Presentation 2006-11-13
Learning and Prediction of Environmental Time Series Data with Chaos Recurrent Neural Network
Tomoaki HOTAKA, Masahiro NAKAGAWA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this report, it proposes the recurrent neural network that uses the chaos neuron as a method of the prediction of chaos or fractal time series. And, it's shown that the prediction of the environmental time series is also possible by the use of this prediction method by applying to fallen snow data. Consequently, the Predict error has become small to about one digit using the Chaos neuron more than using the Sigmoid neuron. Moreover, it was shown that the prediction of an actual environmental time series was also possible by doing learning and the prediction of the fallen snow data. In addition, the prediction accuracy can be improved by dividing the fallen snow data into the trend component and the difference data, and composing another network in each time series.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Recurrent Neural Network / Periodic Chaos Neuron / Time Series Prediction
Paper # NLP2006-75
Date of Issue

Conference Information
Committee NLP
Conference Date 2006/11/6(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Nonlinear Problems (NLP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Learning and Prediction of Environmental Time Series Data with Chaos Recurrent Neural Network
Sub Title (in English)
Keyword(1) Recurrent Neural Network
Keyword(2) Periodic Chaos Neuron
Keyword(3) Time Series Prediction
1st Author's Name Tomoaki HOTAKA
1st Author's Affiliation Department of Electrical Engineering, Nagaoaka University of Technology()
2nd Author's Name Masahiro NAKAGAWA
2nd Author's Affiliation Department of Electrical Engineering, Nagaoaka University of Technology
Date 2006-11-13
Paper # NLP2006-75
Volume (vol) vol.106
Number (no) 344
Page pp.pp.-
#Pages 6
Date of Issue