ニューラルネットワークによる吟醸酒の官能評価値から総合評価値の推定

Translated title of the contribution: Estimation of Total Evaluation from Sensory Evaluation of Sake (Ginjo) Using a Neural Network

各務 彰洋, 花井 泰三, 本多 裕之, 西田 淑男, 深谷 伊和男, 小林 猛

Research output: Contribution to journal › Article

Abstract

This paper discusses modeling of the total evaluation process of sake (Ginjo) using a neural network (NN) and multiple regression analysis (MRA). In each method, the total evaluation of 61 Ginjo samples was estimated from data sets of the sensory evaluations of 7 characteristics. The values of the performance index, J, based on errors between actual and estimated values were smaller in the NN model than in MRA. In particular, the NN model with 3 input variables selected from the 7 characteristics evaluated had a simple structure and the J value was sufficiently low. Samples with a large error were found to have the characteristic of "extraordinary flavor". Addition of "extraordinary flavor" as a new input variable in the NN decreased the error of the model. The results suggested that 4 variables (color, flavor base, aging and extraordinary flavor) are important in the total evaluation of Ginjo, and that a nonlinear modeling method such as a NN is effective in analyzing the sensory evaluation process.
Original languageJapanese
Pages (from-to)199-205
Number of pages7
JournalSeibutsu-kogaku Kaishi
Volume73
Issue number3
Publication statusPublished - 1995

Fingerprint

sake
neural networks
sensory evaluation
flavor
Neural Networks (Computer)
regression analysis
Regression Analysis
Color
sampling
color
methodology

Cite this

各務彰洋, 花井泰三, 本多裕之, 西田淑男, 深谷伊和男, & 小林猛 (1995). ニューラルネットワークによる吟醸酒の官能評価値から総合評価値の推定. Seibutsu-kogaku Kaishi, 73(3), 199-205.

ニューラルネットワークによる吟醸酒の官能評価値から総合評価値の推定. / 各務彰洋; 花井泰三; 本多裕之; 西田淑男; 深谷伊和男; 小林猛.

In: Seibutsu-kogaku Kaishi, Vol. 73, No. 3, 1995, p. 199-205.

Research output: Contribution to journal › Article

各務彰洋, 花井泰三, 本多裕之, 西田淑男, 深谷伊和男 & 小林猛 1995, 'ニューラルネットワークによる吟醸酒の官能評価値から総合評価値の推定', Seibutsu-kogaku Kaishi, vol. 73, no. 3, pp. 199-205.
各務彰洋, 花井泰三, 本多裕之, 西田淑男, 深谷伊和男, 小林猛. ニューラルネットワークによる吟醸酒の官能評価値から総合評価値の推定. Seibutsu-kogaku Kaishi. 1995;73(3):199-205.
各務彰洋 ; 花井泰三 ; 本多裕之 ; 西田淑男 ; 深谷伊和男 ; 小林猛. / ニューラルネットワークによる吟醸酒の官能評価値から総合評価値の推定. In: Seibutsu-kogaku Kaishi. 1995 ; Vol. 73, No. 3. pp. 199-205.
@article{136a28e24bf3415f8d7ac49106175ad0,
title = "ニューラルネットワークによる吟醸酒の官能評価値から総合評価値の推定",
abstract = "This paper discusses modeling of the total evaluation process of sake (Ginjo) using a neural network (NN) and multiple regression analysis (MRA). In each method, the total evaluation of 61 Ginjo samples was estimated from data sets of the sensory evaluations of 7 characteristics. The values of the performance index, J, based on errors between actual and estimated values were smaller in the NN model than in MRA. In particular, the NN model with 3 input variables selected from the 7 characteristics evaluated had a simple structure and the J value was sufficiently low. Samples with a large error were found to have the characteristic of {"}extraordinary flavor{"}. Addition of {"}extraordinary flavor{"} as a new input variable in the NN decreased the error of the model. The results suggested that 4 variables (color, flavor base, aging and extraordinary flavor) are important in the total evaluation of Ginjo, and that a nonlinear modeling method such as a NN is effective in analyzing the sensory evaluation process.",
author = "彰洋 各務 and 泰三 花井 and 裕之 本多 and 淑男 西田 and 伊和男 深谷 and 猛 小林",
year = "1995",
language = "Japanese",
volume = "73",
pages = "199--205",
journal = "Seibutsu-kogaku Kaishi",
issn = "0919-3758",
publisher = "日本生物工学会",
number = "3",

}

TY - JOUR

T1 - ニューラルネットワークによる吟醸酒の官能評価値から総合評価値の推定

AU - 各務, 彰洋

AU - 花井, 泰三

AU - 本多, 裕之

AU - 西田, 淑男

AU - 深谷, 伊和男

AU - 小林, 猛

PY - 1995

Y1 - 1995

N2 - This paper discusses modeling of the total evaluation process of sake (Ginjo) using a neural network (NN) and multiple regression analysis (MRA). In each method, the total evaluation of 61 Ginjo samples was estimated from data sets of the sensory evaluations of 7 characteristics. The values of the performance index, J, based on errors between actual and estimated values were smaller in the NN model than in MRA. In particular, the NN model with 3 input variables selected from the 7 characteristics evaluated had a simple structure and the J value was sufficiently low. Samples with a large error were found to have the characteristic of "extraordinary flavor". Addition of "extraordinary flavor" as a new input variable in the NN decreased the error of the model. The results suggested that 4 variables (color, flavor base, aging and extraordinary flavor) are important in the total evaluation of Ginjo, and that a nonlinear modeling method such as a NN is effective in analyzing the sensory evaluation process.

AB - This paper discusses modeling of the total evaluation process of sake (Ginjo) using a neural network (NN) and multiple regression analysis (MRA). In each method, the total evaluation of 61 Ginjo samples was estimated from data sets of the sensory evaluations of 7 characteristics. The values of the performance index, J, based on errors between actual and estimated values were smaller in the NN model than in MRA. In particular, the NN model with 3 input variables selected from the 7 characteristics evaluated had a simple structure and the J value was sufficiently low. Samples with a large error were found to have the characteristic of "extraordinary flavor". Addition of "extraordinary flavor" as a new input variable in the NN decreased the error of the model. The results suggested that 4 variables (color, flavor base, aging and extraordinary flavor) are important in the total evaluation of Ginjo, and that a nonlinear modeling method such as a NN is effective in analyzing the sensory evaluation process.

M3 - 記事

VL - 73

SP - 199

EP - 205

JO - Seibutsu-kogaku Kaishi

JF - Seibutsu-kogaku Kaishi

SN - 0919-3758

IS - 3

ER -

Access to Document