期刊文献+

基于SAMP-Net的MIMO信号检测算法 认领

Signal detection based on SAMP-Net method for MIMO systems
在线阅读 下载PDF
收藏 分享 导出
摘要 文中提出了一种用于多输入多输出(MIMO)检测的模型驱动型深度学习网络。首先,对MIMO系统信号检测问题进行了建模,并且介绍了几种传统检测算法;然后,将简化近似消息传递(SAMP)迭代检测算法与深度学习结合,通过展开原算法得到网络结构,提出了新型模型驱动的深度学习网络SAMP-Net,通过学习得到最优可训练的参数,提高检测性能;最后,将其与最小均方误差(MMSE)算法、Richardson算法、SAMP算法进行检测性能比较。仿真结果表明,SAMP-Net算法可以在瑞利MIMO信道中以较低计算复杂度逼近MMSE算法的检测性能。 A model-driven deep learning network for multiple-input multiple-output(MIMO)detection is proposed.Firstly,the signal detection problem of MIMO system is modeled and several traditional iterative detection algorithms are introduced.Secondly,a new model-driven deep learning network,called the SAMP-Net,is proposed by combining the simplified approximate messaging(SAMP)iterative detection algorithm with deep learning.Finally,the detection performance of SAMP-Net algorithm is compared with that of the minimum mean square error(MMSE)algorithm,Richardson algorithm and SAMP algorithm.Simulation results show that the SAMP-Net algorithm can approach the detection performance of the MMSE algorithm with low computational complexity in Rayleigh MIMO channels.
作者 胡钟秀 王鸿 宋荣方 HU Zhongxiu;WANG Hong;SONG Rongfang(College of Teleconnnunications&Information Engineering,Nanjing University of Posts and Telecommunications,Nanjing 210003,China)
出处 《南京邮电大学学报:自然科学版》 北大核心 2020年第6期36-41,共6页 Journal of Nanjing University of Posts and Telecommunications:Natural Science Edition
基金 江苏省自然科学基金(BK20181392)资助项目。
关键词 深度学习 迭代算法 模型驱动 MIMO检测 deep learning iterative algorithm model-driven MIMO detection
  • 相关文献

参考文献3

二级参考文献24

  • 1SORENSEN L,SKOUBY K E.User scenarios 2020[R].[S.l.:s.n],2009. 被引量:1
  • 23GPP.Physical channels and modulation(Release 11):TS36.211[S].2010. 被引量:1
  • 3MARZETTA T L.Noncooperative cellular wireless with unlimited numbers of base station antennas[J].IEEE Transactions on Wireless Communications,2010,9(11):3590-3600. 被引量:1
  • 4NGO H Q,LARSSON E G,MARZETTA T L.Energy and spectral efficiency of very large multiuser MIMO system[J].IEEE Transactions on Wireless Communications,2013,61(4):1436-1449. 被引量:1
  • 5HEATH RW,LOZANO A,MARZETTA T L,et al.Five disruptive technology directions for 5G[J].IEEE Communications Magazine,2013,52(2):74-80. 被引量:1
  • 6LARSSON E G,TUFVESSON F,EDFORS O,et al.Massive MIMO for next generation wireless systems[J].IEEE Journal of Selected Topics in Signal Processing,2014,8(5):742-758. 被引量:1
  • 7SRINIDHI N,DATTA T,CHOCKALINGAM A,et al.Layered tabu search algorithm for large-MIMO detection and a lower bound on ML performance[J].IEEE Transactions on Wireless Communications,2011,59(11):2955-2963. 被引量:1
  • 8SOM P,DATTA T,SRINIDHI N,et al.Low-complexity detection in large-dimension MIMO-ISI channels using graphical models[J].IEEE Journal of Selected Topics in Signal Processing,2011,5(8):1497-1511. 被引量:1
  • 9STUDER C,B魻LCSKEI H.Soft-input soft-output single tree-search sphere decoding[J].IEEE Transactions on Information Theory,2010,56(10):4827-4842. 被引量:1
  • 10LARSSON E,JALD魪N J.Fixed-complexity soft MIMO detection via partial marginalization[J].IEEE Transactions on Signal Processing,2008,56(8):3397-3407. 被引量:1

共引文献6

维普数据出版直通车
今日学术
投稿分析
职称考试

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部 意见反馈