Combination of laser-induced breakdown spectroscopy and Raman
spectroscopy for multivariate classification of bacteria

J 2018

Combination of laser-induced breakdown spectroscopy and Raman spectroscopy for multivariate classification of bacteria

PROCHAZKA, David, Martin MAZURA, Ota SAMEK, Katarína REBROŠOVÁ, Pavel PORIZKA et. al.

Základní údaje

Originální název

Combination of laser-induced breakdown spectroscopy and Raman spectroscopy for multivariate classification of bacteria

Autoři

PROCHAZKA, David (203 Česká republika, garant), Martin MAZURA (203 Česká republika), Ota SAMEK (203 Česká republika), Katarína REBROŠOVÁ (703 Slovensko, domácí), Pavel PORIZKA (203 Česká republika), J. KLUS (203 Česká republika), Petra PROCHAZKOVÁ (203 Česká republika, domácí), J. NOVOTNY (203 Česká republika), Karel NOVOTNÝ (203 Česká republika) a J. KAISER (203 Česká republika)

Vydání

Spectrochimica Acta, Part B: Atomic Spectroscopy, Oxford, PERGAMON-ELSEVIER SCIENCE LTD, 2018, 0584-8547

Další údaje

Jazyk

angličtina

Typ výsledku

Článek v odborném periodiku

Obor

21100 2.11 Other engineering and technologies

Stát vydavatele

Velká Británie a Severní Irsko

Utajení

není předmětem státního či obchodního tajemství

Odkazy

full text

Impakt faktor

Impact factor: 3.101

Kód RIV

RIV/00216224:14110/18:00102429

Organizační jednotka

Lékařská fakulta

DOI

http://dx.doi.org/10.1016/j.sab.2017.11.004

UT WoS

000423897000002

Klíčová slova anglicky

Laser-induced breakdown spectroscopy; Raman spectroscopy; Chemometrics; Bacteria

Štítky

14110113, podil, rivok

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 26. 3. 2019 10:29, Soňa Böhmová

Anotace

V originále

In this work, we investigate the impact of data provided by complementary laser-based spectroscopic methods on multivariate classification accuracy. Discrimination and classification of five Staphylococcus bacterial strains and one strain of Escherichia coli is presented. The technique that we used for measurements is a combination of Raman spectroscopy and Laser-Induced Breakdown Spectroscopy (LIBS). Obtained spectroscopic data were then processed using Multivariate Data Analysis algorithms. Principal Components Analysis (PCA) was selected as the most suitable technique for visualization of bacterial strains data. To classify the bacterial strains, we used Neural Networks, namely a supervised version of Kohonen's self-organizing maps (SOM). We were processing results in three different ways - separately from LIBS measurements, from Raman measurements, and we also merged data from both mentioned methods. The three types of results were then compared. By applying the PCA to Raman spectroscopy data, we observed that two bacterial strains were fully distinguished from the rest of the data set. In the case of LIBS data, three bacterial strains were fully discriminated. Using a combination of data from both methods, we achieved the complete discrimination of all bacterial strains. All the data were classified with a high success rate using SOM algorithm. The most accurate classification was obtained using a combination of data from both techniques. The classification accuracy varied, depending on specific samples and techniques. As for LIBS, the classification accuracy ranged from 45% to 100%, as for Raman Spectroscopy from 50% to 100% and in case of merged data, all samples were classified correctly. Based on the results of the experiments presented in this work, we can assume that the combination of Raman spectroscopy and LIBS significantly enhances discrimination and classification accuracy of bacterial species and strains. The reason is the complementarity in obtained chemical information while using these two methods. (C) 2017 Elsevier B.V. All rights reserved.

Návaznosti

LQ1601, projekt VaV

Název: CEITEC 2020 (Akronym: CEITEC2020)

Investor: Ministerstvo školství, mládeže a tělovýchovy ČR, CEITEC 2020

Citovat

PROCHAZKA, David, Martin MAZURA, Ota SAMEK, Katarína REBROŠOVÁ, Pavel PORIZKA, J. KLUS, Petra PROCHAZKOVÁ, J. NOVOTNY, Karel NOVOTNÝ a J. KAISER. Combination of laser-induced breakdown spectroscopy and Raman spectroscopy for multivariate classification of bacteria. Spectrochimica Acta, Part B: Atomic Spectroscopy. Oxford: PERGAMON-ELSEVIER SCIENCE LTD, 2018, roč. 139, JAN 2018, s. 6-12. ISSN 0584-8547. Dostupné z: https://dx.doi.org/10.1016/j.sab.2017.11.004.

