Signal Modulation Recognition Method Based on Residual Connection SWT-LSTM

In response to the problem of low signal modulation recognition rate under low signal-to-noise ratio(SNR), this paper proposes a modulation recognition method based on residual connection SWT-LSTM. The algorithm inputs IQ signal data into the network and utilizes the SWT-LSTM network layer to extract signal features and achieve modulation recognition. The connection between SWT and residual can improve the network’s ability to extract useful features and improve recognition rate under low SNR. The simulation results show the excellent performance of the algorithm, and the recognition rate of the proposed recognition model is higher than that of other algorithms.