Radio signals modulation mode recognition based on semisupervised deep learning
Xuezhi He, Lin Lin, Jinbao Xie · 2019 IEEE 2nd International Conference on Automation, Electronics and Electrical Engineering (AUTEEE) · 2019
With the rapid development of radio communication technology, the application requirement for recognizing modulation mode of radio communication has also increased, therefore it has become a research focus. This paper proposes a method by combining semi-supervised ideas with the CNN network to realize radio modulation recognition. The basic idea is to design a deep learning model based on convolutional neural networks, which will make full use of a large number of unlabeled radio signals in air as well as the labeled radio signals to train convolutional neural networks. Our experimental results illustrate that the performance of our proposed method in recognizing BPSK, QPSK, 8PSK, 4QAM, 16QAM, and 64QAM modulation modes in various environments is better than MLP and CNN.