Modulation classification of communication signals

In this paper we develop a novel algorithm using wavelet transform and pattern recognition to identify the modulation types of the communication signals automatically. Wavelet transform is used to estimate the symbol rate of the received signals in order to discriminate analogue signals from digital ones. Then the key features are extracted to identify the specific modulation type by threshold method. Computer simulation results demonstrate that the performance of the algorithm is efficient at the SNR ≤ 15 dB.