An automatic KANSEI fuzzy rule creating system using thesaurus

Hajime Hotta, Masafumi Hagiwara

Research output: Contribution to journalArticle

Abstract

In this paper, we propose an automatic Kansei fuzzy rule creating system using thesaurus. In general, there are a lot of words that express impressions. However, conventional approaches of Kansei engineering are not suitable to use many impression words because it is difficult to collect enough data. The proposed system is an enhanced algorithm of the conventional method that the authors proposed before. The proposed system extracts fuzzy rules for many words defined in the thesaurus dictionary while the conventional one can extract rules of specified words which user defined. The flow of the system consists of 3 steps: (1) construction of thesaurus networks; (2) data collection by web questionnaire sheets; (3) Extraction of fuzzy rules. In order to extract Kansei fuzzy rules, the system employs enhanced GRNN(general regression neural network) which can treat relative words of the thesaurus network. Using a Japanese thesaurus dictionary in the experiments, the sets of fuzzy rules for 1,195 impression words are extracted, and the fuzzy rules extracted by the proposed system obtained higher accuracy than those extracted by the conventional one.

Original languageEnglish
Pages (from-to)176-184
Number of pages9
JournalTransactions of the Japanese Society for Artificial Intelligence
Volume23
Issue number3
Publication statusPublished - 2008
Externally publishedYes

Fingerprint

Thesauri
Fuzzy rules
Glossaries
Neural networks

Keywords

  • Fuzzy logic
  • Kansei engineering
  • Neural network
  • Thesaurus

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

An automatic KANSEI fuzzy rule creating system using thesaurus. / Hotta, Hajime; Hagiwara, Masafumi.

In: Transactions of the Japanese Society for Artificial Intelligence, Vol. 23, No. 3, 2008, p. 176-184.

Research output: Contribution to journalArticle

@article{13e2f7a19a7f4f13a433f70bf8e4ea4f,
title = "An automatic KANSEI fuzzy rule creating system using thesaurus",
abstract = "In this paper, we propose an automatic Kansei fuzzy rule creating system using thesaurus. In general, there are a lot of words that express impressions. However, conventional approaches of Kansei engineering are not suitable to use many impression words because it is difficult to collect enough data. The proposed system is an enhanced algorithm of the conventional method that the authors proposed before. The proposed system extracts fuzzy rules for many words defined in the thesaurus dictionary while the conventional one can extract rules of specified words which user defined. The flow of the system consists of 3 steps: (1) construction of thesaurus networks; (2) data collection by web questionnaire sheets; (3) Extraction of fuzzy rules. In order to extract Kansei fuzzy rules, the system employs enhanced GRNN(general regression neural network) which can treat relative words of the thesaurus network. Using a Japanese thesaurus dictionary in the experiments, the sets of fuzzy rules for 1,195 impression words are extracted, and the fuzzy rules extracted by the proposed system obtained higher accuracy than those extracted by the conventional one.",
keywords = "Fuzzy logic, Kansei engineering, Neural network, Thesaurus",
author = "Hajime Hotta and Masafumi Hagiwara",
year = "2008",
language = "English",
volume = "23",
pages = "176--184",
journal = "Transactions of the Japanese Society for Artificial Intelligence",
issn = "1346-0714",
publisher = "Japanese Society for Artificial Intelligence",
number = "3",

}

TY - JOUR

T1 - An automatic KANSEI fuzzy rule creating system using thesaurus

AU - Hotta, Hajime

AU - Hagiwara, Masafumi

PY - 2008

Y1 - 2008

N2 - In this paper, we propose an automatic Kansei fuzzy rule creating system using thesaurus. In general, there are a lot of words that express impressions. However, conventional approaches of Kansei engineering are not suitable to use many impression words because it is difficult to collect enough data. The proposed system is an enhanced algorithm of the conventional method that the authors proposed before. The proposed system extracts fuzzy rules for many words defined in the thesaurus dictionary while the conventional one can extract rules of specified words which user defined. The flow of the system consists of 3 steps: (1) construction of thesaurus networks; (2) data collection by web questionnaire sheets; (3) Extraction of fuzzy rules. In order to extract Kansei fuzzy rules, the system employs enhanced GRNN(general regression neural network) which can treat relative words of the thesaurus network. Using a Japanese thesaurus dictionary in the experiments, the sets of fuzzy rules for 1,195 impression words are extracted, and the fuzzy rules extracted by the proposed system obtained higher accuracy than those extracted by the conventional one.

AB - In this paper, we propose an automatic Kansei fuzzy rule creating system using thesaurus. In general, there are a lot of words that express impressions. However, conventional approaches of Kansei engineering are not suitable to use many impression words because it is difficult to collect enough data. The proposed system is an enhanced algorithm of the conventional method that the authors proposed before. The proposed system extracts fuzzy rules for many words defined in the thesaurus dictionary while the conventional one can extract rules of specified words which user defined. The flow of the system consists of 3 steps: (1) construction of thesaurus networks; (2) data collection by web questionnaire sheets; (3) Extraction of fuzzy rules. In order to extract Kansei fuzzy rules, the system employs enhanced GRNN(general regression neural network) which can treat relative words of the thesaurus network. Using a Japanese thesaurus dictionary in the experiments, the sets of fuzzy rules for 1,195 impression words are extracted, and the fuzzy rules extracted by the proposed system obtained higher accuracy than those extracted by the conventional one.

KW - Fuzzy logic

KW - Kansei engineering

KW - Neural network

KW - Thesaurus

UR - http://www.scopus.com/inward/record.url?scp=42949088515&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=42949088515&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:42949088515

VL - 23

SP - 176

EP - 184

JO - Transactions of the Japanese Society for Artificial Intelligence

JF - Transactions of the Japanese Society for Artificial Intelligence

SN - 1346-0714

IS - 3

ER -