TY  - JOUR
AU  - Ivanović, Marija D.
AU  - Mančić, Ana
AU  - Hermann-Avigliano, Carla
AU  - Hadžievski, Ljupčo
AU  - Maluckov, Aleksandra
PY  - 2020
UR  - https://vinar.vin.bg.ac.rs/handle/123456789/8837
AB  - In this paper, we establish a new scheme for identification and classification of high intensity events generated by the propagation of light through a photorefractive SBN crystal. Among these events, which are the inevitable consequence of the development of modulation instability, are speckling and soliton-like patterns. The usual classifiers, developed on statistical measures, such as the significant intensity, often provide only a partial characterization of these events. Here, we try to overcome this deficiency by implementing the convolution neural network method to relate experimental data of light intensity distribution and corresponding numerical outputs with different high intensity regimes. The train and test sets are formed of experimentally obtained intensity profiles at the crystal output facet and corresponding numerical profiles. The accuracy of detection of speckles reaches maximum value of 100%, while the accuracy of solitons and caustic detection is above 97%. These performances are promising for the creation of neural network based routines for prediction of extreme events in wave media. © 2020 IOP Publishing Ltd.
T2  - Journal of Optics
T1  - Deep learning-based classification of high intensity light patterns in photorefractive crystals
VL  - 22
IS  - 3
SP  - 035504
DO  - 10.1088/2040-8986/ab70f0
ER  - 

@article{
author = "Ivanović, Marija D. and Mančić, Ana and Hermann-Avigliano, Carla and Hadžievski, Ljupčo and Maluckov, Aleksandra",
year = "2020",
abstract = "In this paper, we establish a new scheme for identification and classification of high intensity events generated by the propagation of light through a photorefractive SBN crystal. Among these events, which are the inevitable consequence of the development of modulation instability, are speckling and soliton-like patterns. The usual classifiers, developed on statistical measures, such as the significant intensity, often provide only a partial characterization of these events. Here, we try to overcome this deficiency by implementing the convolution neural network method to relate experimental data of light intensity distribution and corresponding numerical outputs with different high intensity regimes. The train and test sets are formed of experimentally obtained intensity profiles at the crystal output facet and corresponding numerical profiles. The accuracy of detection of speckles reaches maximum value of 100%, while the accuracy of solitons and caustic detection is above 97%. These performances are promising for the creation of neural network based routines for prediction of extreme events in wave media. © 2020 IOP Publishing Ltd.",
journal = "Journal of Optics",
title = "Deep learning-based classification of high intensity light patterns in photorefractive crystals",
volume = "22",
number = "3",
pages = "035504",
doi = "10.1088/2040-8986/ab70f0"
}

Ivanović, M. D., Mančić, A., Hermann-Avigliano, C., Hadžievski, L.,& Maluckov, A.. (2020). Deep learning-based classification of high intensity light patterns in photorefractive crystals. in Journal of Optics, 22(3), 035504.
https://doi.org/10.1088/2040-8986/ab70f0

Ivanović MD, Mančić A, Hermann-Avigliano C, Hadžievski L, Maluckov A. Deep learning-based classification of high intensity light patterns in photorefractive crystals. in Journal of Optics. 2020;22(3):035504.
doi:10.1088/2040-8986/ab70f0 .

Ivanović, Marija D., Mančić, Ana, Hermann-Avigliano, Carla, Hadžievski, Ljupčo, Maluckov, Aleksandra, "Deep learning-based classification of high intensity light patterns in photorefractive crystals" in Journal of Optics, 22, no. 3 (2020):035504,
https://doi.org/10.1088/2040-8986/ab70f0 . .