Artificial odor discrimination system using multiple quartz resonator sensor and FNLVQ-MSA neural network for recognizing concentration of odor

W. Jatmiko, K. Sekiyama, T. Fukuda, Takayuki Matsuno, B. Kusumoputro

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

Abstract

An electronic odor discrimination system had been developed. The developed system showed high recognition probability to discriminate various single odors to its high generality properties, however the system had a limitation in recognizing the fragrances mixture. In order to improve the performance of the proposed system, development of the sensor and other neural network are being sought. This paper explains the improvement of the capability of that system. In this experiment, the improvement is conducted not only by replacing the last hardware system from 4 quartz resonator-basic resonance frequencies 10 MHz with new 16 quartz resonator-basic resonance frequencies 20 MHz, but also by replacing the pattern classifier from Back Propagation (BP) neural network with Variance of Back Propagation, Probabilistic Neural Network (PNN) and Fuzzy-Neuro Learning Vector Quantization. Matrix similarity analysis (MSA) is then proposed to increase the accuracy of the FNLVQ, become FNLVQ-MSA neural system in determining the best exemplar vector, for speeding up its convergence. The purpose of the recent study is to construct a new artificial odor discrimination system for recognizing the concentration of fragrance. The using of new sensing system and FNLVQ-MSA has produced higher capability to recognize the concentration of fragrance compared to the earlier mentioned system.

Original languageEnglish
Title of host publicationProceedings of the SICE Annual Conference
Pages1639-1644
Number of pages6
Publication statusPublished - 2005
Externally publishedYes
EventSICE Annual Conference 2005 - Okayama, Japan
Duration: Aug 8 2005Aug 10 2005

Other

OtherSICE Annual Conference 2005
CountryJapan
CityOkayama
Period8/8/058/10/05

Fingerprint

Fragrances
Odors
Quartz
Resonators
Neural networks
Backpropagation
Sensors
Vector quantization
Classifiers
Hardware
Experiments

Keywords

  • Electronic Odor
  • FNLVQ
  • Matrix Similarity Analysis

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Jatmiko, W., Sekiyama, K., Fukuda, T., Matsuno, T., & Kusumoputro, B. (2005). Artificial odor discrimination system using multiple quartz resonator sensor and FNLVQ-MSA neural network for recognizing concentration of odor. In Proceedings of the SICE Annual Conference (pp. 1639-1644)

Artificial odor discrimination system using multiple quartz resonator sensor and FNLVQ-MSA neural network for recognizing concentration of odor. / Jatmiko, W.; Sekiyama, K.; Fukuda, T.; Matsuno, Takayuki; Kusumoputro, B.

Proceedings of the SICE Annual Conference. 2005. p. 1639-1644.

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

Jatmiko, W, Sekiyama, K, Fukuda, T, Matsuno, T & Kusumoputro, B 2005, Artificial odor discrimination system using multiple quartz resonator sensor and FNLVQ-MSA neural network for recognizing concentration of odor. in Proceedings of the SICE Annual Conference. pp. 1639-1644, SICE Annual Conference 2005, Okayama, Japan, 8/8/05.
Jatmiko W, Sekiyama K, Fukuda T, Matsuno T, Kusumoputro B. Artificial odor discrimination system using multiple quartz resonator sensor and FNLVQ-MSA neural network for recognizing concentration of odor. In Proceedings of the SICE Annual Conference. 2005. p. 1639-1644
Jatmiko, W. ; Sekiyama, K. ; Fukuda, T. ; Matsuno, Takayuki ; Kusumoputro, B. / Artificial odor discrimination system using multiple quartz resonator sensor and FNLVQ-MSA neural network for recognizing concentration of odor. Proceedings of the SICE Annual Conference. 2005. pp. 1639-1644
@inproceedings{3d3407a7f99840d1bfbd7703d6296bcc,
title = "Artificial odor discrimination system using multiple quartz resonator sensor and FNLVQ-MSA neural network for recognizing concentration of odor",
abstract = "An electronic odor discrimination system had been developed. The developed system showed high recognition probability to discriminate various single odors to its high generality properties, however the system had a limitation in recognizing the fragrances mixture. In order to improve the performance of the proposed system, development of the sensor and other neural network are being sought. This paper explains the improvement of the capability of that system. In this experiment, the improvement is conducted not only by replacing the last hardware system from 4 quartz resonator-basic resonance frequencies 10 MHz with new 16 quartz resonator-basic resonance frequencies 20 MHz, but also by replacing the pattern classifier from Back Propagation (BP) neural network with Variance of Back Propagation, Probabilistic Neural Network (PNN) and Fuzzy-Neuro Learning Vector Quantization. Matrix similarity analysis (MSA) is then proposed to increase the accuracy of the FNLVQ, become FNLVQ-MSA neural system in determining the best exemplar vector, for speeding up its convergence. The purpose of the recent study is to construct a new artificial odor discrimination system for recognizing the concentration of fragrance. The using of new sensing system and FNLVQ-MSA has produced higher capability to recognize the concentration of fragrance compared to the earlier mentioned system.",
keywords = "Electronic Odor, FNLVQ, Matrix Similarity Analysis",
author = "W. Jatmiko and K. Sekiyama and T. Fukuda and Takayuki Matsuno and B. Kusumoputro",
year = "2005",
language = "English",
pages = "1639--1644",
booktitle = "Proceedings of the SICE Annual Conference",

