random appearances actually predictable; on the other hand, the inherent extreme sensitivity of chaotic p

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Intelligent optimal recursive neural network method of time series prediction
  • Intelligent optimal recursive neural network method of time series prediction
  • Intelligent optimal recursive neural network method of time series prediction

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0031] The present invention will be further described below in conjunction with the drawings and embodiments (prediction of the Shanghai Composite Index sequence).

[0032] Calculate the time series attractor dimension D of the Shanghai Composite Index by the saturated correlation dimension (G-P) method, and select the embedding dimension m> =2D+1; According to the needs of the prediction step size, the corresponding time delay τ is selected to reconstruct the phase space.

[0033] The structure of the RPNN network is uniquely determined by the embedding dimension m, and the number of nodes is the same as m. Suppose RPNN has n nodes, and the network input is X → ( t ) = ( x ( t ) , x ( t - τ ) , . . . , x ( t - ( n - 1 ) τ ) ) T , The output of the network is:

[0034] y j ( t ) = σ j ( x j ( t ) + b j ( t ) + X i = 1 j ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention provides an intelligent optimal recursive neural network method of time series prediction, and relates to time series prediction analysis. A time series prediction model based on recurrent predictor neural network (RPNN) combined with a simulated annealing particle swarm optimization (SAPSO) algorithm takes chaos and phase-space reconstruction as theoretical basis so as to realize nonlinear time series prediction. The method comprises the steps of calculating time series attractor dimensionality by a saturated correlation dimension method, and carrying out phase-space reconstruction by selecting embedded dimension and delaying time. The structure of the RPNN is only decided by the embedded dimension, and the SAPSO hybrid optimization algorithm is adopted by network training. The SAPSO algorithm is combined with the rapid convergence characteristic of a PSO algorithm and the complete searching characteristic of an SA algorithm; the method is capable of expanding the optimal searching range while maintaining the rate of convergence, so that the aim of not falling into local extremum is realized; the intelligent optimal recursive neural network method is mainly used for the nonlinear time series prediction.

Description

technical field [0001] The invention relates to time series prediction analysis, in particular to an intelligent optimization recursive neural network method for time series prediction. Background technique [0002] The analysis and prediction of time series has important application value in many fields. However, most of the linear models used in the early time series forecast analysis have certain limitations in theory and method. Most systems have complex nonlinear characteristics. The introduction of nonlinear research paradigms to analyze and predict time series, and approximate description of chaotic dynamical systems through nonlinear iteration and learning models is the inevitable result of the development of nonlinear time series forecasting theory. [0003] Chaos is one of the nonlinear characteristics of time series. Chaos prediction theory holds that: on the one hand, the deterministic characteristics of chaos make many seemingly random appearances actually pre...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06N3/04G06N5/04
Inventor 孟力高鑫刘曦毕业平
Owner XIAMEN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap