Modulation recognition of symbol shaped digital signals

A new recognition algorithm to the symbol shaped signals is presented, in which eight digital modulation types are classified. The infection to signals and parameterspsila extraction aroused by symbol shape is introduced in detailed, and the modulation types are classified from the decision-tree classifier. The computer simulation results show that, the algorithm has a good recognition performance for the shaped signals, further more it has a better recognition performance than the methods without consideration of the symbol shape.