Survey of Research on Application of Deep Learning in Modulation Recognition

Modulation recognition is an important research branch in the field of communication, which is widely used in civil and military fields. The classic methods depend on decision theory, signal feature and the choice of classifier, while the deep learning network can get the signal feature directly from the data, and its recognition accuracy is higher than the classic methods. This paper summarized the application of deep learning in modulation recognition. Firstly, the basic concept of deep learning and the common network structure in modulation recognition were introduced. Secondly, the common signal forms and signal preprocessing technologies of input deep learning network were given, and the characteristics and performance of different deep learning networks were summarized and analyzed. Finally, the challenges and future research directions in this field were discussed.