Open AccessGaussian kernel-aided deep neural network equalizer utilized in underwater PAM8 visible light communication system
Author(s) -
Nan Chi,
Yiheng Zhao,
Meng Shi,
Xingyu Lu
Publication year - 2018
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.26.026700
Subject(s) - computer science , visible light communication , kernel (algebra) , underwater , artificial neural network , distortion (music) , gaussian , equalizer , transmission (telecommunications) , underwater acoustic communication , artificial intelligence , set (abstract data type) , telecommunications , optics , bandwidth (computing) , mathematics , channel (broadcasting) , physics , amplifier , oceanography , light emitting diode , combinatorics , quantum mechanics , programming language , geology
In this paper, we demonstrate a novel Gaussian kernel-aided deep neural network (GK-DNN) equalizer that can effectively compensate for the high nonlinear distortion of underwater PAM8 visible light communication (VLC) channels. The application of a Gaussian kernel can reduce the necessary training iterations to 47.06%, enabling it to outperform the traditional DNN equalizer. At the same time, a novel design strategy with respect to the structure of the GK-DNN equalizer is proposed, which can effectively save computing resources and reduce the data volume of the necessary training data set. By using the GK-DNN equalizer, a 1.5 Gbps PAM8 VLC system over 1.2-m underwater transmission is successfully demonstrated.