An automatic modulation recognition algorithm based on HHT and SVD

In order to solve the problem of signal classification and recognition in communication reconnaissance, a novel automatic modulation recognition algorithm based on HHT and SVD is presented in this paper. The instantaneous feature parameters of received signal are extracted using HHT. Then, singular values of matrix which is composed of instantaneous parameters are used as characteristic vector and inputted to the generalized regression neural network (GRNN) to recognize the modulation of the signal. The simulation results show that application of this approach enables the system to identify the hiding location and the modulation of common communication signals, such as MASK, MFSK and MPSK, with a higher recognition ratio.