Title :

Classification of challenging Laser-Induced Breakdown Spectroscopy soil sample data - EMSLIBS contest

Author(s) :

Vrábel, Jakub [Auteur]
Central European Institute of Technology [Brno] [CEITEC MU]
Képeš, Erik [Auteur]
Central European Institute of Technology [Brno] [CEITEC MU]
Duponchel, Ludovic [Auteur]
Laboratoire Avancé de Spectroscopie pour les Intéractions la Réactivité et l'Environnement (LASIRE) - UMR 8516
Motto-Ros, Vincent [Auteur]
Institut Lumière Matière [Villeurbanne] [ILM]
Fabre, Cécile [Auteur]
GeoRessources
Schreckenberg, Frederik [Auteur]
Fraunhofer-Institut für Lasertechnik [ILT]
Prasse, Paul [Auteur]
Institut für informatik [Potsdam]
Riebe, Daniel [Auteur]
Institut für Chemie [Universität Potsdam] | Institute of Chemistry [University of Potsdam]
Junjuri, Rajendhar [Auteur]
University of Hyderabad
Gundawar, Manoj Kumar [Auteur]
University of Hyderabad
Tan, Xiaofeng [Auteur]
Pořízka, Pavel [Auteur]
Central European Institute of Technology [Brno] [CEITEC MU]
Kaiser, Jozef [Auteur]
Central European Institute of Technology [Brno] [CEITEC MU]

Journal title :

Spectrochimica Acta Part B: Atomic Spectroscopy

Volume number :

169

Publication date :

2020

HAL domain(s) :

Planète et Univers [physics]/Sciences de la Terre

English abstract : [en]

We present results of the classification contest organized for the EMSLIBS 2019 conference. For this publication, we chose only the five best approaches and discussed their algorithm in detail. The main focus of the contest ...
Show more >We present results of the classification contest organized for the EMSLIBS 2019 conference. For this publication, we chose only the five best approaches and discussed their algorithm in detail. The main focus of the contest reflected both recent and long-term challenges of Laser-Induced Breakdown Spectroscopy (LIBS) data processing. The contest was designed with a purpose to raise a challenge in handling and processing a very large dataset, containing high-dimensional elemental spectra. For the contest, 138 samples were measured using a lab-based LIBS system. In total, the data set consisted of 70,000 spectra, separated into 12 classes according to their elemental composition. Due to its extensivity and complexity, the data set is unique within the LIBS community. The central idea was to simulate the so-called “out-of-sample” classification (i.e. according to similar elemental composition), implying various real-world applications. Even more, it reflects the current level of expertise in the LIBS community and the capability of the LIBS method itself.Show less >

Audience :

Non spécifiée

Popular science :

Non

Administrative institution(s) :

ENSCL
CNRS
Université de Lille

Collections :

• Laboratoire Avancé de Spectroscopie pour les Intéractions la Réactivité et l'Environnement (LASIRE) - UMR 8516

Research team(s) :

Propriétés magnéto structurales des matériaux (PMSM)

Submission date :

2024-02-21T17:12:02Z
2024-02-23T11:27:17Z
2024-02-23T11:45:01Z