TMRN-GLU: A Transformer-Based Automatic Classification Recognition Network Improved by Gate Linear Unit

Abstract

Automaticmodulation recognition (AMR) has been a long-standing hot topic among scholars, and it has obvious performance advantages over traditional algorithms. However, CNN and RNN, which are commonly used in serial classification tasks, suffer from the problems of not being able to make good use of global information and slow running speed due to serial operations, respectively. In this paper, to solve the above problems, a Transformer-based automatic classification recognition network improved by Gate Linear Unit (TMRN-GLU) is proposed, which combines the advantages of CNN with a high efficiency of parallel operations and RNN with a sufficient extraction of global information of the temporal signal context. Relevant experiments on the RML2016.10b public dataset show that the proposed algorithm not only has a significant advantage in the number of parameters compared with the existing algorithms, but also has improved recognition accuracy under various signal-to-noise ratios.In particular, the accuracy of the proposed algorithm improves significantly compared with other algorithms under low signal-to-noise ratio conditions. The accuracy is improved by at least 9% at low signal-to-noise ratio (6 dB) and about 3% at high signal-to-noise ratio (>2 dB).