Presentation 2001/3/10
Classification and prediction of complex data by nonlinear local reference of prototypical examples
Takaya Miyano, Takako Tsutsui, Yoichi Seki, Hitoshi Taniguchi,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) An adaptive nonlinear local approximation technique based on the method originally introduced by Sugihara and May for chaotic time series prediction is applied to a classification problem of care needs certification for the long-term care insurance system and to a regression problem of forecasting nursing time of patients at acute care units of hospitals. The approximating model searches for similar examples to the situation of a current elderly person or patient from a library data base for reference, making an inference about the corresponding care class or nursing time by virtue of a nonlinear and additive combination of the basis examples. The present approach may capture reality of actual decision-making dependent on precedent examples.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) long-term care / need for nursing / local nonlinear approximation / inductive inference
Paper # NLP2000-173
Date of Issue

Conference Information
Committee NLP
Conference Date 2001/3/10(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) Classification and prediction of complex data by nonlinear local reference of prototypical examples
Sub Title (in English)
Keyword(1) long-term care
Keyword(2) need for nursing
Keyword(3) local nonlinear approximation
Keyword(4) inductive inference
1st Author's Name Takaya Miyano
1st Author's Affiliation Hirosaki University()
2nd Author's Name Takako Tsutsui
2nd Author's Affiliation National Institute of Public Health
3rd Author's Name Yoichi Seki
3rd Author's Affiliation Gunma University
4th Author's Name Hitoshi Taniguchi
4th Author's Affiliation Chihaya T3 Corporation
Date 2001/3/10
Paper # NLP2000-173
Volume (vol) vol.100
Number (no) 681
Page pp.pp.-
#Pages 8
Date of Issue