Classification of challenging Laser-Induced Breakdown Spectroscopy soil sample data - EMSLIBS contest - Institut Lumière Matière Accéder directement au contenu
Article Dans Une Revue Spectrochimica Acta Part B: Atomic Spectroscopy Année : 2020

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

Résumé

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.
Fichier principal
Vignette du fichier
1-s2.0-S0584854720300422-main.pdf (2.61 Mo) Télécharger le fichier
Origine : Accord explicite pour ce dépôt
Loading...

Dates et versions

hal-02869477 , version 1 (27-08-2020)

Licence

Paternité

Identifiants

Citer

Jakub Vrábel, Erik Képeš, Ludovic Duponchel, Vincent Motto-Ros, Cécile Fabre, et al.. Classification of challenging Laser-Induced Breakdown Spectroscopy soil sample data - EMSLIBS contest. Spectrochimica Acta Part B: Atomic Spectroscopy, 2020, 169, pp.105872. ⟨10.1016/j.sab.2020.105872⟩. ⟨hal-02869477⟩
197 Consultations
144 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More