Publication detail

Restricted Boltzmann Machine Method for Dimensionality Reduction of Spectroscopic Data

VRÁBEL, J. POŘÍZKA, P. KAISER, J.

Original Title

Restricted Boltzmann Machine Method for Dimensionality Reduction of Spectroscopic Data

Type

conference proceedings

Language

English

Original Abstract

Multivariate data obtained using, for instance, Laser-Induced Breakdown Spectroscopy (LIBS) are quite bulky and complex. Advanced processing of spectroscopic data demands a multidisciplinary approach covering not only modern machine learning tools but also a deep understanding of underlying physical mechanisms. Strong non-linearities of those mechanisms are inducing problems in their processing using standard linear algorithms. Artificial Neural Networks (ANN) seem suitable for this task, and based on their success, they are given considerable attention within the spectroscopic community. We propose a new methodology based on Restricted Boltzmann Machine (ANN method) for dimensionality reduction of spectroscopic data and compare it to well known linear techniques such as PCA. Moreover, we apply this technique to the processing and mapping of very high-dimensional LIBS data.

Keywords

LIBS, Machine Learning, RBM, Neural Networks, Spectroscopy, Data, Dimension Reduction

Authors

VRÁBEL, J.; POŘÍZKA, P.; KAISER, J.

Released

8. 9. 2019

Publisher

Spektroskopická společnost Jana Marka Marci

Location

Ke Karlovu 2027/3, 120 00 Praha 2 - Nové Město

ISBN

978-80-88195-13-9

Book

EMSLIBS 2019 Book of abstracts

Pages count

293

URL

http://libs.ceitec.cz/files/281/213.pdf

BibTex

@proceedings{BUT159096,
  editor="Jakub {Vrábel} and Pavel {Pořízka} and Jozef {Kaiser}",
  title="Restricted Boltzmann Machine Method for Dimensionality Reduction of Spectroscopic Data",
  year="2019",
  pages="293",
  publisher="Spektroskopická společnost Jana Marka Marci",
  address="Ke Karlovu 2027/3, 120 00 Praha 2 - Nové Město",
  isbn="978-80-88195-13-9",
  url="http://libs.ceitec.cz/files/281/213.pdf"
}