@article{1411768,
   author = {Prochazka, David and Mazura, Martin and Samek, Ota and Rebrošová, Katarína and Porizka, Pavel and Klus, J. and Prochazková, Petra and Novotny, J. and Novotný, Karel and Kaiser, J.},
   article_location = {Oxford},
   article_number = {JAN 2018},
   doi = {http://dx.doi.org/10.1016/j.sab.2017.11.004},
   keywords = {Laser-induced breakdown spectroscopy; Raman spectroscopy; Chemometrics; Bacteria},
   language = {eng},
   issn = {0584-8547},
   journal = {Spectrochimica Acta, Part B: Atomic Spectroscopy},
   title = {Combination of laser-induced breakdown spectroscopy and Raman spectroscopy for multivariate classification of bacteria},
   url = {https://www.sciencedirect.com/science/article/pii/S058485471730109X},
   volume = {139},
   year = {2018}
}

TY  - JOUR
ID  - 1411768
AU  - Prochazka, David - Mazura, Martin - Samek, Ota - Rebrošová, Katarína - Porizka, Pavel - Klus, J. - Prochazková, Petra - Novotny, J. - Novotný, Karel - Kaiser, J.
PY  - 2018
TI  - Combination of laser-induced breakdown spectroscopy and Raman spectroscopy for multivariate classification of bacteria
JF  - Spectrochimica Acta, Part B: Atomic Spectroscopy
VL  - 139
IS  - JAN 2018
SP  - 6-12
EP  - 6-12
PB  - PERGAMON-ELSEVIER SCIENCE LTD
SN  - 05848547
KW  - Laser-induced breakdown spectroscopy
KW  - Raman spectroscopy
KW  - Chemometrics
KW  - Bacteria
UR  - https://www.sciencedirect.com/science/article/pii/S058485471730109X
N2  - In this work, we investigate the impact of data provided by complementary laser-based spectroscopic methods on multivariate classification accuracy. Discrimination and classification of five Staphylococcus bacterial strains and one strain of Escherichia coli is presented. The technique that we used for measurements is a combination of Raman spectroscopy and Laser-Induced Breakdown Spectroscopy (LIBS). Obtained spectroscopic data were then processed using Multivariate Data Analysis algorithms. Principal Components Analysis (PCA) was selected as the most suitable technique for visualization of bacterial strains data. To classify the bacterial strains, we used Neural Networks, namely a supervised version of Kohonen's self-organizing maps (SOM). We were processing results in three different ways - separately from LIBS measurements, from Raman measurements, and we also merged data from both mentioned methods. The three types of results were then compared. By applying the PCA to Raman spectroscopy data, we observed that two bacterial strains were fully distinguished from the rest of the data set. In the case of LIBS data, three bacterial strains were fully discriminated. Using a combination of data from both methods, we achieved the complete discrimination of all bacterial strains. All the data were classified with a high success rate using SOM algorithm. The most accurate classification was obtained using a combination of data from both techniques. The classification accuracy varied, depending on specific samples and techniques. As for LIBS, the classification accuracy ranged from 45% to 100%, as for Raman Spectroscopy from 50% to 100% and in case of merged data, all samples were classified correctly. Based on the results of the experiments presented in this work, we can assume that the combination of Raman spectroscopy and LIBS significantly enhances discrimination and classification accuracy of bacterial species and strains. The reason is the complementarity in obtained chemical information while using these two methods. (C) 2017 Elsevier B.V. All rights reserved.
ER  -

PROCHAZKA, David, Martin MAZURA, Ota SAMEK, Katarína REBROŠOVÁ, Pavel PORIZKA, J. KLUS, Petra PROCHAZKOVÁ, J. NOVOTNY, Karel NOVOTNÝ a J. KAISER. Combination of laser-induced breakdown spectroscopy and Raman spectroscopy for multivariate classification of bacteria. \textit{Spectrochimica Acta, Part B: Atomic Spectroscopy}. Oxford: PERGAMON-ELSEVIER SCIENCE LTD, 2018, roč.~139, JAN 2018, s.~6-12. ISSN~0584-8547. Dostupné z: https://dx.doi.org/10.1016/j.sab.2017.11.004.

Podrobný výpis o publikaci