Experimental evaluation of latency coding for gas recognition

Jaber Hassan J. Al-Yamani, Farid Boussaid, Amine Bermak, Dominique Martinez

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

Abstract

Commercial gas recognition systems use advanced computationally intensive signal processing/pattern recognition algorithms to identify gases and discriminate between them. This severely impacts on the size and cost of such systems but also limits their large-scale deployment. Biologically-inspired gas recognition schemes have the potential to greatly simplify the task of gas recognition, enabling the advent of low cost and low power miniature gas systems. In this paper, we present an experimental evaluation of bio-inspired latency coding for gas recognition. The performance of this bio-inspired approach was evaluated against four commonly used pattern recognition algorithms, namely K Nearest Neighbors (KNN), neural networks (Multi-Layer Perceptron (MLP), Radial Basis Function (RBF)) and density models (Gaussian Mixture Models (GMM). Reported experimental results suggest that latency coding could perform as well if not better than more computationally intensive pattern recognition techniques.

Original languageEnglish
Title of host publication2013 8th IEEE Design and Test Symposium, IDT 2013
DOIs
Publication statusPublished - 2013
Externally publishedYes
Event2013 8th IEEE Design and Test Symposium, IDT 2013 - Marrakesh, Morocco
Duration: 16 Dec 201318 Dec 2013

Other

Other2013 8th IEEE Design and Test Symposium, IDT 2013
CountryMorocco
CityMarrakesh
Period16/12/1318/12/13

Fingerprint

Gases
Pattern recognition
Multilayer neural networks
Costs
Signal processing
Neural networks

Keywords

  • electronic nose
  • gas sensors
  • glomerular convergence
  • latency coding
  • olfaction

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Al-Yamani, J. H. J., Boussaid, F., Bermak, A., & Martinez, D. (2013). Experimental evaluation of latency coding for gas recognition. In 2013 8th IEEE Design and Test Symposium, IDT 2013 [6727123] https://doi.org/10.1109/IDT.2013.6727123

Experimental evaluation of latency coding for gas recognition. / Al-Yamani, Jaber Hassan J.; Boussaid, Farid; Bermak, Amine; Martinez, Dominique.

2013 8th IEEE Design and Test Symposium, IDT 2013. 2013. 6727123.

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

Al-Yamani, JHJ, Boussaid, F, Bermak, A & Martinez, D 2013, Experimental evaluation of latency coding for gas recognition. in 2013 8th IEEE Design and Test Symposium, IDT 2013., 6727123, 2013 8th IEEE Design and Test Symposium, IDT 2013, Marrakesh, Morocco, 16/12/13. https://doi.org/10.1109/IDT.2013.6727123
Al-Yamani JHJ, Boussaid F, Bermak A, Martinez D. Experimental evaluation of latency coding for gas recognition. In 2013 8th IEEE Design and Test Symposium, IDT 2013. 2013. 6727123 https://doi.org/10.1109/IDT.2013.6727123
Al-Yamani, Jaber Hassan J. ; Boussaid, Farid ; Bermak, Amine ; Martinez, Dominique. / Experimental evaluation of latency coding for gas recognition. 2013 8th IEEE Design and Test Symposium, IDT 2013. 2013.
@inproceedings{ca1899ca3de34122b798c8881be4fdc8,
title = "Experimental evaluation of latency coding for gas recognition",
abstract = "Commercial gas recognition systems use advanced computationally intensive signal processing/pattern recognition algorithms to identify gases and discriminate between them. This severely impacts on the size and cost of such systems but also limits their large-scale deployment. Biologically-inspired gas recognition schemes have the potential to greatly simplify the task of gas recognition, enabling the advent of low cost and low power miniature gas systems. In this paper, we present an experimental evaluation of bio-inspired latency coding for gas recognition. The performance of this bio-inspired approach was evaluated against four commonly used pattern recognition algorithms, namely K Nearest Neighbors (KNN), neural networks (Multi-Layer Perceptron (MLP), Radial Basis Function (RBF)) and density models (Gaussian Mixture Models (GMM). Reported experimental results suggest that latency coding could perform as well if not better than more computationally intensive pattern recognition techniques.",
keywords = "electronic nose, gas sensors, glomerular convergence, latency coding, olfaction",
author = "Al-Yamani, {Jaber Hassan J.} and Farid Boussaid and Amine Bermak and Dominique Martinez",
year = "2013",
doi = "10.1109/IDT.2013.6727123",
language = "English",
isbn = "9781479935253",
booktitle = "2013 8th IEEE Design and Test Symposium, IDT 2013",

}

TY - GEN

T1 - Experimental evaluation of latency coding for gas recognition

AU - Al-Yamani, Jaber Hassan J.

AU - Boussaid, Farid

AU - Bermak, Amine

AU - Martinez, Dominique

PY - 2013

Y1 - 2013

N2 - Commercial gas recognition systems use advanced computationally intensive signal processing/pattern recognition algorithms to identify gases and discriminate between them. This severely impacts on the size and cost of such systems but also limits their large-scale deployment. Biologically-inspired gas recognition schemes have the potential to greatly simplify the task of gas recognition, enabling the advent of low cost and low power miniature gas systems. In this paper, we present an experimental evaluation of bio-inspired latency coding for gas recognition. The performance of this bio-inspired approach was evaluated against four commonly used pattern recognition algorithms, namely K Nearest Neighbors (KNN), neural networks (Multi-Layer Perceptron (MLP), Radial Basis Function (RBF)) and density models (Gaussian Mixture Models (GMM). Reported experimental results suggest that latency coding could perform as well if not better than more computationally intensive pattern recognition techniques.

AB - Commercial gas recognition systems use advanced computationally intensive signal processing/pattern recognition algorithms to identify gases and discriminate between them. This severely impacts on the size and cost of such systems but also limits their large-scale deployment. Biologically-inspired gas recognition schemes have the potential to greatly simplify the task of gas recognition, enabling the advent of low cost and low power miniature gas systems. In this paper, we present an experimental evaluation of bio-inspired latency coding for gas recognition. The performance of this bio-inspired approach was evaluated against four commonly used pattern recognition algorithms, namely K Nearest Neighbors (KNN), neural networks (Multi-Layer Perceptron (MLP), Radial Basis Function (RBF)) and density models (Gaussian Mixture Models (GMM). Reported experimental results suggest that latency coding could perform as well if not better than more computationally intensive pattern recognition techniques.

KW - electronic nose

KW - gas sensors

KW - glomerular convergence

KW - latency coding

KW - olfaction

UR - http://www.scopus.com/inward/record.url?scp=84894437755&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84894437755&partnerID=8YFLogxK

U2 - 10.1109/IDT.2013.6727123

DO - 10.1109/IDT.2013.6727123

M3 - Conference contribution

SN - 9781479935253

BT - 2013 8th IEEE Design and Test Symposium, IDT 2013

ER -