Detailed study of spectral features obtained from LIBS and Raman spectroscopy

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26620%2F20%3APU137846" target="_blank" >RIV/00216305:26620/20:PU137846 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.scixconference.org/" target="_blank" >https://www.scixconference.org/</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Detailed study of spectral features obtained from LIBS and Raman spectroscopy

Popis výsledku v původním jazyce

Investigation of samples is getting complex when providing structural and chemical analysis. The chemical analysis itself may be obtained via the utilization of various techniques giving diverse, yet complementary information. Their combined utilization is not trivial when considering sample preparation, sampling, data collection, and processing. In our work, we focus on elaborate data processing to provide robust data analysis and not using machine learning tools as black boxes. This demands a straightforward connection of machine learning to the data sources (e.g., spectroscopy, plasma physics, analytical chemistry) for efficient feature extraction and visualization. We have selected a series of polymer materials characterized by complex spectra datasets obtained by using various spectroscopic methods (LIBS and Raman spectroscopy). We demonstrate a step-by-step algorithm for polymer classification using individual spectroscopic datasets as well as their combination. The robustness of our classificat

Název v anglickém jazyce

Detailed study of spectral features obtained from LIBS and Raman spectroscopy

Popis výsledku anglicky

Investigation of samples is getting complex when providing structural and chemical analysis. The chemical analysis itself may be obtained via the utilization of various techniques giving diverse, yet complementary information. Their combined utilization is not trivial when considering sample preparation, sampling, data collection, and processing. In our work, we focus on elaborate data processing to provide robust data analysis and not using machine learning tools as black boxes. This demands a straightforward connection of machine learning to the data sources (e.g., spectroscopy, plasma physics, analytical chemistry) for efficient feature extraction and visualization. We have selected a series of polymer materials characterized by complex spectra datasets obtained by using various spectroscopic methods (LIBS and Raman spectroscopy). We demonstrate a step-by-step algorithm for polymer classification using individual spectroscopic datasets as well as their combination. The robustness of our classificat

Druh

O - Ostatní výsledky

CEP obor

—

OECD FORD obor

10406 - Analytical chemistry

Projekt

<a href="/cs/project/LQ1601" target="_blank" >LQ1601: CEITEC 2020</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2020

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů