Open AccessDirect decoding of nonlinear OFDM-QAM signals using convolutional neural network
Author(s) -
Wen Qi Zhang,
Terence Chan,
V Shahraam Afshar
Publication year - 2021
Publication title -
optics express
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.394
H-Index - 271
ISSN - 1094-4087
DOI - 10.1364/oe.419609
Subject(s) - decoding methods , computer science , convolutional neural network , convolutional code , orthogonal frequency division multiplexing , fast fourier transform , artificial neural network , optical communication , fourier transform , algorithm , qam , limit (mathematics) , nonlinear system , quadrature amplitude modulation , artificial intelligence , optics , telecommunications , bit error rate , channel (broadcasting) , mathematics , physics , mathematical analysis , quantum mechanics
Nonlinear Fourier transform, as a technique that has a great potential to overcome the capacity limit in fibre optical communication system, faces speed and accuracy bottlenecks in practice. Machine learning using convolutional neural networks shows great potential in NFT-based applications. We have developed a convolutional neural network for decoding information in NFT-based communication and numerically demonstrated its performance in comparison to a fast NFT algorithm. The comparison indicates the potential of conventional neural network to replace NFT calculations for decoding of information.