Automatic modulation recognition using wavelet transform and neural networks in wireless systems
EURASIP Journal on Advances in Signal Processing
Hi-index | 0.00 |
In this paper, some methods allowing automatic discrimination between the types of modulations proposed by the DPRS communication standard are presented. In a non-cooperative context, the receiver must first be able to detect the presence of a modulated signal before eventually carrying out its demodulation (i.e. having access to the information). For this purpose a receiver capable of identifying digital modulations of type M-QAM, 8-PSK and GMSK, proposed by the ETSI---DPRS standard, has been studied. Three detection algorithms have been investigated. The first is based on the observation of the amplitude histograms, the second on the continuous wavelet transform and the third on the maximum likelihood for the joint probability densities of phases and amplitudes. Their performance has been evaluated against signal to noise ratio.