Application of neural networks to determine the discrete spectrum of the direct Zakharov - Shabat problem

E. V. Sedov; I. S. Chekhovskoy; J. E. Prilepsky; M. P. Fedoruk

doi:10.1070/QEL17463

Application of neural networks to determine the discrete spectrum of the direct Zakharov - Shabat problem

E. V. Sedov, I. S. Chekhovskoy^*, J. E. Prilepsky, M. P. Fedoruk

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

Abstract

A neural network architecture is proposed to determine the number of solitons generated by random processes in optical wavelength-division multiplexed telecommunication systems with QPSK, 16-QAM, 64-QAM, and 1024-QAM modulation. The dependence of the prediction quality of a neural network with a special architecture on the number of soliton modes in the signal and the parameters of this signal is studied.

Original language	English
Pages (from-to)	1105-1109
Number of pages	5
Journal	Quantum Electronics
Volume	50
Issue number	12
DOIs	https://doi.org/10.1070/QEL17463
Publication status	Published - 31 Dec 2020

Bibliographical note

Funding Information:
The work was supported by the Fund of the President of the Russian Federation for State Support of Young Russian Scientists (Grant No. MK-677.2020.9). The work of I.S. Chekhovskoy was supported by the state assignment for fundamental research (FSUS-2020-0034), and the work of J.E. Prilepsky was supported by the Leverhulme Trust (Project RPG-2018-063).

Keywords

inverse scattering problem method
machine learning
neural networks
nonlinear Fourier transform
nonlinear Schrödinger equation
optical telecommunication systems
wavelength-division multiplexing
Zakharov - Shabat problem

Access to Document

10.1070/QEL17463

Cite this

@article{7989ff2397654666a9f1ef7a4c8ab491,

title = "Application of neural networks to determine the discrete spectrum of the direct Zakharov - Shabat problem",

abstract = "A neural network architecture is proposed to determine the number of solitons generated by random processes in optical wavelength-division multiplexed telecommunication systems with QPSK, 16-QAM, 64-QAM, and 1024-QAM modulation. The dependence of the prediction quality of a neural network with a special architecture on the number of soliton modes in the signal and the parameters of this signal is studied. ",

keywords = "inverse scattering problem method, machine learning, neural networks, nonlinear Fourier transform, nonlinear Schr{\"o}dinger equation, optical telecommunication systems, wavelength-division multiplexing, Zakharov - Shabat problem",

author = "Sedov, {E. V.} and Chekhovskoy, {I. S.} and Prilepsky, {J. E.} and Fedoruk, {M. P.}",

note = "Funding Information: The work was supported by the Fund of the President of the Russian Federation for State Support of Young Russian Scientists (Grant No. MK-677.2020.9). The work of I.S. Chekhovskoy was supported by the state assignment for fundamental research (FSUS-2020-0034), and the work of J.E. Prilepsky was supported by the Leverhulme Trust (Project RPG-2018-063). ",

year = "2020",

month = dec,

day = "31",

doi = "10.1070/QEL17463",

language = "English",

volume = "50",

pages = "1105--1109",

journal = "Quantum Electronics",

issn = "1063-7818",

publisher = "Turpion Ltd.",

number = "12",

}

TY - JOUR

T1 - Application of neural networks to determine the discrete spectrum of the direct Zakharov - Shabat problem

AU - Sedov, E. V.

AU - Chekhovskoy, I. S.

AU - Prilepsky, J. E.

AU - Fedoruk, M. P.

N1 - Funding Information: The work was supported by the Fund of the President of the Russian Federation for State Support of Young Russian Scientists (Grant No. MK-677.2020.9). The work of I.S. Chekhovskoy was supported by the state assignment for fundamental research (FSUS-2020-0034), and the work of J.E. Prilepsky was supported by the Leverhulme Trust (Project RPG-2018-063).

PY - 2020/12/31

Y1 - 2020/12/31

N2 - A neural network architecture is proposed to determine the number of solitons generated by random processes in optical wavelength-division multiplexed telecommunication systems with QPSK, 16-QAM, 64-QAM, and 1024-QAM modulation. The dependence of the prediction quality of a neural network with a special architecture on the number of soliton modes in the signal and the parameters of this signal is studied.

AB - A neural network architecture is proposed to determine the number of solitons generated by random processes in optical wavelength-division multiplexed telecommunication systems with QPSK, 16-QAM, 64-QAM, and 1024-QAM modulation. The dependence of the prediction quality of a neural network with a special architecture on the number of soliton modes in the signal and the parameters of this signal is studied.

KW - inverse scattering problem method

KW - machine learning

KW - neural networks

KW - nonlinear Fourier transform

KW - nonlinear Schrödinger equation

KW - optical telecommunication systems

KW - wavelength-division multiplexing

KW - Zakharov - Shabat problem

UR - http://www.scopus.com/inward/record.url?scp=85098275474&partnerID=8YFLogxK

UR - https://www.turpion.org/php/paper.phtml?journal_id=qe&paper_id=17463

U2 - 10.1070/QEL17463

DO - 10.1070/QEL17463

M3 - Article

AN - SCOPUS:85098275474

SN - 1063-7818

VL - 50

SP - 1105

EP - 1109

JO - Quantum Electronics

JF - Quantum Electronics

IS - 12

ER -

Application of neural networks to determine the discrete spectrum of the direct Zakharov - Shabat problem

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this