Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Classification of challenging Laser-Induced Breakdown Spectroscopy soilsample data - EMSLIBS contest

: Vrábel, Jakub; Képeš, Erik; Duponchel, Ludovik; Motto-Ros, Vincent; Fabred, Cécile; Connemann, Sven; Schreckenberg, Frederik; Prasse, Paul; Riebe, Daniel; Junjuri, Rajendhar; Gundawarh, Manoj Kumar; Tan, Xiaofeng; Pořízka, Pavel; Kaiser, Jozef

Volltext ()

Spectrochimica acta. B 169 (2020), Art. 105872, 12 S.
ISSN: 0038-6987
ISSN: 0584-8547
Zeitschriftenaufsatz, Elektronische Publikation
Fraunhofer ILT ()
Laser-induced breakdown spectroscopy (LIBS); Machine Learning; Classification benchmark; EMSLIBS contest; Chemometrics

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.