Probabilistic rank score coding: A robust rank-order based classifier for electronic nose applications

Muhammad Hassan, Samir Brahim Belhaouari, Amine Bermak

Research output: Contribution to journalArticle

15 Citations (Scopus)

Abstract

Motivated by the recent experimental findings about odor identification with the unique spiking patterns of neurons in the biological olfactory system, rank-order-based classifiers have been proposed for gas identification in electronic nose applications. These classifiers rely on one-to-one mapping between the target gas and the temporal sequence of spiking sensors in an electronic nose. However, shuffled spike sequences, due to low repeatability of the response patterns from the sensors, limit the performance of these classifiers. We propose a robust probabilistic rank score coding scheme that tabulates the probability of each spiking sensor at each rank, or temporal position, by exploiting all the spike sequences of the sensors for each target gas, and we analyze a new test vector with this tabular information for its identification. A new quantification metric is proposed in order to estimate the confidence of the classifier's output. Overall, our coding scheme provides an analytical solution that spots the most probable gas for any new test spike sequence with the quantitative feedback. In order to evaluate the robustness of our coding scheme, we target the identification of commonly found health-endangering indoor gases, such as C6H6, CH2O, CO, NO2, and SO2, as a case study. Data of these gases are acquired using our in-house fabricated gas sensor array under different operating conditions, as well as an array of commercially available gas sensors under uniform operational settings. An accuracy rate of 100% has been achieved in both cases with our probabilistic rank score coding scheme.

Original languageEnglish
Article number7047232
Pages (from-to)3934-3946
Number of pages13
JournalIEEE Sensors Journal
Volume15
Issue number7
DOIs
Publication statusPublished - 1 Jul 2015
Externally publishedYes

Fingerprint

classifiers
coding
Classifiers
Gases
electronics
gases
spiking
sensors
Sensors
spikes
Chemical sensors
Sensor arrays
Odors
Biological systems
odors
Neurons
Electronic nose
neurons
Health
health

Keywords

  • electronic nose
  • gas identification
  • Probabilistic rank score coding
  • rank-order based classifiers
  • shuffled spike sequences

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Instrumentation

Cite this

Probabilistic rank score coding : A robust rank-order based classifier for electronic nose applications. / Hassan, Muhammad; Belhaouari, Samir Brahim; Bermak, Amine.

In: IEEE Sensors Journal, Vol. 15, No. 7, 7047232, 01.07.2015, p. 3934-3946.

Research output: Contribution to journalArticle

@article{c00d3547afd4441f93b812e3f7b39390,
title = "Probabilistic rank score coding: A robust rank-order based classifier for electronic nose applications",
abstract = "Motivated by the recent experimental findings about odor identification with the unique spiking patterns of neurons in the biological olfactory system, rank-order-based classifiers have been proposed for gas identification in electronic nose applications. These classifiers rely on one-to-one mapping between the target gas and the temporal sequence of spiking sensors in an electronic nose. However, shuffled spike sequences, due to low repeatability of the response patterns from the sensors, limit the performance of these classifiers. We propose a robust probabilistic rank score coding scheme that tabulates the probability of each spiking sensor at each rank, or temporal position, by exploiting all the spike sequences of the sensors for each target gas, and we analyze a new test vector with this tabular information for its identification. A new quantification metric is proposed in order to estimate the confidence of the classifier's output. Overall, our coding scheme provides an analytical solution that spots the most probable gas for any new test spike sequence with the quantitative feedback. In order to evaluate the robustness of our coding scheme, we target the identification of commonly found health-endangering indoor gases, such as C6H6, CH2O, CO, NO2, and SO2, as a case study. Data of these gases are acquired using our in-house fabricated gas sensor array under different operating conditions, as well as an array of commercially available gas sensors under uniform operational settings. An accuracy rate of 100{\%} has been achieved in both cases with our probabilistic rank score coding scheme.",
keywords = "electronic nose, gas identification, Probabilistic rank score coding, rank-order based classifiers, shuffled spike sequences",
author = "Muhammad Hassan and Belhaouari, {Samir Brahim} and Amine Bermak",
year = "2015",
month = "7",
day = "1",
doi = "10.1109/JSEN.2015.2405296",
language = "English",
volume = "15",
pages = "3934--3946",
journal = "IEEE Sensors Journal",
issn = "1530-437X",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "7",

}

TY - JOUR

T1 - Probabilistic rank score coding

T2 - A robust rank-order based classifier for electronic nose applications

AU - Hassan, Muhammad

AU - Belhaouari, Samir Brahim

AU - Bermak, Amine

PY - 2015/7/1

Y1 - 2015/7/1

N2 - Motivated by the recent experimental findings about odor identification with the unique spiking patterns of neurons in the biological olfactory system, rank-order-based classifiers have been proposed for gas identification in electronic nose applications. These classifiers rely on one-to-one mapping between the target gas and the temporal sequence of spiking sensors in an electronic nose. However, shuffled spike sequences, due to low repeatability of the response patterns from the sensors, limit the performance of these classifiers. We propose a robust probabilistic rank score coding scheme that tabulates the probability of each spiking sensor at each rank, or temporal position, by exploiting all the spike sequences of the sensors for each target gas, and we analyze a new test vector with this tabular information for its identification. A new quantification metric is proposed in order to estimate the confidence of the classifier's output. Overall, our coding scheme provides an analytical solution that spots the most probable gas for any new test spike sequence with the quantitative feedback. In order to evaluate the robustness of our coding scheme, we target the identification of commonly found health-endangering indoor gases, such as C6H6, CH2O, CO, NO2, and SO2, as a case study. Data of these gases are acquired using our in-house fabricated gas sensor array under different operating conditions, as well as an array of commercially available gas sensors under uniform operational settings. An accuracy rate of 100% has been achieved in both cases with our probabilistic rank score coding scheme.

AB - Motivated by the recent experimental findings about odor identification with the unique spiking patterns of neurons in the biological olfactory system, rank-order-based classifiers have been proposed for gas identification in electronic nose applications. These classifiers rely on one-to-one mapping between the target gas and the temporal sequence of spiking sensors in an electronic nose. However, shuffled spike sequences, due to low repeatability of the response patterns from the sensors, limit the performance of these classifiers. We propose a robust probabilistic rank score coding scheme that tabulates the probability of each spiking sensor at each rank, or temporal position, by exploiting all the spike sequences of the sensors for each target gas, and we analyze a new test vector with this tabular information for its identification. A new quantification metric is proposed in order to estimate the confidence of the classifier's output. Overall, our coding scheme provides an analytical solution that spots the most probable gas for any new test spike sequence with the quantitative feedback. In order to evaluate the robustness of our coding scheme, we target the identification of commonly found health-endangering indoor gases, such as C6H6, CH2O, CO, NO2, and SO2, as a case study. Data of these gases are acquired using our in-house fabricated gas sensor array under different operating conditions, as well as an array of commercially available gas sensors under uniform operational settings. An accuracy rate of 100% has been achieved in both cases with our probabilistic rank score coding scheme.

KW - electronic nose

KW - gas identification

KW - Probabilistic rank score coding

KW - rank-order based classifiers

KW - shuffled spike sequences

UR - http://www.scopus.com/inward/record.url?scp=84930507823&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84930507823&partnerID=8YFLogxK

U2 - 10.1109/JSEN.2015.2405296

DO - 10.1109/JSEN.2015.2405296

M3 - Article

AN - SCOPUS:84930507823

VL - 15

SP - 3934

EP - 3946

JO - IEEE Sensors Journal

JF - IEEE Sensors Journal

SN - 1530-437X

IS - 7

M1 - 7047232

ER -