Presentation 2002/3/12
Development of the Diagnostic System for the Prescription of Chinese Medicines by Neural Network
Takuro OGASAWARA, Takahide MATSUOKA, Toshiaki TAKEDA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In order to assist diagnosis for prescription of Chinese medicines, learning of neural network was applied to register input-output relation of diagnosis preserving generalizing ability. Matrix type prescription table were implemented in 3-layered neural network with back-propagation algorithm. Seventy-seven diseases were induded in individual network separately. Suitable numbers of hidden-layer units were studied to find best parameter for generalization. Following step is to develop "Kanpo prescription-aid net" with helpful GUI for medical practice.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Diagnostic system / Chinese herb medicine / Neural network / Multi-layer net / Diagnosing matrix / Number of hidden layer units
Paper # MBE2001-189
Date of Issue

Conference Information
Committee MBE
Conference Date 2002/3/12(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 ME and Bio Cybernetics (MBE)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Development of the Diagnostic System for the Prescription of Chinese Medicines by Neural Network
Sub Title (in English)
Keyword(1) Diagnostic system
Keyword(2) Chinese herb medicine
Keyword(3) Neural network
Keyword(4) Multi-layer net
Keyword(5) Diagnosing matrix
Keyword(6) Number of hidden layer units
1st Author's Name Takuro OGASAWARA
1st Author's Affiliation Faculty of Engineering, Utsunomiya University()
2nd Author's Name Takahide MATSUOKA
2nd Author's Affiliation Faculty of Engineering, Utsunomiya University
3rd Author's Name Toshiaki TAKEDA
3rd Author's Affiliation Jichi Medical School, School of Nursing
Date 2002/3/12
Paper # MBE2001-189
Volume (vol) vol.101
Number (no) 734
Page pp.pp.-
#Pages 5
Date of Issue