To deal with the insufficient recognition accuracy of traditional signal modulation recognition methods, this paper proposes a new communication signal modulation recognition method with a deep neural network that integrates a multi-feature multi-channel ResNet and BiLSTM neural network (MF-MC ResNet-BiLSTM). By converting the original modulation data into three different vector formats, which are IQ format, AP format, and FFT format, we obtained the model inputs which contain various feature information. After inputting three types of vector signals into the multi-channel feature fusion module, the network converts these input signals into a high-dimensional feature space for feature fusion, and extracts features we need from different signal sources. Meanwhile, we designed a multi-channel model that integrates ResNet-BiLSTM to perform feature fusion, extracting key features of the modulation signal to avoid the degradation of orthogonality caused by parameter imbalance. To further enhance modulation recognition performance, an adaptive multi-head attention network was designed to extract features through weighted integration. Simulation results demonstrate that this method exhibits model generalization capabilities and good robustness. Experimental data validate that the method achieves a recognition rate of 95.67% and a recall rate of 94.56% in low signal-to-noise ratio (SNR) environments (−22 dB–2 dB), significantly outperforming existing networks like MMF(multimodal fusion), FGDNN(fusion GRU deep learning neural network), and LightMFFS(redlightweight multi-feature fusion structure).
Li et al. (Wed,) studied this question.