A new scheme of automatic modulation classification using wavelet and WSVM

This paper deals with automatic modulation classification of communication signals. A new scheme of automatic modulation classification using wavelet analysis and wavelet support vector machine (WSVM) is proposed. Further, a new way of training for wavelet features is carried out to adapt to signals which are non-stable and varied in a wide range of signal-to-noise rates (SNR). Through such training, a single classifier can classify modulation types with high accuracy without knowing signals´ SNR if only the SNR is in a certain range. Computer simulation shows that the classifier can separate ten modulation types, i.e. 2ASK, 4ASK, 2FSK, 4FSK, 2PSK, 4PSK, 16QAM, TFM, pi/4QPSK, OQPSK and success rates are over 96.5% when SNR is not lower than 3 dB. Accuracy and efficiency of the proposed scheme are obviously improved