Classifier comparison and sensor selection for e-noses

M. Pardo, G. Sberveglieri, B. Sisk, Nathan S Lewis

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

2 Citations (Scopus)

Abstract

Data derived from chemical vapor sensor arrays was analyzed using Fischer linear discriminant analysis (LDA) and multilayer perceptrons (MLP). Datasets produced by an e-nose based on polymer-carbon black sensors and those produced by a second e-nose based on five thin film metal oxide sensors was analyzed. The datasets were chosen to give classification problems of varying hardness: from the discrimination of two almost Gaussian distributed analytes to the discrimination of two analytes in the presents of interferents at different concentration levels. The performance of the best 5-sensors subset selected with MLP was found to be better than the performance of the LDA-selected subsets.

Original languageEnglish
Title of host publicationProceedings of IEEE Sensors
Pages606-610
Number of pages5
Volume2
Edition1
Publication statusPublished - 2003
EventSecond International Conference on Sensors: IEEE Sensors 2003 - Toronto, Ont., Canada
Duration: Oct 22 2003Oct 24 2003

Other

OtherSecond International Conference on Sensors: IEEE Sensors 2003
CountryCanada
CityToronto, Ont.
Period10/22/0310/24/03

Fingerprint

Classifiers
Discriminant analysis
Multilayer neural networks
Sensors
Sensor arrays
Carbon black
Set theory
Hardness
Vapors
Thin films
Oxides
Polymers
Metals

ASJC Scopus subject areas

  • Engineering (miscellaneous)
  • Electrical and Electronic Engineering

Cite this

Pardo, M., Sberveglieri, G., Sisk, B., & Lewis, N. S. (2003). Classifier comparison and sensor selection for e-noses. In Proceedings of IEEE Sensors (1 ed., Vol. 2, pp. 606-610)

Classifier comparison and sensor selection for e-noses. / Pardo, M.; Sberveglieri, G.; Sisk, B.; Lewis, Nathan S.

Proceedings of IEEE Sensors. Vol. 2 1. ed. 2003. p. 606-610.

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

Pardo, M, Sberveglieri, G, Sisk, B & Lewis, NS 2003, Classifier comparison and sensor selection for e-noses. in Proceedings of IEEE Sensors. 1 edn, vol. 2, pp. 606-610, Second International Conference on Sensors: IEEE Sensors 2003, Toronto, Ont., Canada, 10/22/03.
Pardo M, Sberveglieri G, Sisk B, Lewis NS. Classifier comparison and sensor selection for e-noses. In Proceedings of IEEE Sensors. 1 ed. Vol. 2. 2003. p. 606-610
Pardo, M. ; Sberveglieri, G. ; Sisk, B. ; Lewis, Nathan S. / Classifier comparison and sensor selection for e-noses. Proceedings of IEEE Sensors. Vol. 2 1. ed. 2003. pp. 606-610
@inproceedings{adc67499d15f435fb5cf63920318a03d,
title = "Classifier comparison and sensor selection for e-noses",
abstract = "Data derived from chemical vapor sensor arrays was analyzed using Fischer linear discriminant analysis (LDA) and multilayer perceptrons (MLP). Datasets produced by an e-nose based on polymer-carbon black sensors and those produced by a second e-nose based on five thin film metal oxide sensors was analyzed. The datasets were chosen to give classification problems of varying hardness: from the discrimination of two almost Gaussian distributed analytes to the discrimination of two analytes in the presents of interferents at different concentration levels. The performance of the best 5-sensors subset selected with MLP was found to be better than the performance of the LDA-selected subsets.",
author = "M. Pardo and G. Sberveglieri and B. Sisk and Lewis, {Nathan S}",
year = "2003",
language = "English",
volume = "2",
pages = "606--610",
booktitle = "Proceedings of IEEE Sensors",
edition = "1",

}

TY - GEN

T1 - Classifier comparison and sensor selection for e-noses

AU - Pardo, M.

AU - Sberveglieri, G.

AU - Sisk, B.

AU - Lewis, Nathan S

PY - 2003

Y1 - 2003

N2 - Data derived from chemical vapor sensor arrays was analyzed using Fischer linear discriminant analysis (LDA) and multilayer perceptrons (MLP). Datasets produced by an e-nose based on polymer-carbon black sensors and those produced by a second e-nose based on five thin film metal oxide sensors was analyzed. The datasets were chosen to give classification problems of varying hardness: from the discrimination of two almost Gaussian distributed analytes to the discrimination of two analytes in the presents of interferents at different concentration levels. The performance of the best 5-sensors subset selected with MLP was found to be better than the performance of the LDA-selected subsets.

AB - Data derived from chemical vapor sensor arrays was analyzed using Fischer linear discriminant analysis (LDA) and multilayer perceptrons (MLP). Datasets produced by an e-nose based on polymer-carbon black sensors and those produced by a second e-nose based on five thin film metal oxide sensors was analyzed. The datasets were chosen to give classification problems of varying hardness: from the discrimination of two almost Gaussian distributed analytes to the discrimination of two analytes in the presents of interferents at different concentration levels. The performance of the best 5-sensors subset selected with MLP was found to be better than the performance of the LDA-selected subsets.

UR - http://www.scopus.com/inward/record.url?scp=1542303707&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=1542303707&partnerID=8YFLogxK

M3 - Conference contribution

VL - 2

SP - 606

EP - 610

BT - Proceedings of IEEE Sensors

ER -