Abstract
This paper presents an improved algorithm for modulation recognition of received digital signals using continuous wavelet transform (CWT). The Morlet wavelet and optimal scales are used when extract the features. It is able to classify ASK, FSK, PSK and QAM signals, as well as to identify the modulation order. The algorithm needs no prior information for the received signal. The simulation indicated that the success rate of 90% can be achieved when the SNR is not less than 2 dB.