}

TY - GEN

T1 - Artificial odor discrimination system using multiple quartz resonator sensor and FNLVQ-MSA neural network for recognizing concentration of odor

AU - Jatmiko, W.

AU - Sekiyama, K.

AU - Fukuda, T.

AU - Matsuno, Takayuki

AU - Kusumoputro, B.

PY - 2005

Y1 - 2005

N2 - An electronic odor discrimination system had been developed. The developed system showed high recognition probability to discriminate various single odors to its high generality properties, however the system had a limitation in recognizing the fragrances mixture. In order to improve the performance of the proposed system, development of the sensor and other neural network are being sought. This paper explains the improvement of the capability of that system. In this experiment, the improvement is conducted not only by replacing the last hardware system from 4 quartz resonator-basic resonance frequencies 10 MHz with new 16 quartz resonator-basic resonance frequencies 20 MHz, but also by replacing the pattern classifier from Back Propagation (BP) neural network with Variance of Back Propagation, Probabilistic Neural Network (PNN) and Fuzzy-Neuro Learning Vector Quantization. Matrix similarity analysis (MSA) is then proposed to increase the accuracy of the FNLVQ, become FNLVQ-MSA neural system in determining the best exemplar vector, for speeding up its convergence. The purpose of the recent study is to construct a new artificial odor discrimination system for recognizing the concentration of fragrance. The using of new sensing system and FNLVQ-MSA has produced higher capability to recognize the concentration of fragrance compared to the earlier mentioned system.

AB - An electronic odor discrimination system had been developed. The developed system showed high recognition probability to discriminate various single odors to its high generality properties, however the system had a limitation in recognizing the fragrances mixture. In order to improve the performance of the proposed system, development of the sensor and other neural network are being sought. This paper explains the improvement of the capability of that system. In this experiment, the improvement is conducted not only by replacing the last hardware system from 4 quartz resonator-basic resonance frequencies 10 MHz with new 16 quartz resonator-basic resonance frequencies 20 MHz, but also by replacing the pattern classifier from Back Propagation (BP) neural network with Variance of Back Propagation, Probabilistic Neural Network (PNN) and Fuzzy-Neuro Learning Vector Quantization. Matrix similarity analysis (MSA) is then proposed to increase the accuracy of the FNLVQ, become FNLVQ-MSA neural system in determining the best exemplar vector, for speeding up its convergence. The purpose of the recent study is to construct a new artificial odor discrimination system for recognizing the concentration of fragrance. The using of new sensing system and FNLVQ-MSA has produced higher capability to recognize the concentration of fragrance compared to the earlier mentioned system.

KW - Electronic Odor

KW - FNLVQ

KW - Matrix Similarity Analysis

UR - http://www.scopus.com/inward/record.url?scp=33645284190&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33645284190&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:33645284190

SP - 1639

EP - 1644

BT - Proceedings of the SICE Annual Conference

ER -