%0 Journal Article %T NEURAL NETWORK SOLUTION OF INVERSE PROBLEM OF IDENTIFICATION OF LIGHT PETROLEUM PRODUCTS BY RAMAN SPECTROSCOPY FOR FIRE INVESTIGATION %A Otgon, F.V. %A Dementiev, F.A. %A Ivanov, A.V. %K light petroleum products, Raman spectrometry, neural network architecture, fire investigation %J NATURAL AND MAN-MADE RISKS (PHYSICO-MATHEMATICAL AND APPLIED ASPECTS) %D 2018 %N 2018 %P 7 %I Saint-Petersburg University of State Fire Service of Emercom of Russia