Blind signal-type classification using a novel robust feature subset selection method and neural network classifier

摘要: Automatic modulation recognition plays an important role for many novel computer and communication technologies. Most of the proposed systems can only identify a few kinds digital signal and/or low order them. They usually require high levels signal-to-noise ratio. In this paper, we present hybrid intelligent system that automatically recognizes variety signals. recognizer, multilayer perceptron neural network with resilient back propagation learning algorithm is as classifier. For first time, combination set spectral features higher moments up to eighth cumulants are effective features. Then have optimized classifier design by bees (BA) selection best fed This optimization method new area. Simulation results show technique has very accuracy seven selected BA.