陈嘉润, 余宝贤, 王剑莹, 张涵. 基于深度神经网络的高频谱效率频分复用系统的信道估计方法[J]. 华南师范大学学报(自然科学版), 2020, 52(3): 17-21. doi: 10.6054/j.jscnun.2020038
引用本文: 陈嘉润, 余宝贤, 王剑莹, 张涵. 基于深度神经网络的高频谱效率频分复用系统的信道估计方法[J]. 华南师范大学学报(自然科学版), 2020, 52(3): 17-21. doi: 10.6054/j.jscnun.2020038
CHEN Jiarun, YU Baoxian, WANG Jianying, ZHANG Han. A DNN-Based Channel Estimation Method for Spectral Efficient Frequency Division Multiplexing Systems[J]. Journal of South China Normal University (Natural Science Edition), 2020, 52(3): 17-21. doi: 10.6054/j.jscnun.2020038
Citation: CHEN Jiarun, YU Baoxian, WANG Jianying, ZHANG Han. A DNN-Based Channel Estimation Method for Spectral Efficient Frequency Division Multiplexing Systems[J]. Journal of South China Normal University (Natural Science Edition), 2020, 52(3): 17-21. doi: 10.6054/j.jscnun.2020038

基于深度神经网络的高频谱效率频分复用系统的信道估计方法

A DNN-Based Channel Estimation Method for Spectral Efficient Frequency Division Multiplexing Systems

  • 摘要: 针对高频谱效率频分复用(SEFDM)系统, 提出了一种基于深度神经网络(DNN)的信道估计方法.该方法使用等间隔相互正交的导频符号, 将其接收信号作为DNN的输入信号, 通过4层的全连接DNN结构提取信道特征, 最终实现了时域上的信道估计.仿真结果表明:提出的信道估计方法在同等条件下的均方误差(MSE)明显比最小二乘法(LS)的低, 对应的解调性能也更优, 且对导频数量具有更强的鲁棒性, 由此反映出该方法的优越性.

     

    Abstract: A channel estimation method based on deep neural network (DNN) for spectral efficient frequency division multiplexing (SEFDM) systems is proposed. The method employs uniform spaced orthogonal pilot symbols to achieve the channel estimation. To be specific, the received pilot signals are used as the input of the four-layer DNN in order to extract the channel features. Simulation results show that the proposed scheme can yield a smaller mean square error (MSE) and, in turn, perform better demodulation in comparison with the conventional least square (LS) method. In particular, the DNN-based method is more robust to the number of pilots, which indicates its superiority.

     

/

返回文章
返回