Modeling of Total Evaluation Process of <i>Ginjo sake</i> Using a Fuzzy Neural Network

Taizo Hanai, Akihiro Kakamu, Hiroyuki Honda, Takeshi Furuhashi, Yoshiki Uchikawa, Takeshi Kobayashi

Research output: Contribution to journalArticle

Abstract

A modeling of total evaluation process of <i>sake(Ginjo)</i> was studied using a fuzzy neural network(FNN). Total evaluation of 61 <i>Ginjo</i> samples was estimated from each data set of 7 sensory evaluations. The values of performance index, <i>J</i>, based on the errors between actual and estimated values in FNN model were used for the evaluation of model. In FNN model with all 7 input variables, <i>J</i> value was 0.025 and it was almost similar to that of NN model as reported previously. The FNN model with 3 variables (color, flavor base and aging) selected previously was also tested, and <i>J</i> value (0.023) was also almost similar to that of NN model (<i>J</i>=0.024). To optimize the input variables and the number of membership functions, Parameter Increasing Method (PIM) was applied to the part of premise in FNN model. The FNN model obtained was constructed with 2 membership functions for color, 3 for flavor top, 2 for flavor base and 3 for hard-soft, and <i>J</i> value of 0.013 was fairy small. From analysis of connection weight of the FNN obtained, the acquired rules were easily described in the form of IF-THEN rule. Extraordinary flavor was added as a new input variable to above 3 FNNs. <i>J</i> values in all models decreased furthermore and especially the FNN with 3 variables and extraordinary flavor was found to show the lowest <i>J</i> value (0.010). It was concluded that 4 variables (color, flavor top, aging, extraordinary flavor) were important in the total evaluation of <i>Ginjo</i>. The results suggest that the fuzzy modeling using a FNN is effective on the analysis of sensory evaluation process.
Original languageEnglish
Pages (from-to)1113-1120
Number of pages8
JournalTransactions of the Society of Instrument and Control Engineers
Volume32
Issue number7
DOIs
Publication statusPublished - 1996

Fingerprint

sake
neural networks
flavor
sensory evaluation
color

Cite this

Modeling of Total Evaluation Process of <i>Ginjo sake</i> Using a Fuzzy Neural Network. / Hanai, Taizo; Kakamu, Akihiro; Honda, Hiroyuki; Furuhashi, Takeshi; Uchikawa, Yoshiki; Kobayashi, Takeshi.

In: Transactions of the Society of Instrument and Control Engineers, Vol. 32, No. 7, 1996, p. 1113-1120.

Research output: Contribution to journalArticle

Hanai, Taizo ; Kakamu, Akihiro ; Honda, Hiroyuki ; Furuhashi, Takeshi ; Uchikawa, Yoshiki ; Kobayashi, Takeshi. / Modeling of Total Evaluation Process of <i>Ginjo sake</i> Using a Fuzzy Neural Network. In: Transactions of the Society of Instrument and Control Engineers. 1996 ; Vol. 32, No. 7. pp. 1113-1120.
@article{68e9377dd7b4475e8dc0675397c47c61,
title = "Modeling of Total Evaluation Process of Ginjo sake Using a Fuzzy Neural Network",
abstract = "A modeling of total evaluation process of sake(Ginjo) was studied using a fuzzy neural network(FNN). Total evaluation of 61 Ginjo samples was estimated from each data set of 7 sensory evaluations. The values of performance index, J, based on the errors between actual and estimated values in FNN model were used for the evaluation of model. In FNN model with all 7 input variables, J value was 0.025 and it was almost similar to that of NN model as reported previously. The FNN model with 3 variables (color, flavor base and aging) selected previously was also tested, and J value (0.023) was also almost similar to that of NN model (J=0.024). To optimize the input variables and the number of membership functions, Parameter Increasing Method (PIM) was applied to the part of premise in FNN model. The FNN model obtained was constructed with 2 membership functions for color, 3 for flavor top, 2 for flavor base and 3 for hard-soft, and J value of 0.013 was fairy small. From analysis of connection weight of the FNN obtained, the acquired rules were easily described in the form of IF-THEN rule. Extraordinary flavor was added as a new input variable to above 3 FNNs. J values in all models decreased furthermore and especially the FNN with 3 variables and extraordinary flavor was found to show the lowest J value (0.010). It was concluded that 4 variables (color, flavor top, aging, extraordinary flavor) were important in the total evaluation of Ginjo. The results suggest that the fuzzy modeling using a FNN is effective on the analysis of sensory evaluation process.",
author = "Taizo Hanai and Akihiro Kakamu and Hiroyuki Honda and Takeshi Furuhashi and Yoshiki Uchikawa and Takeshi Kobayashi",
year = "1996",
doi = "10.9746/sicetr1965.32.1113",
language = "English",
volume = "32",
pages = "1113--1120",
journal = "Transactions of the Society of Instrument and Control Engineers",
issn = "0453-4654",
publisher = "公益社団法人 計測自動制御学会",
number = "7",

