Comparison of classification methods used for analysis of complex biological gas mixtures by means of laser spectroscopy

Abstract

The results of comparison of quality of two classificators-SVM (support vector machine) and SIMCA (soft independent modelling of class analogies) on model data contained profiles of absorbtion specra of exhalted air are presented. It is shown, that SVM classification results can be improved by preprocessing if input data with principal component analysis method.

Original language	English
Title of host publication	21st International Symposium on Atmospheric and Ocean Optics: Atmospheric Physics
Publisher	SPIE
Volume	9680
ISBN (Electronic)	9781628419085
DOIs	https://doi.org/10.1117/12.2205777
Publication status	Published - 2015
Externally published	Yes
Event	21st International Symposium on Atmospheric and Ocean Optics: Atmospheric Physics - Tomsk, Russian Federation Duration: 22 Jun 2015 → 26 Jun 2015

Conference

Conference	21st International Symposium on Atmospheric and Ocean Optics: Atmospheric Physics
Country	Russian Federation
City	Tomsk
Period	22.6.15 → 26.6.15

Keywords

gas mixtures analysis
laser spectroscopy
Principal component analysis
SIMCA
SVM

ASJC Scopus subject areas

Applied Mathematics
Computer Science Applications
Electrical and Electronic Engineering
Electronic, Optical and Magnetic Materials
Condensed Matter Physics

Access to Document

10.1117/12.2205777

Fingerprint Dive into the research topics of 'Comparison of classification methods used for analysis of complex biological gas mixtures by means of laser spectroscopy'. Together they form a unique fingerprint.

Cite this

Comparison of classification methods used for analysis of complex biological gas mixtures by means of laser spectroscopy. / Kistenev, Y. V.; Shapovalov, A. V.; Vrazhnov, D. A.; Nikolaev, V. V.; Nikiforova, O. Y.

21st International Symposium on Atmospheric and Ocean Optics: Atmospheric Physics. Vol. 9680 SPIE, 2015. 968049.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Kistenev, YV, Shapovalov, AV, Vrazhnov, DA, Nikolaev, VV & Nikiforova, OY 2015, Comparison of classification methods used for analysis of complex biological gas mixtures by means of laser spectroscopy. in 21st International Symposium on Atmospheric and Ocean Optics: Atmospheric Physics. vol. 9680, 968049, SPIE, 21st International Symposium on Atmospheric and Ocean Optics: Atmospheric Physics, Tomsk, Russian Federation, 22.6.15. https://doi.org/10.1117/12.2205777

@inproceedings{932ee922550141cc8b3011fb7194442a,

title = "Comparison of classification methods used for analysis of complex biological gas mixtures by means of laser spectroscopy",

abstract = "The results of comparison of quality of two classificators-SVM (support vector machine) and SIMCA (soft independent modelling of class analogies) on model data contained profiles of absorbtion specra of exhalted air are presented. It is shown, that SVM classification results can be improved by preprocessing if input data with principal component analysis method.",

keywords = "gas mixtures analysis, laser spectroscopy, Principal component analysis, SIMCA, SVM",

author = "Kistenev, {Y. V.} and Shapovalov, {A. V.} and Vrazhnov, {D. A.} and Nikolaev, {V. V.} and Nikiforova, {O. Y.}",

year = "2015",

doi = "10.1117/12.2205777",

language = "English",

volume = "9680",

booktitle = "21st International Symposium on Atmospheric and Ocean Optics: Atmospheric Physics",

publisher = "SPIE",

note = "21st International Symposium on Atmospheric and Ocean Optics: Atmospheric Physics ; Conference date: 22-06-2015 Through 26-06-2015",

}

TY - GEN

T1 - Comparison of classification methods used for analysis of complex biological gas mixtures by means of laser spectroscopy

AU - Kistenev, Y. V.

AU - Shapovalov, A. V.

AU - Vrazhnov, D. A.

AU - Nikolaev, V. V.

AU - Nikiforova, O. Y.

PY - 2015

Y1 - 2015

N2 - The results of comparison of quality of two classificators-SVM (support vector machine) and SIMCA (soft independent modelling of class analogies) on model data contained profiles of absorbtion specra of exhalted air are presented. It is shown, that SVM classification results can be improved by preprocessing if input data with principal component analysis method.

AB - The results of comparison of quality of two classificators-SVM (support vector machine) and SIMCA (soft independent modelling of class analogies) on model data contained profiles of absorbtion specra of exhalted air are presented. It is shown, that SVM classification results can be improved by preprocessing if input data with principal component analysis method.

KW - gas mixtures analysis

KW - laser spectroscopy

KW - Principal component analysis

KW - SIMCA

KW - SVM

UR - http://www.scopus.com/inward/record.url?scp=84963614495&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84963614495&partnerID=8YFLogxK

U2 - 10.1117/12.2205777

DO - 10.1117/12.2205777

M3 - Conference contribution

AN - SCOPUS:84963614495

VL - 9680

BT - 21st International Symposium on Atmospheric and Ocean Optics: Atmospheric Physics

PB - SPIE

T2 - 21st International Symposium on Atmospheric and Ocean Optics: Atmospheric Physics

Y2 - 22 June 2015 through 26 June 2015

ER -