Continued Electromagnetic Signal Classification Based on Vector Space Separation

Incremental electromagnetic signal classification is crucial in realistic wireless environments where new signal types continuously emerge and historical training data are often unavailable. This paper proposes a model-based incremental learning method driven by vector space separation to mitigate catastrophic forgetting without accessing old-task samples or requiring semantic information. We show that forgetting is largely caused by insufficient separation between old and new classes in the classifier weight space. To address this issue, we jointly introduce weight normalization, a cosine-similarity separation loss, and regularization, together with cross-entropy supervision for new classes. Based on these designs, we propose an incremental learning method based on vector space separation for electromagnetic signal classification, enabling the model to continually recognize modulation signals without requiring semantic information or access to raw data from previous tasks during incremental updates. Experiments on two simulated modulation datasets under multiple task sequences demonstrate that the proposed method consistently alleviates catastrophic forgetting and achieves stable incremental performance, outperforming baselines while avoiding data rehearsal.