利用指数范数的QAM信号调制识别方法

针对高阶正交幅度调制（QAM）类信号的调制识别问题，提出了一种利用指数范数的调制识别分类方法，实现了由5种QAM类信号所组成信号集的调制识别。首先，对信号集内待识别信号提取指数范数特征，依次将16QAM和32QAM信号从信号集内识别出来；然后，对信号集内剩余信号提取高斯指数范数特征，依次识别64QAM、128QAM和256QAM信号；最后，根据决策树原理设计分类器，实现信号集内5种QAM类信号的识别。仿真结果表明，在信噪比大于6 dB时，该方法对信号集内的信号的识别正确率超过96%。

A recognition algorithm of QAM signals based on exponent norm

For the issue of Quadrature Amplitude Modulation (QAM) signals modulation recognition, an algorithm of modulation recognition classification based on exponent norm is put forward. Firstly, 16QAM and 32QAM signals are recognized by using the exponent norm characteristic extracted from the unidentified signals. Then, the Gaussian exponent norm is extracted from remained signals in order to recognize 64QAM,128QAM and 256QAM signals. Finally, a classifier based on the decision tree method is proposed to realize recognition of the five kinds of QAM signals in the signal set. Simulation shows with the proposed algorithm the recognition accuracy rate is over 96% when signal-to-noise ratio (SNR) is more than 6 dB.