Channel Discrepancies Adaptive Modulation Recognition Using Domain Adversarial Training
- Resource Type
- Conference
- Authors
- Li, Yaxing; Wu, Hao; Kang, Ying; Guo, Yu; Cui, Zhongpu; Xing, Jinling; Wang, Qing; Meng, Jin
- Source
- 2021 Asia-Pacific International Symposium on Electromagnetic Compatibility (APEMC) Electromagnetic Compatibility (APEMC), 2021 Asia-Pacific International Symposium on. :1-4 Sep, 2021
- Subject
- Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Engineered Materials, Dielectrics and Plasmas
Fields, Waves and Electromagnetics
General Topics for Engineers
Power, Energy and Industry Applications
Signal Processing and Analysis
Transportation
Training
Wireless communication
Adaptation models
Adaptive systems
Neural networks
Modulation
Feature extraction
automatic modulation recognition
channel discrepancies
domain adversarial training
convolutional neural network
- Language
- ISSN
- 2640-7469
In this paper, we introduce a channel discrepancies adaptive automatic modulation recognition (AMR) method, which employs the domain adversarial training (DAT) to tackle the issue of wireless channel mismatch between training and testing conditions. The channel mismatch is a critical problem for deep learning (DL) based AMR systems. In realistic scenarios, the channel environment mismatch commonly happens and a large mismatch may seriously degrade the recognition accuracy of signals. The introduced channel discrepancies adaptive AMR method consists of a l-dimensional convolutional neural network (1-D CNN) based recognition model and a domain discriminator model. The DAT encourages the 1-D CNN to extract channel invariant features and increase the robustness of the AMR system to new channel environment. We evaluate the proposed method and competition approaches on the popular RadioML2016. 04c and RadioML2016.10a dataset. Experimental results shows that the introduced channel discrepancies adaptive AMR system produce notable better recognition performance than that of the methods without domain adaptation for the channel discrepancies of training and testing datasets.