Unknown odor recognition using Euclidean Fuzzy similarity-based self-organized network inspired by immune algorithm

Muhammad Rahmat Widyanto, Benyamin Kusumo Putro, Kaoru Hirota

Research output: Contribution to journalArticlepeer-review

3 Citations (Scopus)

Abstract

To deal with unknown odor recognition problem for a developed artificial odor discrimination system, Euclidean Fuzzy similarity-based Self-Organized Network inspired by Immune Algorithm (EF-SONIA) is proposed. Euclidean fuzzy similarity enables a zero similarity calculation between an unknown odor vector and hidden unit vectors, so that the system can recognize the unknown odor. In addition, an elliptical approach for fuzziness determination is proposed. The elliptical approach can approximate an appropriate fuzziness, so that the unknown odor recognition accuracy is improved. Experiments on three datasets of three-mixture vegetal odors show that the recognition accuracy of the proposed method is 20% better than those of the conventional method. The system is very promising to be used for a real development of dog robot that enables localization and identification of dangerous natural gas.

Original languageEnglish
Pages (from-to)27-37
Number of pages11
JournalNeural Computing and Applications
Volume17
Issue number1
DOIs
Publication statusPublished - Jan 2008

Keywords

  • Euclidean distance
  • Fuzzy similarity
  • Immune algorithm
  • Odor discrimination
  • Self-organization

Fingerprint

Dive into the research topics of 'Unknown odor recognition using Euclidean Fuzzy similarity-based self-organized network inspired by immune algorithm'. Together they form a unique fingerprint.

Cite this