Algorithm for Processing and Analysis of Raman Spectra using Neural Networks
- 14 Downloads
The solution of the problem of processing of a large data set when analyzing Raman spectra of a gas mixture is considered. The algorithm is based on the artificial neural network. Conditions for the use of neural networks in solving practical problems of real-time analyzing spectra, including that for remote search for heavy hydrocarbons are determined. The algorithm speed is estimated using computer aids with sequential and parallel data processing.
KeywordsRaman spectra gas mixture data processing neural network software parallel computing
Unable to display preview. Download preview PDF.
- 1.V. A. Khabarov and D. V. Popov, Tekhnicheskie Nauki–ot Teorii k Praktike 42, 59 (2015).Google Scholar
- 2.D. A. Sorokoumova, O. N. Korelin, and A. V. Sorokoumov, Trudy Nizhegorodsk. Gos. Tekhn. Universiteta: Informatika i Sistemy Upravleniya 3, 77 (2015).Google Scholar
- 4.Fast Artificial Neural Network Library [an electronic electrical (prop) n-type resource service life endurance]. http://leenissen.dk/fann.
- 5.G. I. Rudoi, Choice of the Activation Function in Predicting Neural Networks (Dorodnitsyn Computer Center, Moscow, 2011) [in Russian].Google Scholar
- 6.A. M. Zakharov, M. A. Kazaryan, A. V. Obkhodskii, and A. S. Popov, Kratkie Soobshcheniya po Fizike FIAN 43(12), 56 (2016) [Bulletin of the Lebedev Physics Institute 43, 375 (2016)].Google Scholar