基于参量直方分布的数字信号调制识别

提出了基于参量立方分布的数字调制信号的神经网络识别方法，在提取信号瞬时幅度、瞬时相位、瞬时频率参量的基础上，将其立方分布作为数字通信信号调制方式识别的特征，用于神经网络的训练与识别。仿真结果说明，这种方法保留了原始信息的明显特征，对数字调制信号识别率高，且具有逻辑关系简单、便于进行实时处理、易于实现等优点。

Modulation Recognition of Digital Signals Based on Parameters Histogram Distribution

An artificial neural networks(ANNs) approach for modulation type recognition for digital modulation signals based on the parameters histogram distribution is presented in this paper.ANNs are used to recognize digital modulation signals based on the parameters histogram distribution of the instantaneous envelope, instantaneous phase and instantaneous frequency, which is suitable for digital modulation types including ASK2, ASK4, PSK2, PSK4, FSK2, FSK4. The simulation results show that our approach is able to extract the key feature of the signals, and is featured by high success recognition rate,simple logic framework,easy to real-time realization.