STF-GCN: A Multi-Domain Graph Convolution Network Method for Automatic Modulation Recognition via Adaptive Correlation
Official Code for "STF-GCN: A Multi-Domain Graph Convolution Network Method for Automatic Modulation Recognition via Adaptive Correlation". [paper]
If our work is helpful to your research, please star us on github and cite :
@ARTICLE{STF-GCN, author={Shao, Mingyuan and Fu, Zhengqiu and Li, Dingzhao and Zhang, Fuqing and Cai, Yilin and Hong, Shaohua and Cao, Lin and Peng, Yuan and Qi, Jie}, journal={IEEE Transactions on Cognitive Communications and Networking}, title={STF-GCN: A Multi-Domain Graph Convolution Network Method for Automatic Modulation Recognition via Adaptive Correlation}, year={2025}, volume={}, number={}, pages={1-1},
##Link https://pan.quark.cn/s/fe24884dd6fd#/list/share We have placed all three datasets with 1. model architecture, 2. Tensorboard file of thetraining process, 3. confusion matrix and accuracy of each Epoch in training, 4. training parameter weights, 5. test set pkl file and 6. test results
The complete training process will be organized later...