Interclass and Intraclass Modulation Recognition using the Wavelet Transform

This paper presents an algorithm for modulation recognition of received signals in the presence of additive white Gaussian noise (AWGN) with the use of the wavelet transform. The decision is made based on the extraction of some special features of the continuous wavelet transform of the received signal. The Haar wavelet was used as the mother wavelet. Besides the SNR, the algorithm needs no further information for the received signal such as signal bandwidth or carrier frequency. It is able to classify PSK, QAM, FSK and ASK signals, as well as to identify the modulation order. Effort was made in order to reduce the computational workload, so that the algorithm can be suitable for real-time recognition. After extended simulation the algorithm proved to be practically inerrable for SNR>12 dB and achieves low rates of false detection for SNR=10 dB.