AMC-Net: An Effective Network for Automatic Modulation Classification
This work addresses a specific limitation in wireless communication systems for improved signal monitoring and decoding, but it appears incremental as it builds on existing deep learning approaches for AMC.
The paper tackles the problem of automatic modulation classification in low SNR environments by proposing AMC-Net, which improves recognition through frequency-domain denoising and multi-scale feature extraction, achieving better efficiency and effectiveness than current methods on two datasets.
Automatic modulation classification (AMC) is a crucial stage in the spectrum management, signal monitoring, and control of wireless communication systems. The accurate classification of the modulation format plays a vital role in the subsequent decoding of the transmitted data. End-to-end deep learning methods have been recently applied to AMC, outperforming traditional feature engineering techniques. However, AMC still has limitations in low signal-to-noise ratio (SNR) environments. To address the drawback, we propose a novel AMC-Net that improves recognition by denoising the input signal in the frequency domain while performing multi-scale and effective feature extraction. Experiments on two representative datasets demonstrate that our model performs better in efficiency and effectiveness than the most current methods.