Modulation Recognition Algorithms for Communication Signals Based on Particle Swarm Optimization and Support Vector Machines

To solve the problems of most communication signals modulation recognition methods´ computational complexity and classifier training difficulties, a method of modulation recognition is proposed based on particle swarm optimization(PSO) and support vector machine (SVM). Combine wavelet decomposition theory with the modulated signals´ instantaneous characteristics, high-order cumulants and fractal theory to obtain a hybrid model of feature vector, and use PSO-SVM classifier to identify ten kinds of modulation signals as 2ASK, 4ASK, 2PSK, 4PSK, 8PSK, 2FSK, 4FSK, 8FSK, 16QAM, MSK. The simulation results show that the recognition rates are all over 98% at SNR 5dB.