Automatic modulation classification using hybrid features: Performance Comparison

Automatic Modulation Classification (AMC) is the technique for classifying the modulation scheme of an intercepted and possibly noisy signal whose modulation scheme is unknown. Automatic modulation classification of the digital modulation type of a signal has been taking much interest in the communication areas. This is due to the advances in reconfigurable signal processing systems, especially for the application of software radio system. Ten Digitally modulated signals are considered. Channel conditions have been modeled by simulating AWGN and multipath Rayleigh fading effect. Seven key features have been used to develop the classifier. Higher order QAM signals such as 16QAM, 64QAM and 256 QAM are classified using higher order statistical parameters such as moments and cumulants. Feature based Decision tree and ANN classifier have been developed and their performances are compared under varying channel conditions for SNR as low as -5dB.