Transmitting antenna number estimation method based on convolutional neural network

The invention discloses a transmitting antenna number estimation method based on a convolutional neural network. The method comprises the following steps: establishing a receiving signal model of a non-cooperative MIMO system; preprocessing the characteristic value of the received signal covariance matrix according to a random matrix theory to obtain a preprocessed characteristic value; constructing a data set based on the preprocessed feature values; building a convolutional neural network model, and training the network model by using the constructed data set; and estimating the number of transmitting antennas by using the trained convolutional neural network. The transmitting antenna number estimation method provided by the invention adopts a mode based on data driving, does not need to depend on subjective parameter setting, can obtain a more stable and more accurate estimation result, and has good estimation performance. 本发明公开了一种基于卷积神经网络的发射天线数目估计方法，包括以下步骤：建立非合作MIMO系统的接收信号模型；根据随机矩阵理论对接收信号协方差矩阵的特征值进行预处理，得到