Polar Feature Based Deep Architectures for Automatic Modulation Classification Considering Channel Fading
This work addresses AMC for better spectrum utilization in wireless communications, presenting an incremental improvement with specific gains in accuracy and efficiency.
The authors tackled the problem of automatic modulation classification (AMC) for intelligent receivers by proposing a polar-based deep learning architecture with a channel compensation network (CCN), achieving a 5% improvement in recognition accuracy and a 48% reduction in training overhead, along with a 14% accuracy boost under practical channel fading conditions.
To develop intelligent receivers, automatic modulation classification (AMC) plays an important role for better spectrum utilization. The emerging deep learning (DL) technique has received much attention in AMC due to its superior performance in classifying data with deep structure. In this work, a novel polar-based deep learning architecture with channel compensation network (CCN) is proposed. Our test results show that learning features from polar domain (r-theta) can improve recognition accuracy by 5% and reduce training overhead by 48%. Besides, the proposed CCN is also robust to channel fading, such as amplitude and phase offsets, and can improve the recognition accuracy by 14% under practical channel environments.