Gas identification algorithms for microelectronic gas sensor

S. Brahim Belhouari, Amine Bermak, G. Wei, P. C H Chan

Research output: Contribution to journalArticle

13 Citations (Scopus)

Abstract

Gas identification represents a big challenge for pattern recognition systems due to several particular problems. The aim of this study is to compare the accuracy of a range of advanced and classical pattern recognition algorithms for gas identification from sensor array signals. Density estimation is applied in the construction of classifiers through the use of Bayes rule. Experiments on real sensors' data proved the effectiveness of the approach with an excellent classification performance. We compare the classification accuracy of different density models with several neural networks architectures. On our gas sensors data, the best performance was achieved by Gaussian mixture models with more than 92% accuracy.

Original languageEnglish
Pages (from-to)584-587
Number of pages4
JournalConference Record - IEEE Instrumentation and Measurement Technology Conference
Volume1
Publication statusPublished - 2004
Externally publishedYes

Fingerprint

Chemical sensors
microelectronics
Microelectronics
Pattern recognition systems
pattern recognition
sensors
Sensor arrays
Network architecture
Gases
gases
Pattern recognition
Classifiers
classifiers
Neural networks
Sensors
Experiments

Keywords

  • Classification
  • Density models
  • Gas sensor array
  • Neural networks
  • Pattern recognition

ASJC Scopus subject areas

  • Instrumentation

Cite this

Gas identification algorithms for microelectronic gas sensor. / Belhouari, S. Brahim; Bermak, Amine; Wei, G.; Chan, P. C H.

In: Conference Record - IEEE Instrumentation and Measurement Technology Conference, Vol. 1, 2004, p. 584-587.

Research output: Contribution to journalArticle

@article{e55caf469b4c46629f79beb9e198fd89,
title = "Gas identification algorithms for microelectronic gas sensor",
abstract = "Gas identification represents a big challenge for pattern recognition systems due to several particular problems. The aim of this study is to compare the accuracy of a range of advanced and classical pattern recognition algorithms for gas identification from sensor array signals. Density estimation is applied in the construction of classifiers through the use of Bayes rule. Experiments on real sensors' data proved the effectiveness of the approach with an excellent classification performance. We compare the classification accuracy of different density models with several neural networks architectures. On our gas sensors data, the best performance was achieved by Gaussian mixture models with more than 92{\%} accuracy.",
keywords = "Classification, Density models, Gas sensor array, Neural networks, Pattern recognition",
author = "Belhouari, {S. Brahim} and Amine Bermak and G. Wei and Chan, {P. C H}",
year = "2004",
language = "English",
volume = "1",
pages = "584--587",
journal = "Conference Record - IEEE Instrumentation and Measurement Technology Conference",
issn = "1091-5281",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Gas identification algorithms for microelectronic gas sensor

AU - Belhouari, S. Brahim

AU - Bermak, Amine

AU - Wei, G.

AU - Chan, P. C H

PY - 2004

Y1 - 2004

N2 - Gas identification represents a big challenge for pattern recognition systems due to several particular problems. The aim of this study is to compare the accuracy of a range of advanced and classical pattern recognition algorithms for gas identification from sensor array signals. Density estimation is applied in the construction of classifiers through the use of Bayes rule. Experiments on real sensors' data proved the effectiveness of the approach with an excellent classification performance. We compare the classification accuracy of different density models with several neural networks architectures. On our gas sensors data, the best performance was achieved by Gaussian mixture models with more than 92% accuracy.

AB - Gas identification represents a big challenge for pattern recognition systems due to several particular problems. The aim of this study is to compare the accuracy of a range of advanced and classical pattern recognition algorithms for gas identification from sensor array signals. Density estimation is applied in the construction of classifiers through the use of Bayes rule. Experiments on real sensors' data proved the effectiveness of the approach with an excellent classification performance. We compare the classification accuracy of different density models with several neural networks architectures. On our gas sensors data, the best performance was achieved by Gaussian mixture models with more than 92% accuracy.

KW - Classification

KW - Density models

KW - Gas sensor array

KW - Neural networks

KW - Pattern recognition

UR - http://www.scopus.com/inward/record.url?scp=4644334215&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=4644334215&partnerID=8YFLogxK

M3 - Article

VL - 1

SP - 584

EP - 587

JO - Conference Record - IEEE Instrumentation and Measurement Technology Conference

JF - Conference Record - IEEE Instrumentation and Measurement Technology Conference

SN - 1091-5281

ER -