Dimensionality Reduction and Improving the Performance of Automatic Modulation Classification using Genetic Programming

This paper shows how we can make advantage of using genetic programming in selection of suitable features for automatic modulation recognition. Automatic modulation recognition is one of theessential components of modern receivers. In this regard, selection of suitable features maysignificantly affect the performance of the process. Simulations were conducted with 5db and 10db SNRs. Test and training data released from real ones were recorded in an actual communication system. For performance analyzing of the proposed method, a set of experiments were conductedconsidering signals with 2PSK, 4PSK, 2FSK, 4FSK, 16QAM and 64 QAM modulations. The results show that the selected features by the model improve the performance of automatic modulation recognition substantially. During our experiments, we also reached the suitable values and forms for mutation and crossover ratio, fitness function as well as other parameters for the proposed model

Keywords:

Modulation Automatic Detection , Genetic Programming , Entropy , Multi-layer Neural Network Perceptron , Decision Tree