基于ROLS的径向基函数神经网络实现数字调制自动识别

Automatic Digital Modulation Recognition Based on ROLS Radial Basis Function Neural Network

针对径向基函数(RBF)神经网络和统计模式识别的特点,提出利用递归正交最小二乘法(ROLS)的RBF神经网络实现数字信号调制样式的自动识别。仿真结果表明,利用ROLS算法很好地实现了RBF神经网络权值的确定和中心的选择,从而大大减少了网络的训练样本数和训练时间,提高了网络的识别性能。

Based on the radial basis function （RBF） and the algorithm of statistical pattern recognition modulation recognition, this paper puts forward an algorithm based on Recursive Orthogonal Least Squares for automatic （ROLS） RBF neural network for the recognition of different digital modulated signals. The simulation results demonstrate that the ROLS algorithm is used not only for calculating the weights of the network, but also for choosing RBF neural networks centers sequentially according to minimizing the output error, and improve the recognition ability of the neural network with significant reduction in the number of required centers without retraining.