典型文献
Deep Learning-Based AMP for Massive MIMO Detection
文献摘要：
Low-complexity detectors play an es-sential role in massive multiple-input multiple-output(MIMO)transmissions.In this work,we discuss the perspectives of utilizing approximate message passing(AMP)algorithm to the detection of massive MIMO transmission.To this end,we need to efficiently re-duce the divergence occurrence in AMP iterations and bridge the performance gap that AMP has from the optimum detector while making use of its advantage of low computational load.Our solution is to build a neural network to learn and optimize AMP detec-tion with four groups of specifically designed learn-able coefficients such that divergence rate and detec-tion mean squared error(MSE)can be significantly reduced.Moreover,the proposed deep learning-based AMP has a much faster converging rate,and thus a much lower computational complexity than conven-tional AMP,providing an alternative solution for the massive MIMO detection.Extensive simulation ex-periments are provided to validate the advantages of the proposed deep learning-based AMP.
文献关键词：
中图分类号：
作者姓名：
Yang Yang;Shaoping Chen;Xiqi Gao
作者机构：
Hubei Key Laboratory of Intelligent Wireless Communications,South-Central Minzu University,Wuhan 430074,China;National Mobile Communications Research Laboratory,Southeast University,Nanjing 210096,China
文献出处：
引用格式：
[1]Yang Yang;Shaoping Chen;Xiqi Gao-.Deep Learning-Based AMP for Massive MIMO Detection)[J].中国通信（英文版）,2022(10):69-77
A类：
B类：
Deep,Learning,Based,AMP,Massive,MIMO,Detection,Low,complexity,detectors,play,sential,role,massive,multiple,input,output,transmissions,In,this,discuss,perspectives,utilizing,approximate,message,passing,algorithm,detection,To,end,need,efficiently,divergence,occurrence,iterations,bridge,performance,gap,that,has,from,optimum,while,making,use,its,computational,load,Our,solution,build,neural,network,optimize,four,groups,specifically,designed,able,coefficients,such,rate,mean,squared,error,MSE,be,significantly,reduced,Moreover,proposed,deep,learning,much,faster,converging,thus,lower,than,conven,providing,alternative,Extensive,simulation,periments,provided,validate,advantages
AB值：
0.587436
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。
