Edge-Efficient Transformer for End-to-End RF Spectrum Monitoring

E-SpecFormer is introduced for end-to-end automatic modulation and covert channel recognition. It features LiTAN, a Softmax- and LayerNorm-free attention mechanism that lowers complexity and improves accuracy in RF tasks. Available in Nano, Small, Medium, and Large variants for various hardware constraints, the Nano version achieves 86.5% average accuracy for SNRs>0 dB using the RadioML2018 dataset. Additionally, it reaches 94.2% accuracy on the hardware Trojan-based CC dataset, optimizing edge-efficient RF spectrum monitoring performance.