{"ID":2840133,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.14640","arxiv_id":"2511.14640","title":"Doppler Invariant CNN for Signal Classification","abstract":"Radio spectrum monitoring in contested environments motivates the need for reliable automatic signal classification technology. Prior work highlights deep learning as a promising approach, but existing models depend on brute-force Doppler augmentation to achieve real-world generalization, which undermines both training efficiency and interpretability. In this paper, we propose a convolutional neural network (CNN) architecture with complex-valued layers that exploits convolutional shift equivariance in the frequency domain. To establish provable frequency bin shift invariance, we use adaptive polyphase sampling (APS) as pooling layers followed by a global average pooling layer at the end of the network. Using a synthetic dataset of common interference signals, experimental results demonstrate that unlike a vanilla CNN, our model maintains consistent classification accuracy with and without random Doppler shifts despite being trained on no Doppler-shifted examples. Overall, our method establishes an invariance-driven framework for signal classification that offers provable robustness against real-world effects.","short_abstract":"Radio spectrum monitoring in contested environments motivates the need for reliable automatic signal classification technology. Prior work highlights deep learning as a promising approach, but existing models depend on brute-force Doppler augmentation to achieve real-world generalization, which undermines both training...","url_abs":"https://arxiv.org/abs/2511.14640","url_pdf":"https://arxiv.org/pdf/2511.14640v1","authors":"[\"Avi Bagchi\",\"Dwight Hutchenson\"]","published":"2025-11-18T16:31:13Z","proceeding":"eess.SP","tasks":"[\"eess.SP\",\"cs.LG\"]","methods":"[\"Convolutional Neural Network\"]","has_code":false}