Neural network application in automatic recognition of communication signals

Automatic recognition of modulated signals has seen increasing demand nowadays. The use of artificial neural networks (NNs) for the purpose has been popular since the late 90's. This paper proposes radial basis functions (RBF) to perform the recognition of eight kinds of modulated signals. Design considerations for the NN recognition are discussed. Computer simulation results show that the overall success rate is over 93% at the signal-to-noise ratio (SNR) of 6 dB, and the overall success rate is over 96% at the SNR of 10 dB.