Digital Modulation Classification through time and frequency domain features using Neural Networks

Abstract

Cognitive Radio (CR) networks has been presented in the last decade as a solution to the problem of increasing congestion in frequency spectrum, through opportunistic spectrum access techniques. One of the main components of Cognitive Radio receivers is the Automatic Modulation Classification (AMC), in which the CR can blindly identify the modulation scheme of a detected signal. AMC has several applications, including military, spectrum surveillance and management, and commercial applications. In this paper we propose an AMC based on two different Neural Networks (NN) classifiers: Feed-Forward with Resilient Back-Propagation NN and Probabilistic NN. NN classifiers take their inputs as a feature vector from a Features extraction phase. Features selected for classification are the statistical features of the received signal's instantaneous amplitude, frequency and phase. Simulations show that both NN classifiers can achieve over 80% correct classification up to Signal-to-Noise Ratio (SNR) of 5 dB, and the probability of correct classification increases up to 99% at a SNR of 15 dB.