Fully Dense Neural Network for the Automatic Modulation Recognition
This addresses the problem of inefficient preprocessing and high memory consumption in radio signal recognition for intelligent radio systems, though it appears incremental as it builds on existing CNN and attention mechanisms.
The paper tackles automatic modulation recognition by proposing a Fully Dense Neural Network (FDNN) that directly processes raw IQ data, eliminating the need for spectrogram preprocessing. On the RML2016.10a dataset, FDNN achieves higher recognition rates with lower model complexity and parameters compared to existing methods.
Nowadays, we mainly use various convolution neural network (CNN) structures to extract features from radio data or spectrogram in AMR. Based on expert experience and spectrograms, they not only increase the difficulty of preprocessing, but also consume a lot of memory. In order to directly use in-phase and quadrature (IQ) data obtained by the receiver and enhance the efficiency of network extraction features to improve the recognition rate of modulation mode, this paper proposes a new network structure called Fully Dense Neural Network (FDNN). This network uses residual blocks to extract features, dense connect to reduce model size, and adds attentions mechanism to recalibrate. Experiments on RML2016.10a show that this network has a higher recognition rate and lower model complexity. And it shows that the FDNN model with dense connections can not only extract features effectively but also greatly reduce model parameters, which also provides a significant contribution for the application of deep learning to the intelligent radio system.