Fast and Robust gas identification system using an integrated gas sensor technology and Gaussian mixture models

Sofiane Brahim-Belhouari, Amine Bermak, Minghua Shi, Philip C H Chan

Research output: Contribution to journalArticle

29 Citations (Scopus)

Abstract

Among the most serious limitations facing the success of future consumer gas identification systems are the drift problem and the real-time detection due to the slow response of most of today's gas sensors. This paper shows that the combination of an integrated sensor array and a Gaussian mixture model permits success in gas identification problems. An integrated sensor array has been designed with the aim of combustion gases identification. Our identification system is able to quickly recognize gases with more than 96% accuracy. Robust detection is introduced through a drift counteraction approach based on extending the training data set using a simulated drift.

Original languageEnglish
Pages (from-to)1433-1444
Number of pages12
JournalIEEE Sensors Journal
Volume5
Issue number6
DOIs
Publication statusPublished - Dec 2005
Externally publishedYes

Fingerprint

system identification
Chemical sensors
Identification (control systems)
sensors
Sensor arrays
Gases
gases
education

Keywords

  • Drift counteraction
  • Fast recognition
  • Gas sensors
  • Gaussian mixture model (GMM)

ASJC Scopus subject areas

  • Engineering(all)
  • Electrical and Electronic Engineering

Cite this

Fast and Robust gas identification system using an integrated gas sensor technology and Gaussian mixture models. / Brahim-Belhouari, Sofiane; Bermak, Amine; Shi, Minghua; Chan, Philip C H.

In: IEEE Sensors Journal, Vol. 5, No. 6, 12.2005, p. 1433-1444.

Research output: Contribution to journalArticle

Brahim-Belhouari, Sofiane ; Bermak, Amine ; Shi, Minghua ; Chan, Philip C H. / Fast and Robust gas identification system using an integrated gas sensor technology and Gaussian mixture models. In: IEEE Sensors Journal. 2005 ; Vol. 5, No. 6. pp. 1433-1444.
@article{dc7d976786574e8e9bd2231751222843,
title = "Fast and Robust gas identification system using an integrated gas sensor technology and Gaussian mixture models",
abstract = "Among the most serious limitations facing the success of future consumer gas identification systems are the drift problem and the real-time detection due to the slow response of most of today's gas sensors. This paper shows that the combination of an integrated sensor array and a Gaussian mixture model permits success in gas identification problems. An integrated sensor array has been designed with the aim of combustion gases identification. Our identification system is able to quickly recognize gases with more than 96{\%} accuracy. Robust detection is introduced through a drift counteraction approach based on extending the training data set using a simulated drift.",
keywords = "Drift counteraction, Fast recognition, Gas sensors, Gaussian mixture model (GMM)",
author = "Sofiane Brahim-Belhouari and Amine Bermak and Minghua Shi and Chan, {Philip C H}",
year = "2005",
month = "12",
doi = "10.1109/JSEN.2005.858926",
language = "English",
volume = "5",
pages = "1433--1444",
journal = "IEEE Sensors Journal",
issn = "1530-437X",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "6",

}

TY - JOUR

T1 - Fast and Robust gas identification system using an integrated gas sensor technology and Gaussian mixture models

AU - Brahim-Belhouari, Sofiane

AU - Bermak, Amine

AU - Shi, Minghua

AU - Chan, Philip C H

PY - 2005/12

Y1 - 2005/12

N2 - Among the most serious limitations facing the success of future consumer gas identification systems are the drift problem and the real-time detection due to the slow response of most of today's gas sensors. This paper shows that the combination of an integrated sensor array and a Gaussian mixture model permits success in gas identification problems. An integrated sensor array has been designed with the aim of combustion gases identification. Our identification system is able to quickly recognize gases with more than 96% accuracy. Robust detection is introduced through a drift counteraction approach based on extending the training data set using a simulated drift.

AB - Among the most serious limitations facing the success of future consumer gas identification systems are the drift problem and the real-time detection due to the slow response of most of today's gas sensors. This paper shows that the combination of an integrated sensor array and a Gaussian mixture model permits success in gas identification problems. An integrated sensor array has been designed with the aim of combustion gases identification. Our identification system is able to quickly recognize gases with more than 96% accuracy. Robust detection is introduced through a drift counteraction approach based on extending the training data set using a simulated drift.

KW - Drift counteraction

KW - Fast recognition

KW - Gas sensors

KW - Gaussian mixture model (GMM)

UR - http://www.scopus.com/inward/record.url?scp=29044450430&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=29044450430&partnerID=8YFLogxK

U2 - 10.1109/JSEN.2005.858926

DO - 10.1109/JSEN.2005.858926

M3 - Article

VL - 5

SP - 1433

EP - 1444

JO - IEEE Sensors Journal

JF - IEEE Sensors Journal

SN - 1530-437X

IS - 6

ER -