Sensory modeling of coffee with a fuzzy neural network

O. Tominaga, F. Ito, Taizo Hanai, H. Honda, T. Kobayashi

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

Models were constructed to predict sensory evaluation scores from the blending ratio of coffee beans. Twenty-two blended coffees were prepared from 3 representative beans and were evaluated with respect to 10 sensory attributes by 5 coffee cup-tasters and by models constructed using the response surface method (RSM), multiple regression analysis (MRA), and a fuzzy neural network (FNN). The RSM and MRA models showed good correlations for some sensory attributes, but lacked sufficient overall accuracy. The FNN model exhibited high correlations for all attributes, clearly demonstrated the relationships between blending ratio and flavor characteristics, and was accurate enough for practical use. FNN, thus, constitutes a powerful tool for accelerating product development.

Original languageEnglish
Pages (from-to)363-368
Number of pages6
JournalJournal of Food Science
Volume67
Issue number1
DOIs
Publication statusPublished - Jan 1 2002
Externally publishedYes

Fingerprint

Coffee
neural networks
Regression Analysis
sensory properties
Neural Networks (Computer)
regression analysis
coffee beans
product development
sensory evaluation
beans
flavor
methodology

All Science Journal Classification (ASJC) codes

  • Food Science

Cite this

Sensory modeling of coffee with a fuzzy neural network. / Tominaga, O.; Ito, F.; Hanai, Taizo; Honda, H.; Kobayashi, T.

In: Journal of Food Science, Vol. 67, No. 1, 01.01.2002, p. 363-368.

Research output: Contribution to journalArticle

Tominaga, O. ; Ito, F. ; Hanai, Taizo ; Honda, H. ; Kobayashi, T. / Sensory modeling of coffee with a fuzzy neural network. In: Journal of Food Science. 2002 ; Vol. 67, No. 1. pp. 363-368.
@article{2ded5b8b01e648e6b19447979c67e0f5,
title = "Sensory modeling of coffee with a fuzzy neural network",
abstract = "Models were constructed to predict sensory evaluation scores from the blending ratio of coffee beans. Twenty-two blended coffees were prepared from 3 representative beans and were evaluated with respect to 10 sensory attributes by 5 coffee cup-tasters and by models constructed using the response surface method (RSM), multiple regression analysis (MRA), and a fuzzy neural network (FNN). The RSM and MRA models showed good correlations for some sensory attributes, but lacked sufficient overall accuracy. The FNN model exhibited high correlations for all attributes, clearly demonstrated the relationships between blending ratio and flavor characteristics, and was accurate enough for practical use. FNN, thus, constitutes a powerful tool for accelerating product development.",
author = "O. Tominaga and F. Ito and Taizo Hanai and H. Honda and T. Kobayashi",
year = "2002",
month = "1",
day = "1",
doi = "10.1111/j.1365-2621.2002.tb11411.x",
language = "English",
volume = "67",
pages = "363--368",
journal = "Journal of Food Science",
issn = "0022-1147",
publisher = "Wiley-Blackwell",
number = "1",

}

TY - JOUR

T1 - Sensory modeling of coffee with a fuzzy neural network

AU - Tominaga, O.

AU - Ito, F.

AU - Hanai, Taizo

AU - Honda, H.

AU - Kobayashi, T.

PY - 2002/1/1

Y1 - 2002/1/1

N2 - Models were constructed to predict sensory evaluation scores from the blending ratio of coffee beans. Twenty-two blended coffees were prepared from 3 representative beans and were evaluated with respect to 10 sensory attributes by 5 coffee cup-tasters and by models constructed using the response surface method (RSM), multiple regression analysis (MRA), and a fuzzy neural network (FNN). The RSM and MRA models showed good correlations for some sensory attributes, but lacked sufficient overall accuracy. The FNN model exhibited high correlations for all attributes, clearly demonstrated the relationships between blending ratio and flavor characteristics, and was accurate enough for practical use. FNN, thus, constitutes a powerful tool for accelerating product development.

AB - Models were constructed to predict sensory evaluation scores from the blending ratio of coffee beans. Twenty-two blended coffees were prepared from 3 representative beans and were evaluated with respect to 10 sensory attributes by 5 coffee cup-tasters and by models constructed using the response surface method (RSM), multiple regression analysis (MRA), and a fuzzy neural network (FNN). The RSM and MRA models showed good correlations for some sensory attributes, but lacked sufficient overall accuracy. The FNN model exhibited high correlations for all attributes, clearly demonstrated the relationships between blending ratio and flavor characteristics, and was accurate enough for practical use. FNN, thus, constitutes a powerful tool for accelerating product development.

UR - http://www.scopus.com/inward/record.url?scp=0036191818&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036191818&partnerID=8YFLogxK

U2 - 10.1111/j.1365-2621.2002.tb11411.x

DO - 10.1111/j.1365-2621.2002.tb11411.x

M3 - Article

VL - 67

SP - 363

EP - 368

JO - Journal of Food Science

JF - Journal of Food Science

SN - 0022-1147

IS - 1

ER -