Comparison of the performance of different discriminant algorithms, in analyte discrimination tasks using an array of carbon black - Polymer composite vapor detectors

T. P. Vaid, M. C. Burl, Nathan S Lewis

Research output: Contribution to journalArticle

42 Citations (Scopus)

Abstract

An array of 20 compositionally different carbon black - polymer composite chemiresistor vapor detectors was challenged under laboratory conditions to discriminate between a pair of extremely similar pure analytes (H2O and D2O), compositionally similar mixtures of pairs of compounds, and low concentrations of vapors of similar chemicals. Several discriminant algorithms were utilized, including k nearest neighbors (κNN, with κ = 1), linear discriminant analysis (LDA, or Fisher's linear discriminant), quadratic discriminant analysis (QDA), regularized discriminant analysis (RDA, a hybrid of LDA and QDA), partial least squares, and soft independent modeling of class analogy (SIMCA). H2O and D2O were perfectly classified by most of the discriminants when a separate training and test set was used. As expected, discrimination performance decreased as the analyte concentration decreased, and performance decreased as the composition of the analyte mixtures became more similar. RDA was the overall best-performing discriminant, and LDA was the best-performing discriminant that did not require several cross-validations for optimization.

Original languageEnglish
Pages (from-to)321-331
Number of pages11
JournalAnalytical Chemistry
Volume73
Issue number2
DOIs
Publication statusPublished - Jan 15 2001

Fingerprint

Soot
Discriminant analysis
Polymers
Vapors
Detectors
Composite materials
Chemical analysis

ASJC Scopus subject areas

  • Analytical Chemistry

Cite this

@article{c26080dffa4d46bf8fe9a5f2fb58b323,
title = "Comparison of the performance of different discriminant algorithms, in analyte discrimination tasks using an array of carbon black - Polymer composite vapor detectors",
abstract = "An array of 20 compositionally different carbon black - polymer composite chemiresistor vapor detectors was challenged under laboratory conditions to discriminate between a pair of extremely similar pure analytes (H2O and D2O), compositionally similar mixtures of pairs of compounds, and low concentrations of vapors of similar chemicals. Several discriminant algorithms were utilized, including k nearest neighbors (κNN, with κ = 1), linear discriminant analysis (LDA, or Fisher's linear discriminant), quadratic discriminant analysis (QDA), regularized discriminant analysis (RDA, a hybrid of LDA and QDA), partial least squares, and soft independent modeling of class analogy (SIMCA). H2O and D2O were perfectly classified by most of the discriminants when a separate training and test set was used. As expected, discrimination performance decreased as the analyte concentration decreased, and performance decreased as the composition of the analyte mixtures became more similar. RDA was the overall best-performing discriminant, and LDA was the best-performing discriminant that did not require several cross-validations for optimization.",
author = "Vaid, {T. P.} and Burl, {M. C.} and Lewis, {Nathan S}",
year = "2001",
month = "1",
day = "15",
doi = "10.1021/ac000792f",
language = "English",
volume = "73",
pages = "321--331",
journal = "Analytical Chemistry",
issn = "0003-2700",
publisher = "American Chemical Society",
number = "2",

}

TY - JOUR

T1 - Comparison of the performance of different discriminant algorithms, in analyte discrimination tasks using an array of carbon black - Polymer composite vapor detectors

AU - Vaid, T. P.

AU - Burl, M. C.

AU - Lewis, Nathan S

PY - 2001/1/15

Y1 - 2001/1/15

N2 - An array of 20 compositionally different carbon black - polymer composite chemiresistor vapor detectors was challenged under laboratory conditions to discriminate between a pair of extremely similar pure analytes (H2O and D2O), compositionally similar mixtures of pairs of compounds, and low concentrations of vapors of similar chemicals. Several discriminant algorithms were utilized, including k nearest neighbors (κNN, with κ = 1), linear discriminant analysis (LDA, or Fisher's linear discriminant), quadratic discriminant analysis (QDA), regularized discriminant analysis (RDA, a hybrid of LDA and QDA), partial least squares, and soft independent modeling of class analogy (SIMCA). H2O and D2O were perfectly classified by most of the discriminants when a separate training and test set was used. As expected, discrimination performance decreased as the analyte concentration decreased, and performance decreased as the composition of the analyte mixtures became more similar. RDA was the overall best-performing discriminant, and LDA was the best-performing discriminant that did not require several cross-validations for optimization.

AB - An array of 20 compositionally different carbon black - polymer composite chemiresistor vapor detectors was challenged under laboratory conditions to discriminate between a pair of extremely similar pure analytes (H2O and D2O), compositionally similar mixtures of pairs of compounds, and low concentrations of vapors of similar chemicals. Several discriminant algorithms were utilized, including k nearest neighbors (κNN, with κ = 1), linear discriminant analysis (LDA, or Fisher's linear discriminant), quadratic discriminant analysis (QDA), regularized discriminant analysis (RDA, a hybrid of LDA and QDA), partial least squares, and soft independent modeling of class analogy (SIMCA). H2O and D2O were perfectly classified by most of the discriminants when a separate training and test set was used. As expected, discrimination performance decreased as the analyte concentration decreased, and performance decreased as the composition of the analyte mixtures became more similar. RDA was the overall best-performing discriminant, and LDA was the best-performing discriminant that did not require several cross-validations for optimization.

UR - http://www.scopus.com/inward/record.url?scp=0035862840&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0035862840&partnerID=8YFLogxK

U2 - 10.1021/ac000792f

DO - 10.1021/ac000792f

M3 - Article

VL - 73

SP - 321

EP - 331

JO - Analytical Chemistry

JF - Analytical Chemistry

SN - 0003-2700

IS - 2

ER -