Recognition of modulation using Multilayer perceptron in digital communication

Digital modulation classification plays an important role in communication field. In communication field applications, the main objective is the perfect monitoring of the intercepted signals and one of the parameters that affect the perfect monitoring in the modulation type of the intercepted signal. In this paper, a set of key features for identifying different types of digital modulation is developed to use the conventional signal processing methods. Computer simulations for different types of band-limited, digitally modulated signals corrupted by band-limited Gaussian noise have been carried out. Expressions for the instantaneous amplitude, frequency and phase of different types of digitally modulated signals are derived. The classification is conducted with Multilayer perceptron (MLP) neural network with back propagation supervised learning algorithm is utilized to determine class of the received signal; the proposed method can recognize six digital modulation types. In addition, computer simulation results are given at last, which shows good performance of the method.