通信学报 ›› 2021, Vol. 42 ›› Issue (7): 84-94.doi: 10.11959/j.issn.1000-436x.2021142

• 学术论文 • 上一篇    下一篇

基于一维CNN的多入多出OSTBC信号协作调制识别

安泽亮1, 张天骐1, 马宝泽1, 邓盼1, 徐雨晴2   

  1. 1 重庆邮电大学通信与信息工程学院，重庆 400065
    2 重庆邮电大学计算机科学与技术学院，重庆 400065
  • 修回日期:2021-03-01 出版日期:2021-07-25 发布日期:2021-07-01
  • 作者简介:安泽亮（1993− ），男，安徽蚌埠人，重庆邮电大学博士生，主要研究方向为调制识别、神经网络
    张天骐（1971− ），男，四川眉山人，博士，重庆邮电大学教授、博士生导师，主要研究方向为神经网络、盲信号处理
    马宝泽（1990− ），男，河北廊坊人，重庆邮电大学博士生，主要研究方向为盲源分离改进
    邓盼（1990− ），男，四川宜宾人，重庆邮电大学博士生，主要研究方向为信号与信息处理、图像处理
    徐雨晴（1990− ），女，安徽宿州人，重庆邮电大学博士生，主要研究方向为数据分析、人工智能
  • 基金资助:
    国家自然科学基金资助项目(61671095);国家自然科学基金资助项目(61702065);国家自然科学基金资助项目(61701067)

Cooperative modulation recognition based on one-dimensional convolutional neural network for MIMO-OSTBC signal

Zeliang AN1, Tianqi ZHANG1, Baoze MA1, Pan DENG1, Yuqing XU2   

  1. 1 School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, China
    2 School of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing 400065, China
  • Revised:2021-03-01 Online:2021-07-25 Published:2021-07-01
  • Supported by:
    The National Natural Science Foundation of China(61671095);The National Natural Science Foundation of China(61702065);The National Natural Science Foundation of China(61701067)

在线阅读

38

PDF下载

402

摘要：

为识别多入多出正交空时分组码（MIMO-OSTBC）系统所采用的调制样式，提出了一种基于一维卷积神经网络（1D-CNN）的协作调制识别算法。首先，采用迫零盲均衡来提升不同调制信号间区分度，并选用天然无损的同相正交（I/Q）信号作为浅层特征；然后，设计并训练基于 1D-CNN 的识别模型，从浅层特征中提取深层特征；最后，采用投票决策和置信度决策融合策略，提升多天线接收端协作识别精度。实验结果表明，所提算法能有效识别{BPSK,4PSK,8PSK,16QAM,4PAM}5种调制方式，当信噪比大于或等于-2 dB时，识别精度可达100%。

关键词: 调制识别, 多入多出正交空时分组码, 迫零盲均衡, 一维卷积神经网络, 决策融合

Abstract:

To recognize the modulation style adopted in multiple-input-multiple-output orthogonal space-time block code (MIMO-OSTBC) systems, a cooperative modulation recognition algorithm based on the one-dimensional convolutional neural network (1D-CNN) was proposed.With the lossless I/Q signal selected as shallow features, the zero-forcing blind equalization was first leveraged to improve the discrimination of different modulation signals.Then the 1D-CNN recognition model was devised and trained to extract deep features from shallow ones.Later, two decision fusion strategies of voting-based and confidence-based were leveraged in the multiple-antenna receiver to improve recognition accuracy.Experimental results show that the proposed algorithm can effectively recognize five modulation types {BPSK, 4PSK,8PSK,16QAM,4PAM}, with a 100% recognition accuracy when the signal-to-noise is equal or greater than-2 dB.

Key words: modulation recognition, MIMO-OSTBC, zero-forcing blind equalization, 1D-CNN, decision fusion

中图分类号: 

No Suggested Reading articles found!