基于改进RBFN的信号调制识别方法

应用高阶统计量和RBF神经网络原理,针对数字调制通信信号提出了一种基于统计模式识别理论的信号调制类型识别新方法。采用信号四阶和六阶统计量提取信号特征,使用新设计的误差函数训练RBF神经网络,使得识别的效率和正确度得到了明显的改善。计算机仿真结果证明了此方法的可行性。

Modulation Recognition Using Improved RBF Nerual Networks

A new efficient method based on statistical pattern recognition theory to recognition digital modulation types of commu- nication signals is proposed.The forth-order and sixth-order cumulants of received signal are adopted for features extraction while RBF neural networks with a new designed training cost function being used for classifier.The result of computer simulation has proved this method can improve the accuracy and efficiency of recognition obviously.