Modulation Classification Based on Statistical Features and Artificial Neural Network
Anas Alarabi, Osama A. S. Alkishriwo · 2021 IEEE 1st International Maghreb Meeting of the Conference on Sciences and Techniques of Automatic Control and Computer Engineering MI-STA · 2021
Modulation classification has been an interesting topic for many years with many applications in both civil and military fields. In this paper, we propose a feature-based automatic modulation recognition method that is based on the time domain statistical features of the amplitude envelope and the instantaneous phase with an artificial neural network (ANN) classifier. We trained and tested the classifier to classify four different digital modulation schemes: BPSK, QPSK, 16QAM and 64QAM. The classifier performance was compared to one of the feature-based methods in literature and simulation results show that the proposed method performs better especially in lower signal to noise ratios (SNRs). The presented method is also tested with the over-the-air captured signal dataset (RadioML.2018) and gave a maximum of 99% correct classification in high SNRs.