SigNet: A Novel Deep Learning Framework for Radio Signal Classification

Deep learning methods achieve great success in many areas due to their powerful feature extraction capabilities and end-to-end training mechanism, recently they are also introduced for radio signal modulation classification. In this paper, we propose a novel deep framework called SigNet, where signal-to-matrix (S2M) operator is adopted convert the original into square matrix first co-trained with follow-up CNN architecture This model further accelerated by integrating 1D convolution operators, leading upgraded SigNet2.0. The simulations on two datasets show that both SigNet SigNet2.0 outperform number of well-known baselines. More interestingly, our proposed models behave extremely well small-sample when only small dataset provided. They can relatively high accuracy even 1% data kept, while other baseline may lose effectiveness much more quickly as get smaller. Such result suggests SigNet/SigNet2.0 could be useful situations labeled difficult obtain. visualization output features demonstrates divide different types signals hyper-space.