Determination of the blending ratio of regular coffee samples by information technology

Osamu Tominaga, Fumio Ito, Taizo Hanai, Hiroyuki Honda, Takeshi Kobayashi

研究成果: ジャーナルへの寄稿記事

6 引用 (Scopus)

抄録

A searching method for the blending ratio of regular coffee with a designed flavor and taste has been developed. A fuzzy neural network (FNN) model was at first constructed for estimation of the sensory scores of various blending ratios. Using the model, the following four methods were attempted in order to estimate the blending ratio with the designed sensory score: 1) an exhaustive search, 2) a method using a genetic algorithm (GA), 3) a method using the GA combined with a reliability index (RIGA), and 4) a reverse FNN model. Among the results of these methods, the RIGA showed a good performance not only on estimation of the known blending ratio but also on the actual blending test in the present study.

元の言語英語
ページ(範囲)137-143
ページ数7
ジャーナルJournal of Chemical Engineering of Japan
35
発行部数2
DOI
出版物ステータス出版済み - 2 1 2002
外部発表Yes

Fingerprint

Coffee
Information technology
Fuzzy neural networks
Genetic algorithms
Flavors

All Science Journal Classification (ASJC) codes

  • Chemistry(all)
  • Chemical Engineering(all)

これを引用

Determination of the blending ratio of regular coffee samples by information technology. / Tominaga, Osamu; Ito, Fumio; Hanai, Taizo; Honda, Hiroyuki; Kobayashi, Takeshi.

:: Journal of Chemical Engineering of Japan, 巻 35, 番号 2, 01.02.2002, p. 137-143.

研究成果: ジャーナルへの寄稿記事

Tominaga, Osamu ; Ito, Fumio ; Hanai, Taizo ; Honda, Hiroyuki ; Kobayashi, Takeshi. / Determination of the blending ratio of regular coffee samples by information technology. :: Journal of Chemical Engineering of Japan. 2002 ; 巻 35, 番号 2. pp. 137-143.
@article{6037b1e1ac0c4e9fa16ff4416cede138,
title = "Determination of the blending ratio of regular coffee samples by information technology",
abstract = "A searching method for the blending ratio of regular coffee with a designed flavor and taste has been developed. A fuzzy neural network (FNN) model was at first constructed for estimation of the sensory scores of various blending ratios. Using the model, the following four methods were attempted in order to estimate the blending ratio with the designed sensory score: 1) an exhaustive search, 2) a method using a genetic algorithm (GA), 3) a method using the GA combined with a reliability index (RIGA), and 4) a reverse FNN model. Among the results of these methods, the RIGA showed a good performance not only on estimation of the known blending ratio but also on the actual blending test in the present study.",
author = "Osamu Tominaga and Fumio Ito and Taizo Hanai and Hiroyuki Honda and Takeshi Kobayashi",
year = "2002",
month = "2",
day = "1",
doi = "10.1252/jcej.35.137",
language = "English",
volume = "35",
pages = "137--143",
journal = "Journal of Chemical Engineering of Japan",
issn = "0021-9592",
publisher = "Society of Chemical Engineers, Japan",
number = "2",

}

TY - JOUR

T1 - Determination of the blending ratio of regular coffee samples by information technology

AU - Tominaga, Osamu

AU - Ito, Fumio

AU - Hanai, Taizo

AU - Honda, Hiroyuki

AU - Kobayashi, Takeshi

PY - 2002/2/1

Y1 - 2002/2/1

N2 - A searching method for the blending ratio of regular coffee with a designed flavor and taste has been developed. A fuzzy neural network (FNN) model was at first constructed for estimation of the sensory scores of various blending ratios. Using the model, the following four methods were attempted in order to estimate the blending ratio with the designed sensory score: 1) an exhaustive search, 2) a method using a genetic algorithm (GA), 3) a method using the GA combined with a reliability index (RIGA), and 4) a reverse FNN model. Among the results of these methods, the RIGA showed a good performance not only on estimation of the known blending ratio but also on the actual blending test in the present study.

AB - A searching method for the blending ratio of regular coffee with a designed flavor and taste has been developed. A fuzzy neural network (FNN) model was at first constructed for estimation of the sensory scores of various blending ratios. Using the model, the following four methods were attempted in order to estimate the blending ratio with the designed sensory score: 1) an exhaustive search, 2) a method using a genetic algorithm (GA), 3) a method using the GA combined with a reliability index (RIGA), and 4) a reverse FNN model. Among the results of these methods, the RIGA showed a good performance not only on estimation of the known blending ratio but also on the actual blending test in the present study.

UR - http://www.scopus.com/inward/record.url?scp=0036465394&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036465394&partnerID=8YFLogxK

U2 - 10.1252/jcej.35.137

DO - 10.1252/jcej.35.137

M3 - Article

VL - 35

SP - 137

EP - 143

JO - Journal of Chemical Engineering of Japan

JF - Journal of Chemical Engineering of Japan

SN - 0021-9592

IS - 2

ER -