2D-FFT Based Modulation Classification Using Deep Convolution Neural Network

TLDR: In this paper, a convolution neural network (CNN) based automatic modulation classification (AMC) method is proposed, where two dimensional Fast Fourier Transform (2D-FFT) is used as a classification feature and a less complex and efficient deep CNN model is designed to classify the modulation schemes of different orders of PSK and QAM.

Abstract: Automatic modulation classification (AMC) has a wide range of applications in the military and civilian areas In the military, it is used for the extraction of information from unknown intercepted signals and the generation of jamming signals Civil applications include interference management and spectrum underutilization To overcome the limitations of traditional methods like maximum likelihood (ML) and feature- based (FB), deep learning (DL) networks have been developed and are being evolved Following this direction, a convolution neural network (CNN) based AMC method is proposed The two dimensional Fast Fourier Transform (2D-FFT) is used as a classification feature and a less complex and efficient deep CNN model is designed to classify the modulation schemes of different orders of PSK and QAM The developed method achieves adequate classification performance for considered five modulation schemes in the AWGN channel