Automatic modulation recognition using wavelet transform and neural network

Modulation type is one of the most important characteristics used in signal waveform identification. An algorithm for automatic modulation recognition has been developed and presented in this study. The suggested algorithm is verified using higher order statistical moments of wavelet transform as a features set. A multi-layer neural network with resilient backpropagation learning algorithm is proposed as a classifier. The purpose is to discriminate different M-ary shift keying modulation types and modulation order without any priori signal information. Pre-processing and features subset selection using principal component analysis will reduce the network complexity and increase the recognizer performance.