基于RBF神经网络的弱信号检测

Signal Detection in Low SNR Based on RBF Neural Network

介绍了一种基于RBF(Radial Basis Function)神经网络的弱信号检测方法,该方法提高了低信嗓比情况下的信号检测正确率。该方法计算不同信噪比情况下多通道接收数据的协方差矩阵,然后将计算得到的协方差矩阵特征值作为训练样本对RBF神经网络进行训练得到检测模型,最后利用该检测模型进行弱信号检测。MATLAB仿真实验表明,提出的基于RBF神经网络的弱信号检测方法具有良好的适应性,对比MMED(Maximum-minimum Eigenvalues Based Detection)和AED(Average Eigenvalue Detec-tion)算法能够有效提升低信噪比情况下的信号检测正确率。

A method of signal detection in low SNR based on RBF neural network is introduced.The accuracy of signal detection is improved in low SNR by RBF neural network.This method calculates the covariance matrix of multi-channel received signal under different SNR conditions.Then use the calculated covariance matrix eigenvalues as training samples to train the PJBF neural network to obtain a detection model.Finally,the detection model is used for signal detection in low SNR.MATLAB simulation experiments show that the signal detection method based on RBF neural network proposed in this paper has good adaptability.Compared with the MMED and the AED methods,RBF neural network method can effectively improve the accuracy of signal detection in low SNR.