A New Approach for Chaotic Time Series Prediction Using Recurrent Neural Network

A New Approach for Chaotic Time Series Prediction Using Recurrent Neural Network

A self-constructing fuzzy neural network (SCFNN) has been successfully used for chaotic time series prediction in the literature. In this paper, we propose the strategy of adding a recurrent path in each node of the hidden layer of SCFNN, resulting in a self-constructing recurrent fuzzy neural netwo...

Full description

Bibliographic Details
Main Authors: Qinghai Li, Rui-Chang Lin
Format: Article
Language:English
Published: Hindawi Limited 2016-01-01
Series:Mathematical Problems in Engineering
Online Access:http://dx.doi.org/10.1155/2016/3542898
id doaj-a1d4c4cb5cf245bbab86e7591f6ac5f8
record_format Article
spelling doaj-a1d4c4cb5cf245bbab86e7591f6ac5f82020-11-25T00:35:47ZengHindawi LimitedMathematical Problems in Engineering1024-123X1563-51472016-01-01201610.1155/2016/35428983542898A New Approach for Chaotic Time Series Prediction Using Recurrent Neural NetworkQinghai Li0Rui-Chang Lin1Department of Electronic Engineering, Zhejiang Industry and Trade Vocational College, East Road 717, Wenzhou 325003, ChinaDepartment of Electronic Engineering, Zhejiang Industry and Trade Vocational College, East Road 717, Wenzhou 325003, ChinaA self-constructing fuzzy neural network (SCFNN) has been successfully used for chaotic time series prediction in the literature. In this paper, we propose the strategy of adding a recurrent path in each node of the hidden layer of SCFNN, resulting in a self-constructing recurrent fuzzy neural network (SCRFNN). This novel network does not increase complexity in fuzzy inference or learning process. Specifically, the structure learning is based on partition of the input space, and the parameter learning is based on the supervised gradient descent method using a delta adaptation law. This novel network can also be applied for chaotic time series prediction including Logistic and Henon time series. More significantly, it features rapider convergence and higher prediction accuracy.http://dx.doi.org/10.1155/2016/3542898
collection DOAJ
language English
format Article
sources DOAJ
author Qinghai Li
Rui-Chang Lin
spellingShingle Qinghai Li
Rui-Chang Lin
A New Approach for Chaotic Time Series Prediction Using Recurrent Neural Network
Mathematical Problems in Engineering
author_facet Qinghai Li
Rui-Chang Lin
author_sort Qinghai Li
title A New Approach for Chaotic Time Series Prediction Using Recurrent Neural Network
title_short A New Approach for Chaotic Time Series Prediction Using Recurrent Neural Network
title_full A New Approach for Chaotic Time Series Prediction Using Recurrent Neural Network
title_fullStr A New Approach for Chaotic Time Series Prediction Using Recurrent Neural Network
title_full_unstemmed A New Approach for Chaotic Time Series Prediction Using Recurrent Neural Network
title_sort new approach for chaotic time series prediction using recurrent neural network
publisher Hindawi Limited
series Mathematical Problems in Engineering
issn 1024-123X
1563-5147
publishDate 2016-01-01
description A self-constructing fuzzy neural network (SCFNN) has been successfully used for chaotic time series prediction in the literature. In this paper, we propose the strategy of adding a recurrent path in each node of the hidden layer of SCFNN, resulting in a self-constructing recurrent fuzzy neural network (SCRFNN). This novel network does not increase complexity in fuzzy inference or learning process. Specifically, the structure learning is based on partition of the input space, and the parameter learning is based on the supervised gradient descent method using a delta adaptation law. This novel network can also be applied for chaotic time series prediction including Logistic and Henon time series. More significantly, it features rapider convergence and higher prediction accuracy.
url http://dx.doi.org/10.1155/2016/3542898
work_keys_str_mv AT qinghaili anewapproachforchaotictimeseriespredictionusingrecurrentneuralnetwork
AT ruichanglin anewapproachforchaotictimeseriespredictionusingrecurrentneuralnetwork
AT qinghaili newapproachforchaotictimeseriespredictionusingrecurrentneuralnetwork
AT ruichanglin newapproachforchaotictimeseriespredictionusingrecurrentneuralnetwork
_version_ 1725307679369330688

Similar Items