Data-Efficient Few-Shot Specific Emitter Identification Using Bi-Interpolative Metric Learning

Specific emitter identification (SEI), a crucial technology at the physical layer of communication protocols, exploits unique radio frequency fingerprints (RFFs) to distinguish between individual emitters. Deep learning (DL) has been widely applied to SEI due to its remarkable capability in uncovering hidden features and distinguishing between different devices. However, DL-based SEI approaches typically require extensive labeled datasets, which are difficult to obtain in real-world scenarios, thus limiting their practical applicability. To address this challenge, we propose a novel few-shot SEI (FS-SEI) method based on bi-interpolative metric learning (Bi-InterML), highly reducing the amount of data needed to adapt the algorithm to a new environment and simultaneously avoiding pretraining. Our approach enhances data quality through wavelet coefficient-based and sequence bi-interpolation, generating enriched data used alongside the original dataset for classification via a complex-valued convolutional neural network (CVCNN). Additionally, interpolative metric learning (IML) is employed to constrain feature distances, enhancing feature discriminability. Experimental results on a real-world Wi-Fi dataset demonstrate the effectiveness of the proposed Bi-InterML-based FS-SEI method, achieving an identification accuracy of 91.48% with 10 samples per category, while it outperforms comparative methods by a margin of 9.64% to 43.18% in the case of 1 sample per category. Furthermore, its generalizability is validated on the base station (BS) dataset, where the proposed method consistently outperforms existing approaches in few-shot scenarios.