Publication result detail

Classification of challenging LIBS soil sample data - EMSLIBS contest

Vrábel, J.; Képeš, E.; Duponchel, L.; Motto-Ros, V.; Fabre, C.; Connemann, S.; Schreckenberg, F.; Riebe, D.; Junjuri, R.; Gundawar, M.K.; Tan, X.; Pořízka, P.; Kaiser, J.

Original Title

Classification of challenging LIBS soil sample data - EMSLIBS contest

English Title

Classification of challenging LIBS soil sample data - EMSLIBS contest

Type

WoS Article

Original Abstract

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.

English abstract

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.

Keywords

EMSLIBS contest; Chemometrics; Laser-induced breakdown spectroscopy (LIBS); Machine learning; Classification benchmark

Key words in English

EMSLIBS contest; Chemometrics; Laser-induced breakdown spectroscopy (LIBS); Machine learning; Classification benchmark

Authors

Vrábel, J.; Képeš, E.; Duponchel, L.; Motto-Ros, V.; Fabre, C.; Connemann, S.; Schreckenberg, F.; Riebe, D.; Junjuri, R.; Gundawar, M.K.; Tan, X.; Pořízka, P.; Kaiser, J.

RIV year

2021

Released

01.07.2020

Publisher

Elsevier

ISBN

0584-8547

Periodical

SPECTROCHIMICA ACTA PART B-ATOMIC SPECTROSCOPY

Volume

169

Number

105872

State

United Kingdom of Great Britain and Northern Ireland

Pages from

1

Pages to

12

Pages count

12

URL

https://www.sciencedirect.com/science/article/pii/S0584854720300422

BibTex

@article{BUT163914,
  author="Vrábel, J. and Képeš, E. and Duponchel, L. and Motto-Ros, V. and Fabre, C. and Connemann, S. and Schreckenberg, F. and Riebe, D. and Junjuri, R. and Gundawar, M.K. and Tan, X. and Pořízka, P. and Kaiser, J.",
  title="Classification of challenging LIBS soil sample data - EMSLIBS contest",
  journal="SPECTROCHIMICA ACTA PART B-ATOMIC SPECTROSCOPY",
  year="2020",
  volume="169",
  number="105872",
  pages="1--12",
  doi="10.1016/j.sab.2020.105872",
  issn="0584-8547",
  url="https://www.sciencedirect.com/science/article/pii/S0584854720300422"
}

Documents

Vrabel Classification
Vrabel description long