Project detail

Explainable Dimension Reduction of Large Spectroscopic Data

Duration: 01.03.2020 — 28.02.2021

Funding resources

Brno University of Technology - Vnitřní projekty VUT

- whole funder (2020-01-01 - 2021-12-31)

On the project

In modern Laser-Induced Breakdown Spectroscopy applications, we produce a very large, high-dimensional datasets which are impossible to inspect by hand or process by commonly used techniques. We have already shown that the dimension of the data can be effectively reduced. However, obtaining easily-understandable low-dimensional representation is still challenging and requires increased attention. Succeeding in this task would dramatically improve the exploration of large LIBS datasets (visualization, collaborative filtering, classification).

Mark

CEITEC VUT-J-20-6528

Default language

Czech

People responsible

Kaiser Jozef, prof. Ing., Ph.D. - fellow researcher
Vrábel Jakub, Ing. - principal person responsible

Units

Advanced instrumentation and methods for material characterization
- (2020-01-01 - 2020-12-31)
Central European Institute of Technology BUT
- (2020-01-01 - 2020-12-31)

Results

VRÁBEL, J.; POŘÍZKA, P.; KAISER, J. Restricted Boltzmann Machine method for dimensionality reduction of large spectroscopic data. Spectrochimica Acta Part B, 2020, vol. 167, no. 105849, p. NA (NA p.)ISSN: 0584-8547.
Detail

VRÁBEL, J.; KÉPEŠ, E.; POŘÍZKA, P.; KAISER, J. Classification of spectroscopic data - challenges, benchmarking and limitations. 2020.
Detail

VRÁBEL, J.; KÉPEŠ, E.; POŘÍZKA, P.; KAISER, J. Distance of spectroscopic data. 2020.
Detail

Responsibility: Vrábel Jakub, Ing.