典型文献
Symbol Detection Based on Temporal Convolutional Network in Optical Communications
文献摘要：
Deep learning (DL) is one of the fastest developing areas in artificial intelligence,it has been recently gained studies and application in computer vi-sion,automatic driving,automatic speech recognition,and communication.This paper uses the DL method to design a symbol detection algorithm in receiver for optical communication systems.The proposed DL based method is implemented by a non-causal tempo-ral convolutional network (ncTCN),which is a convo-lutional neural network and appropriate for sequence processing.Meanwhile,we adopt three methods to re-alize the training process for multiple signal-to-noise ratios of the AWGN channel.Furthermore,we apply two nonlinear activation functions for the noise robust-ness to the proposed ncTCN.Without losing general-ity,we apply the ncTCN-based receiver to the 16-ary quadrature amplitude modulation optical communica-tion system in the simulation experiment.According to the experiment results,the proposed method can ob-tain some bit error rate performance gain compared to some conventional receivers.
文献关键词：
中图分类号：
作者姓名：
Yingzhe Luo;Jianhao Hu
作者机构：
Key Laboratory of Science and Technology on Communication,University of Electronic and Science Technology of China,Chengdu 611731,China
文献出处：
引用格式：
[1]Yingzhe Luo;Jianhao Hu-.Symbol Detection Based on Temporal Convolutional Network in Optical Communications)[J].中国通信（英文版）,2022(01):284-292
A类：
ncTCN,alize
B类：
Symbol,Detection,Based,Temporal,Convolutional,Network,Optical,Communications,Deep,learning,DL,one,fastest,developing,areas,artificial,intelligence,has,been,recently,gained,studies,application,computer,sion,automatic,driving,speech,recognition,communication,This,paper,uses,design,symbol,detection,algorithm,optical,systems,proposed,implemented,by,causal,tempo,convolutional,network,which,neural,appropriate,sequence,processing,Meanwhile,we,adopt,three,methods,training,multiple,signal,noise,ratios,AWGN,channel,Furthermore,apply,nonlinear,activation,functions,robust,ness,Without,losing,general,ity,ary,quadrature,amplitude,modulation,simulation,experiment,According,results,can,tain,some,bit,error,rate,performance,compared,conventional,receivers
AB值：
0.603137
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
