查看文章

This paper presents a signal modulation classifier design using artificial neural networks. We analyze system-level issues including carrier synchronization, bandwidth estimation, and modulation classification. This is an extension of previous work with the addition of standardfree signal classification as well as an in-depth analysis of the feature space used in the neural network. The results show promising classification statistics with over 80% success rates in the presence of noise even with higher-order digital modulations.