Automatic modulation recognition based on mixed-type features

The existing modulation classification method using instantaneous features is poor for low SNRs, and the high-order cumulant features-based modulation recognition algorithm is only applicable to some types of communication modulation signals. To overcome these problems, we propose a mixed features-based modulation recognition algorithm, which refines instantaneous features and high-order cumulant feature, and the back propagation (BP) neural network is adopted as a classifier to perform experiments. The experimental results show that our proposed mixed features-based modulation recognition method can improve the recognition rate for more kinds of signals.