Laser-Induced Breakdown Spectroscopy coupled with chemometrics
for the analysis of steel: The issue of spectral outliers
filtering

J 2016

Laser-Induced Breakdown Spectroscopy coupled with chemometrics for the analysis of steel: The issue of spectral outliers filtering

POŘÍZKA, Pavel, Jakub KLUS, David PROCHAZKA, Erik KÉPEŠ, Aleš HRDLIČKA et. al.

Basic information

Original name

Laser-Induced Breakdown Spectroscopy coupled with chemometrics for the analysis of steel: The issue of spectral outliers filtering

Authors

POŘÍZKA, Pavel (203 Czech Republic), Jakub KLUS (203 Czech Republic), David PROCHAZKA (203 Czech Republic), Erik KÉPEŠ (203 Czech Republic), Aleš HRDLIČKA (203 Czech Republic, belonging to the institution), Jan NOVOTNÝ (203 Czech Republic), Karel NOVOTNÝ (203 Czech Republic, guarantor, belonging to the institution) and Jozef KAISER (203 Czech Republic)

Edition

Spectrochimica Acta B, Elsevier, 2016, 0584-8547

Other information

Language

English

Type of outcome

Článek v odborném periodiku

Field of Study

10406 Analytical chemistry

Country of publisher

United Kingdom of Great Britain and Northern Ireland

Confidentiality degree

není předmětem státního či obchodního tajemství

References:

URL

Impact factor

Impact factor: 3.241

RIV identification code

RIV/00216224:14310/16:00093775

Organization unit

Faculty of Science

DOI

http://dx.doi.org/10.1016/j.sab.2016.08.008

UT WoS

000389497400012

Keywords in English

Laser-Induced Breakdown Spectroscopy; LIBS; Outlier filtering; Principal Component Analysis; PCA; Linear correlation; Total spectral intensity; Soft Independent Modelling of Class Analogies; SIMCA

Abstract

V originále

In this manuscript we highlight the necessity of outlier filtering prior the multivariate classification in Laser-Induced Breakdown Spectroscopy (LIBS) analyses. For the purpose of classification we chose to analyse BAM steel standards that possess similar composition of major and trace elements. To assess the improvement in figures of merit we compared the performance of three outlier filtering approaches (based on Principal Component Analysis, linear correlation and total spectral intensity) already separately discussed in the LIBS literature. The truncated data set was classified using Soft Independent Modelling of Class Analogies (SIMCA). Yielded results showed significant improvement in the performance of multivariate classification coupled to filtered data. The best performance was observed for the total spectral intensity filtering approach gaining the analytical figures of merit (overall accuracy, sensitivity, and specificity) over 98%. It is noteworthy that the results showed relatively low sensitivity and high specificity of the SIMCA algorithm regardless of the presence of outliers in the data sets. Moreover, it was shown that the variance in the data topology of training and testing data sets has a great impact on the consequent data classification.

Links

LQ1601, research and development project

Name: CEITEC 2020 (Acronym: CEITEC2020)

Investor: Ministry of Education, Youth and Sports of the CR

Citovat

POŘÍZKA, Pavel, Jakub KLUS, David PROCHAZKA, Erik KÉPEŠ, Aleš HRDLIČKA, Jan NOVOTNÝ, Karel NOVOTNÝ and Jozef KAISER. Laser-Induced Breakdown Spectroscopy coupled with chemometrics for the analysis of steel: The issue of spectral outliers filtering. Spectrochimica Acta B. Elsevier, 2016, vol. 123, September, p. 114-120. ISSN 0584-8547. Available from: https://dx.doi.org/10.1016/j.sab.2016.08.008.

@article{1374285,
   author = {Pořízka, Pavel and Klus, Jakub and Prochazka, David and Képeš, Erik and Hrdlička, Aleš and Novotný, Jan and Novotný, Karel and Kaiser, Jozef},
   article_number = {September},
   doi = {http://dx.doi.org/10.1016/j.sab.2016.08.008},
   keywords = {Laser-Induced Breakdown Spectroscopy; LIBS; Outlier filtering; Principal Component Analysis; PCA; Linear correlation; Total spectral intensity; Soft Independent Modelling of Class Analogies; SIMCA},
   language = {eng},
   issn = {0584-8547},
   journal = {Spectrochimica Acta B},
   title = {Laser-Induced Breakdown Spectroscopy coupled with chemometrics for the analysis of steel: The issue of spectral outliers filtering},
   url = {http://www.sciencedirect.com/science/article/pii/S0584854716301367},
   volume = {123},
   year = {2016}
}

TY  - JOUR
ID  - 1374285
AU  - Pořízka, Pavel - Klus, Jakub - Prochazka, David - Képeš, Erik - Hrdlička, Aleš - Novotný, Jan - Novotný, Karel - Kaiser, Jozef
PY  - 2016
TI  - Laser-Induced Breakdown Spectroscopy coupled with chemometrics for the analysis of steel: The issue of spectral outliers filtering
JF  - Spectrochimica Acta B
VL  - 123
IS  - September
SP  - 114-120
EP  - 114-120
PB  - Elsevier
SN  - 05848547
KW  - Laser-Induced Breakdown Spectroscopy
KW  - LIBS
KW  - Outlier filtering
KW  - Principal Component Analysis
KW  - PCA
KW  - Linear correlation
KW  - Total spectral intensity
KW  - Soft Independent Modelling of Class Analogies
KW  - SIMCA
UR  - http://www.sciencedirect.com/science/article/pii/S0584854716301367
N2  - In this manuscript we highlight the necessity of outlier filtering prior the multivariate classification in Laser-Induced Breakdown Spectroscopy (LIBS) analyses. For the purpose of classification we chose to analyse BAM steel standards that possess similar composition of major and trace elements. To assess the improvement in figures of merit we compared the performance of three outlier filtering approaches (based on Principal Component Analysis, linear correlation and total spectral intensity) already separately discussed in the LIBS literature. The truncated data set was classified using Soft Independent Modelling of Class Analogies (SIMCA). Yielded results showed significant improvement in the performance of multivariate classification coupled to filtered data. The best performance was observed for the total spectral intensity filtering approach gaining the analytical figures of merit (overall accuracy, sensitivity, and specificity) over 98%. It is noteworthy that the results showed relatively low sensitivity and high specificity of the SIMCA algorithm regardless of the presence of outliers in the data sets. Moreover, it was shown that the variance in the data topology of training and testing data sets has a great impact on the consequent data classification.
ER  -

POŘÍZKA, Pavel, Jakub KLUS, David PROCHAZKA, Erik KÉPEŠ, Aleš HRDLIČKA, Jan NOVOTNÝ, Karel NOVOTNÝ and Jozef KAISER. Laser-Induced Breakdown Spectroscopy coupled with chemometrics for the analysis of steel: The issue of spectral outliers filtering. \textit{Spectrochimica Acta B}. Elsevier, 2016, vol.~123, September, p.~114-120. ISSN~0584-8547. Available from: https://dx.doi.org/10.1016/j.sab.2016.08.008.

Detailed Information on Publication Record