}

TY - JOUR

T1 - Modeling of Total Evaluation Process of Ginjo sake Using a Fuzzy Neural Network

AU - Hanai, Taizo

AU - Kakamu, Akihiro

AU - Honda, Hiroyuki

AU - Furuhashi, Takeshi

AU - Uchikawa, Yoshiki

AU - Kobayashi, Takeshi

PY - 1996

Y1 - 1996

N2 - A modeling of total evaluation process of sake(Ginjo) was studied using a fuzzy neural network(FNN). Total evaluation of 61 Ginjo samples was estimated from each data set of 7 sensory evaluations. The values of performance index, J, based on the errors between actual and estimated values in FNN model were used for the evaluation of model. In FNN model with all 7 input variables, J value was 0.025 and it was almost similar to that of NN model as reported previously. The FNN model with 3 variables (color, flavor base and aging) selected previously was also tested, and J value (0.023) was also almost similar to that of NN model (J=0.024). To optimize the input variables and the number of membership functions, Parameter Increasing Method (PIM) was applied to the part of premise in FNN model. The FNN model obtained was constructed with 2 membership functions for color, 3 for flavor top, 2 for flavor base and 3 for hard-soft, and J value of 0.013 was fairy small. From analysis of connection weight of the FNN obtained, the acquired rules were easily described in the form of IF-THEN rule. Extraordinary flavor was added as a new input variable to above 3 FNNs. J values in all models decreased furthermore and especially the FNN with 3 variables and extraordinary flavor was found to show the lowest J value (0.010). It was concluded that 4 variables (color, flavor top, aging, extraordinary flavor) were important in the total evaluation of Ginjo. The results suggest that the fuzzy modeling using a FNN is effective on the analysis of sensory evaluation process.

AB - A modeling of total evaluation process of sake(Ginjo) was studied using a fuzzy neural network(FNN). Total evaluation of 61 Ginjo samples was estimated from each data set of 7 sensory evaluations. The values of performance index, J, based on the errors between actual and estimated values in FNN model were used for the evaluation of model. In FNN model with all 7 input variables, J value was 0.025 and it was almost similar to that of NN model as reported previously. The FNN model with 3 variables (color, flavor base and aging) selected previously was also tested, and J value (0.023) was also almost similar to that of NN model (J=0.024). To optimize the input variables and the number of membership functions, Parameter Increasing Method (PIM) was applied to the part of premise in FNN model. The FNN model obtained was constructed with 2 membership functions for color, 3 for flavor top, 2 for flavor base and 3 for hard-soft, and J value of 0.013 was fairy small. From analysis of connection weight of the FNN obtained, the acquired rules were easily described in the form of IF-THEN rule. Extraordinary flavor was added as a new input variable to above 3 FNNs. J values in all models decreased furthermore and especially the FNN with 3 variables and extraordinary flavor was found to show the lowest J value (0.010). It was concluded that 4 variables (color, flavor top, aging, extraordinary flavor) were important in the total evaluation of Ginjo. The results suggest that the fuzzy modeling using a FNN is effective on the analysis of sensory evaluation process.

U2 - 10.9746/sicetr1965.32.1113

DO - 10.9746/sicetr1965.32.1113

M3 - Article

VL - 32

SP - 1113

EP - 1120

JO - Transactions of the Society of Instrument and Control Engineers

JF - Transactions of the Society of Instrument and Control Engineers

SN - 0453-4654

IS - 7

ER -