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 |