Automatic Modulation Recognition of Communication Signals.

Sammanfattning: The project is aimed at designing an intelligent communication system where the receiver is able to detect the modulation scheme of the signal it receives using Automatic Modulation Recognition (AMR) algorithms, without having minimum or no prior knowledge of the transmitted signal. Six digital modulation schemes namely QPSK, BPSK, 2ASK, 4ASK, 2FSK, 4FSK and 16QAM were used. Algorithms based on deriving key statistical features from the communication signal, were formed. Features were also extracted using Azzouz and Nandi‟s techniques. Neural Networks were applied to the extracted features to distinguish between signals having different modulation schemes. The simulations were performed for different SNR values as well as different number of neurons in a one and two hidden layers.