A Radio Signal Modulation Recognition Algorithm Based on Residual Networks and Attention Mechanisms

To solve the problem of inaccurate recognition of types of communication signal modulation, a RNN neural network recognition algorithm combining residual block network with attention mechanism is proposed. In this method, 10 kinds of communication signals with Gaussian white noise are generated from standard data sets, such as MASK, MPSK, MFSK, OFDM, 16QAM, AM and FM. Based on the original RNN neural network, residual block network is added to solve the problem of gradient disappearance caused by deep network layers. Attention mechanism is added to the network to accelerate the gradient descent. In the experiment, 16QAM, 2FSK and 4FSK are used as actual samples, IQ data frames of signals are used as input, and the RNN neural network combined with residual block network and attention mechanism is trained. The final recognition results show that the average recognition rate of real-time signals is over 93%. The network has high robustness and good use value.

[1]  Li Jingchun,et al.  Mixed Recognition Algorithm for Signal Modulation Schemes by High-order Cumulants and Cyclic Spectrum , 2016 .

[2]  Claudio R. C. M. da Silva,et al.  Maximum-Likelihood Classification of Digital Amplitude-Phase Modulated Signals in Flat Fading Non-Gaussian Channels , 2011, IEEE Transactions on Communications.

[3]  D. S. Chirov,et al.  Type recognition of the digital modulation of radio signals using neural networks , 2015 .

[4]  Haiyan Wang,et al.  Method of modulation recognition based on combination algorithm of K-means clustering and grading training SVM , 2018, China Communications.

[5]  Yahia A. Eldemerdash,et al.  A Robust Modulation Classification Method for PSK Signals Using Random Graphs , 2019, IEEE Transactions on Instrumentation and Measurement.

[6]  Yunfei Chen,et al.  A robust modulation classification method using convolutional neural networks , 2019, EURASIP J. Adv. Signal Process..

[7]  Liu Ming-qia Recognition method of digital modulation signals over non-Gaussian noise in cognitive radio , 2014 .

[8]  Yu-Dong Yao,et al.  Modulation Classification Based on Signal Constellation Diagrams and Deep Learning , 2019, IEEE Transactions on Neural Networks and Learning Systems.

[9]  Khaled Assaleh,et al.  Automatic modulation classification based on high order cumulants and hierarchical polynomial classifiers , 2016, Phys. Commun..

[10]  Chen Fang-chao Recognition algorithm of digital modulation based on wavelet and high-order cumulants , 2011 .

[11]  Dah-Chung Chang,et al.  Cumulants-based modulation classification technique in multipath fading channels , 2015, IET Commun..