Presentation | 1995/5/19 Extraction properties of frequency components in time series signals for Sandglass Neural Network Hiroki Yoshimura, Kazuhiro Sugata, Naoki Isu, Tadaaki Shimizu, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | The mulitlayer perceptron called by Sandglass Neural Network, whose input layer and output layer have the same number of units and hidden layer has less units than input and output layer, is considered to perform data compression for input signals. We made clear the extraction properties of frequency components in time series signals for Sandglass Neural Network. This Sandglass Neural Network with two hidden units can extracts maximum power component from the numerous frequency components. In this extraction scheme, input signals are transformed by DFT between the input layer and the hidden layer and by IDFT between the hidden layer and the output layer. Connection weights have the function of a revolving facter of DFT. Furthermore, we proposed the cascade model of Sandgalss Neural Networks with two hidden units to pick up the frequency components one after another in order of their power. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | neural network / time series signal / principal component analysis / data compression / DFT |
Paper # | |
Date of Issue |
Conference Information | |
Committee | NLP |
---|---|
Conference Date | 1995/5/19(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) | Extraction properties of frequency components in time series signals for Sandglass Neural Network |
Sub Title (in English) | |
Keyword(1) | neural network |
Keyword(2) | time series signal |
Keyword(3) | principal component analysis |
Keyword(4) | data compression |
Keyword(5) | DFT |
1st Author's Name | Hiroki Yoshimura |
1st Author's Affiliation | Department of Information and Knowledge Engineering, Tottori University() |
2nd Author's Name | Kazuhiro Sugata |
2nd Author's Affiliation | Department of Information and Knowledge Engineering, Tottori University |
3rd Author's Name | Naoki Isu |
3rd Author's Affiliation | Department of Information and Knowledge Engineering, Tottori University |
4th Author's Name | Tadaaki Shimizu |
4th Author's Affiliation | Department of Information and Knowledge Engineering, Tottori University |
Date | 1995/5/19 |
Paper # | |
Volume (vol) | vol.95 |
Number (no) | 47 |
Page | pp.pp.- |
#Pages | 8 |
Date of Issue |