Comparing with the Linear Minimum Mean Square Error (LMMSE) channel estimation method, the method is simple and need not know the channel correlation and signal-to-noise (SNR).
与已有线性最小均方差(LMMSE)信道估计方法相比，该算法简单并且不需要预先知道信道相关矩阵以及信噪比等信道信息。
This method is robust to Gaussian noise and constellation rotation due to initial phase of signal and avoids overfitting and local minimum in neural networks.
这种方法对高斯噪声和星座图由于信号初始相位而引入的旋转具有良好的稳健性，并避免了神经网络中的过学习和局部极小点等缺陷。
应用推荐