A metadata extraction method for taste-impression with sensor technologies

Hanako Kariya, Yasushi Kiyoki

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, we present a metadata extraction method for taste-impression with sensor technologies. Our metadata extraction method extracts taste-impression metadata automatically by using sensor outputs retrieved from the taste sensor, according to characteristic features of foods, such as a type, a nationality, and a theme ("taste domain"). By realizing taste-domain-dependent metadata extraction with sensor technologies, our method transforms sensor outputs into meaningful taste-impression metadata automatically and computes the correlation between the target foods (or drinks) and the query described in taste-impression. Users can intuitively search various information resources regarding foods and drinks on the basis of abstract taste-impression preferences. We clarify the feasibility and effectiveness of our method by several experimental results.

Original languageEnglish
Title of host publicationProceedings - 2005 Symposium on Applications and the Internet Workshops, SAINT2005
Pages442-445
Number of pages4
Publication statusPublished - 2005 Dec 1
Event2005 Symposium on Applications and the Internet Workshops, SAINT2005 - Trento, Italy
Duration: 2005 Jan 312005 Feb 4

Publication series

NameProceedings - 2005 Symposium on Applications and the Internet Workshops, SAINT2005
Volume2005

Other

Other2005 Symposium on Applications and the Internet Workshops, SAINT2005
Country/TerritoryItaly
CityTrento
Period05/1/3105/2/4

ASJC Scopus subject areas

  • Engineering(all)

Fingerprint

Dive into the research topics of 'A metadata extraction method for taste-impression with sensor technologies'. Together they form a unique fingerprint.

Cite this