No abstract

Signal modulation recognition is widely utilized in the field of spectrum detection, channel estimation, and interference recognition. With the development of artificial intelligence, substantial advances in signal recognition utilizing deep learning approaches have been achieved. However, a huge amount of data is required for deep learning. With increasing focus on privacy and security, barriers between data sources are sometimes difficult to break. This limits the data and renders them weak, so that deep learning is not sufficient. Federated learning can be a viable way of solving this challenge. In this article, we will examine the recognition of signal modulation based on federated learning with differential privacy, and the results show that the recognition rate is acceptable while data protection and security are being met.

No abstract