A Bio-Inspired Pattern Recognition System for Tin-Oxide Gas Sensor Applications

Aicha Beya Far, Farid Flitti, Bin Guo, Amine Bermak

Research output: Contribution to journalArticle

24 Citations (Scopus)

Abstract

In this paper, a bio-inspired pattern recognition system for tin-oxide gas sensor applications is proposed. To mimic the biological olfactory system, temperature modulation is first used to virtually increase the number of sensors by periodically sampling the sensors’ response at different temperatures. A convex microhotplate is used in order to improve the thermal properties of the structure enabling efficient temperature modulation process to be carried out. Temperature modulation is shown to increase the number of effective sensors from 16 physically available sensors (integrated on a single chip) to 12000 virtual sensors (VSs). This enables the emulation of a very large number of sensors typically found in biological systems. The response of each sensor is seen as a fingerprint map, which is further processed using various image processing techniques. Self organized maps (SOMs) algorithm is used to create a 2D map for each gas and to combine the huge number of VSs in order to reduce the dimensionality. Image moments are used as a feature enabling to characterize the spatial distribution within the image lattice and to retrieve the brighter regions in the SOM’ nodes exhibiting high activity to the input gas. Experiments on real sensors data show improved performance (96%) as compared with standard gas discrimination algorithms.

Original languageEnglish
Pages (from-to)713-722
Number of pages10
JournalIEEE Sensors Journal
Volume9
Issue number6
DOIs
Publication statusPublished - 2009
Externally publishedYes

Fingerprint

Pattern recognition systems
Tin oxides
Chemical sensors
pattern recognition
tin oxides
sensors
Sensors
gases
Modulation
Biological systems
modulation
Gases
Temperature
temperature
Spatial distribution
Image processing
image processing
discrimination
Thermodynamic properties
spatial distribution

Keywords

  • Gas identification
  • gas sensor arrays
  • machine olfaction
  • pattern analysis
  • self organized map (SOM) algorithm
  • temperature modulation

ASJC Scopus subject areas

  • Instrumentation
  • Electrical and Electronic Engineering

Cite this

A Bio-Inspired Pattern Recognition System for Tin-Oxide Gas Sensor Applications. / Far, Aicha Beya; Flitti, Farid; Guo, Bin; Bermak, Amine.

In: IEEE Sensors Journal, Vol. 9, No. 6, 2009, p. 713-722.

Research output: Contribution to journalArticle

Far, Aicha Beya ; Flitti, Farid ; Guo, Bin ; Bermak, Amine. / A Bio-Inspired Pattern Recognition System for Tin-Oxide Gas Sensor Applications. In: IEEE Sensors Journal. 2009 ; Vol. 9, No. 6. pp. 713-722.
@article{20988755e5384e7cbaeeae6d5f23243f,
title = "A Bio-Inspired Pattern Recognition System for Tin-Oxide Gas Sensor Applications",
abstract = "In this paper, a bio-inspired pattern recognition system for tin-oxide gas sensor applications is proposed. To mimic the biological olfactory system, temperature modulation is first used to virtually increase the number of sensors by periodically sampling the sensors’ response at different temperatures. A convex microhotplate is used in order to improve the thermal properties of the structure enabling efficient temperature modulation process to be carried out. Temperature modulation is shown to increase the number of effective sensors from 16 physically available sensors (integrated on a single chip) to 12000 virtual sensors (VSs). This enables the emulation of a very large number of sensors typically found in biological systems. The response of each sensor is seen as a fingerprint map, which is further processed using various image processing techniques. Self organized maps (SOMs) algorithm is used to create a 2D map for each gas and to combine the huge number of VSs in order to reduce the dimensionality. Image moments are used as a feature enabling to characterize the spatial distribution within the image lattice and to retrieve the brighter regions in the SOM’ nodes exhibiting high activity to the input gas. Experiments on real sensors data show improved performance (96{\%}) as compared with standard gas discrimination algorithms.",
keywords = "Gas identification, gas sensor arrays, machine olfaction, pattern analysis, self organized map (SOM) algorithm, temperature modulation",
author = "Far, {Aicha Beya} and Farid Flitti and Bin Guo and Amine Bermak",
year = "2009",
doi = "10.1109/JSEN.2009.2020116",
language = "English",
volume = "9",
pages = "713--722",
journal = "IEEE Sensors Journal",
issn = "1530-437X",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "6",

}

TY - JOUR

T1 - A Bio-Inspired Pattern Recognition System for Tin-Oxide Gas Sensor Applications

AU - Far, Aicha Beya

AU - Flitti, Farid

AU - Guo, Bin

AU - Bermak, Amine

PY - 2009

Y1 - 2009

N2 - In this paper, a bio-inspired pattern recognition system for tin-oxide gas sensor applications is proposed. To mimic the biological olfactory system, temperature modulation is first used to virtually increase the number of sensors by periodically sampling the sensors’ response at different temperatures. A convex microhotplate is used in order to improve the thermal properties of the structure enabling efficient temperature modulation process to be carried out. Temperature modulation is shown to increase the number of effective sensors from 16 physically available sensors (integrated on a single chip) to 12000 virtual sensors (VSs). This enables the emulation of a very large number of sensors typically found in biological systems. The response of each sensor is seen as a fingerprint map, which is further processed using various image processing techniques. Self organized maps (SOMs) algorithm is used to create a 2D map for each gas and to combine the huge number of VSs in order to reduce the dimensionality. Image moments are used as a feature enabling to characterize the spatial distribution within the image lattice and to retrieve the brighter regions in the SOM’ nodes exhibiting high activity to the input gas. Experiments on real sensors data show improved performance (96%) as compared with standard gas discrimination algorithms.

AB - In this paper, a bio-inspired pattern recognition system for tin-oxide gas sensor applications is proposed. To mimic the biological olfactory system, temperature modulation is first used to virtually increase the number of sensors by periodically sampling the sensors’ response at different temperatures. A convex microhotplate is used in order to improve the thermal properties of the structure enabling efficient temperature modulation process to be carried out. Temperature modulation is shown to increase the number of effective sensors from 16 physically available sensors (integrated on a single chip) to 12000 virtual sensors (VSs). This enables the emulation of a very large number of sensors typically found in biological systems. The response of each sensor is seen as a fingerprint map, which is further processed using various image processing techniques. Self organized maps (SOMs) algorithm is used to create a 2D map for each gas and to combine the huge number of VSs in order to reduce the dimensionality. Image moments are used as a feature enabling to characterize the spatial distribution within the image lattice and to retrieve the brighter regions in the SOM’ nodes exhibiting high activity to the input gas. Experiments on real sensors data show improved performance (96%) as compared with standard gas discrimination algorithms.

KW - Gas identification

KW - gas sensor arrays

KW - machine olfaction

KW - pattern analysis

KW - self organized map (SOM) algorithm

KW - temperature modulation

UR - http://www.scopus.com/inward/record.url?scp=85008033778&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85008033778&partnerID=8YFLogxK

U2 - 10.1109/JSEN.2009.2020116

DO - 10.1109/JSEN.2009.2020116

M3 - Article

AN - SCOPUS:85008033778

VL - 9

SP - 713

EP - 722

JO - IEEE Sensors Journal

JF - IEEE Sensors Journal

SN - 1530-437X

IS - 6

ER -