基于改进RBFN的信号调制识别方法  

Modulation Recognition Using Improved RBF Nerual Networks

作　　者：贺涛[1] 周正欧[1] 

机构地区：[1]电子科技大学电子工程学院,四川成都610054

出　　处：《信号处理》2006年第4期515-518,共4页Journal of Signal Processing

摘　　要：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。A new efficient method based on statistical pattern recognition theory to recognition digital modulation types of communication 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.

关 键 词：调制识别 高阶统计量 径向基函数神经网络 误差函数 

分 类 号：TN911.3[电子电信—通信与信息系统] TP183[电子电信—信息与通信工程]