Modulation Recognition Based on Instantaneous Feature Fusion
Jiaqi Xu, Xuehong Sun, Liping Liu, Yihang Li, Yaxing Wang, Tingting Zhang · 2023
With the rapid development of 5G technology, many innovative technologies and various standards have emerged in the field of wireless communication. Modulation Recognition (MR) is one of the important technologies in communication system, whose main purpose is to recognize the modulation mode of the received signal to overcome the influence of noise interference. In order to solve the problem of modulation recognition accuracy under low signal-to-noise ratio, an instantaneous feature fusion algorithm based on deep learning framework is proposed. This method uses the different characteristics of the instantaneous characteristic values of each modulation signal and the complementary information between the different instantaneous characteristics to carry out modulation recognition. When SNR=0dB, the recognition accuracy can reach 88% when adding two eigenvalues, while the recognition accuracy is 86% when no eigenvalues are added. On the other hand with the increase of the number of added eigenvalues, the modulation recognition accuracy is improved.