Research on Signal Modulation Recognition Method Based on Deep Belief Network

Abstract

In order to solve the problem that high-order signal features need to be extracted manually and the recognition accuracy is not high in the process of signal modulation recognition, this paper applies the depth confidence network to the modulation recognition and studies the method of signal modulation recognition based on the Deep Belief Networks (DBN). In this paper, Restricted Boltzmann Machine (RBM) is used to build the network model of DBN, and then the simulation module of the data set needed by DBN is introduced. The DBN is trained by generating signal data, and the recognition of signal is realized. Simulation results show that the recognition accuracy of the method is higher than that of other machine learning algorithm.