Model construction for quality of beer and brewing process using FNN

Hideki Noguchi, Taizo Hanai, Wataru Takahashi, Tomohiko Ichii, Mitsuru Tanikawa, Susumu Masuoka, Hiroyuki Honda, Takeshi Kobayashi

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

Models for sensory evaluation of beer and the beer brewing process were constructed using a fuzzy neural network (FNN). A new method for optimal model selection using a genetic algorithm and a SWEEP operator method was compared with a conventional method using the parameter increasing method. As the result, the new method was useful for the optimal model selection by simplifying the model structure, improving the reliability of fuzzy rules, and accelerating the calculation speed (about 10 times as fast as conventional method) for constructing the model with high accuracy. The percentage of correct answers of the sensory evaluation model is 92%. The important variables are selected as the input variables, and the obtained fuzzy rules in modeling coincide well with knowledge data bases acquired by process operators, and it is proven that the obtained FNN models are adequate.

Original languageEnglish
Pages (from-to)700-701
Number of pages2
Journalkagaku kogaku ronbunshu
Volume25
Issue number5
Publication statusPublished - Sep 1 1999
Externally publishedYes

Fingerprint

Brewing
Beer
Fuzzy neural networks
Fuzzy rules
Model structures
Mathematical operators
Genetic algorithms

All Science Journal Classification (ASJC) codes

  • Chemistry(all)
  • Chemical Engineering(all)

Cite this

Noguchi, H., Hanai, T., Takahashi, W., Ichii, T., Tanikawa, M., Masuoka, S., ... Kobayashi, T. (1999). Model construction for quality of beer and brewing process using FNN. kagaku kogaku ronbunshu, 25(5), 700-701.

Model construction for quality of beer and brewing process using FNN. / Noguchi, Hideki; Hanai, Taizo; Takahashi, Wataru; Ichii, Tomohiko; Tanikawa, Mitsuru; Masuoka, Susumu; Honda, Hiroyuki; Kobayashi, Takeshi.

In: kagaku kogaku ronbunshu, Vol. 25, No. 5, 01.09.1999, p. 700-701.

Research output: Contribution to journalArticle

Noguchi, H, Hanai, T, Takahashi, W, Ichii, T, Tanikawa, M, Masuoka, S, Honda, H & Kobayashi, T 1999, 'Model construction for quality of beer and brewing process using FNN', kagaku kogaku ronbunshu, vol. 25, no. 5, pp. 700-701.
Noguchi H, Hanai T, Takahashi W, Ichii T, Tanikawa M, Masuoka S et al. Model construction for quality of beer and brewing process using FNN. kagaku kogaku ronbunshu. 1999 Sep 1;25(5):700-701.
Noguchi, Hideki ; Hanai, Taizo ; Takahashi, Wataru ; Ichii, Tomohiko ; Tanikawa, Mitsuru ; Masuoka, Susumu ; Honda, Hiroyuki ; Kobayashi, Takeshi. / Model construction for quality of beer and brewing process using FNN. In: kagaku kogaku ronbunshu. 1999 ; Vol. 25, No. 5. pp. 700-701.
@article{881e83cacc2d42fd87ec840e4836821f,
title = "Model construction for quality of beer and brewing process using FNN",
abstract = "Models for sensory evaluation of beer and the beer brewing process were constructed using a fuzzy neural network (FNN). A new method for optimal model selection using a genetic algorithm and a SWEEP operator method was compared with a conventional method using the parameter increasing method. As the result, the new method was useful for the optimal model selection by simplifying the model structure, improving the reliability of fuzzy rules, and accelerating the calculation speed (about 10 times as fast as conventional method) for constructing the model with high accuracy. The percentage of correct answers of the sensory evaluation model is 92{\%}. The important variables are selected as the input variables, and the obtained fuzzy rules in modeling coincide well with knowledge data bases acquired by process operators, and it is proven that the obtained FNN models are adequate.",
author = "Hideki Noguchi and Taizo Hanai and Wataru Takahashi and Tomohiko Ichii and Mitsuru Tanikawa and Susumu Masuoka and Hiroyuki Honda and Takeshi Kobayashi",
year = "1999",
month = "9",
day = "1",
language = "English",
volume = "25",
pages = "700--701",
journal = "Kagaku Kogaku Ronbunshu",
issn = "0386-216X",
publisher = "The Society of Chemical Engineers, Japan",
number = "5",

}

TY - JOUR

T1 - Model construction for quality of beer and brewing process using FNN

AU - Noguchi, Hideki

AU - Hanai, Taizo

AU - Takahashi, Wataru

AU - Ichii, Tomohiko

AU - Tanikawa, Mitsuru

AU - Masuoka, Susumu

AU - Honda, Hiroyuki

AU - Kobayashi, Takeshi

PY - 1999/9/1

Y1 - 1999/9/1

N2 - Models for sensory evaluation of beer and the beer brewing process were constructed using a fuzzy neural network (FNN). A new method for optimal model selection using a genetic algorithm and a SWEEP operator method was compared with a conventional method using the parameter increasing method. As the result, the new method was useful for the optimal model selection by simplifying the model structure, improving the reliability of fuzzy rules, and accelerating the calculation speed (about 10 times as fast as conventional method) for constructing the model with high accuracy. The percentage of correct answers of the sensory evaluation model is 92%. The important variables are selected as the input variables, and the obtained fuzzy rules in modeling coincide well with knowledge data bases acquired by process operators, and it is proven that the obtained FNN models are adequate.

AB - Models for sensory evaluation of beer and the beer brewing process were constructed using a fuzzy neural network (FNN). A new method for optimal model selection using a genetic algorithm and a SWEEP operator method was compared with a conventional method using the parameter increasing method. As the result, the new method was useful for the optimal model selection by simplifying the model structure, improving the reliability of fuzzy rules, and accelerating the calculation speed (about 10 times as fast as conventional method) for constructing the model with high accuracy. The percentage of correct answers of the sensory evaluation model is 92%. The important variables are selected as the input variables, and the obtained fuzzy rules in modeling coincide well with knowledge data bases acquired by process operators, and it is proven that the obtained FNN models are adequate.

UR - http://www.scopus.com/inward/record.url?scp=33750857294&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33750857294&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:33750857294

VL - 25

SP - 700

EP - 701

JO - Kagaku Kogaku Ronbunshu

JF - Kagaku Kogaku Ronbunshu

SN - 0386-216X

IS - 5

ER -