Presentation 2003/1/28
Meteorological data classification and submodels estimation by competitive modular networks
Mitsutoshi SAITO, Tetsuo FURUKAWA, Syozo YASUI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The meteorological data classification method using competitive modular networks is proposed. The method is used in conjunction with a set of multilayer-perceptron models. A large number of monthly meteorological data collected from various areas of Japan are processed to obtain meteorological types. The results give some insight into region-season coupled changes. A study was also made by replacing the perceptron models by a simple recurrent network, in order to deal with the time series data more directly for better understanding of the underlying dynamcal aspects.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) competitive modular networks / time series models / meteorological classification
Paper # NC2002-131
Date of Issue

Conference Information
Committee NC
Conference Date 2003/1/28(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 Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Meteorological data classification and submodels estimation by competitive modular networks
Sub Title (in English)
Keyword(1) competitive modular networks
Keyword(2) time series models
Keyword(3) meteorological classification
1st Author's Name Mitsutoshi SAITO
1st Author's Affiliation Graduate School of Life Science and Systems Engineering, Kyushu Institute of Technology()
2nd Author's Name Tetsuo FURUKAWA
2nd Author's Affiliation Faculty of Computer Science and Systems Engineering, Kyushu Institute of Technology
3rd Author's Name Syozo YASUI
3rd Author's Affiliation Graduate School of Life Science and Systems Engineering, Kyushu Institute of Technology
Date 2003/1/28
Paper # NC2002-131
Volume (vol) vol.102
Number (no) 628
Page pp.pp.-
#Pages 5
Date of Issue