Fast signal modulation recognition based on feature vector and weighted majority decision

Aiming at reaching high precision and speed in automatic modulation recognition under largely fluctuated SNR software radio environment, a classification recognition structure with training reference was represented, by constructing an effective three-dimensional feature vector and the weighted majority decision classifier, to classify BPSK, QPSK, FSK, PM, MSK signals. Simulation results validated the feasibility and effectiveness of this method.