26 March 2025 in IEEE Signal Processing Letters
Radio frequency (RF) fingerprinting is a technique used to identify different transmitters by analyzing the unique hardware impairments of RF transmitters, known as RF fingerprints. However, many existing studies have primarily focused on transmitter impairments, while the impact of receiver hardware impairments on RF signals has often been overlooked. To alleviate this issue, this letter proposes a receiver-agnostic RF fingerprinting method using unsupervised domain adaptation. The method employs prototypical contrastive learning to align the features of source domain and target domain data, while simultaneously learning the features of both domains. Experimental results on the real-world dataset (WiSig) demonstrate that the proposed method outperforms other receiver-agnostic RF fingerprinting methods.
26 December 2024 in IEEE Communications Letters
Specific emitter identification (SEI) is a unique physical-layer security technology that plays a crucial role in protecting wireless communication systems from various security threats. Although SEI based on artificial neural network models has achieved good identification performance, its performance degrades when labeled samples are limited. To address this issue, this letter proposes a few-shot SEI method based on a contrastive masked learning framework. This method combines contrastive learning and masked learning to enhance the model’s representation capability, and it consists of an encoder, a signal decoder, a feature decoder, and a momentum encoder. Simulation experiments on the open-source datasets LoRa and ADS-B show that the proposed method outperforms other SEI methods.
12 August 2025 in Knowledge-Based Systems
24 March 2026 in IEEE Transactions on Cognitive Communications and Networking
Deep learning techniques have been widely applied to automatic modulation classification (AMC) and have achieved promising results. However, when the sample distribution of signals shifts, such as when signals are transmitted through different channels, the performance of deep learning models tends to degrade significantly. To address this issue, a confidence-guided prototypical contrastive domain adaptation method is proposed for cross-domain AMC. The proposed framework consists of intra-domain prototypical contrastive learning, cross-domain prototypical contrastive learning, and confidence estimation. Intra-domain prototypical contrastive learning is used to model signal features. Cross-domain prototypical contrastive learning is employed to align feature distributions between the source and target domains. Confidence estimation is introduced to measure the contribution of each sample to the alignment process. Experimental results show that in the AWGN → Rayleigh scenario at 0 dB, the proposed method improves classification accuracy by 10%, 6%, 7%, 6%, and 4% compared with CST, WTBG, AMRMIDAN, MMDA-MC, and PMSPDMC, respectively.
6 November 2024 in IEEE Communications Letters
Signal recognition plays a crucial role in wireless communications, with artificial neural network models being widely applied, and the success of these models largely depends on abundant labeled data. However, practical signal recognition scenarios often face a shortage of labeled samples and an abundance of unlabeled ones. Therefore, semi-supervised learning (SSL) methods have emerged as a solution. This letter proposes a novel signal-understanding semi-supervised learning (SUSSL) framework to enhance the performance of SSL further. SUSSL comprises a reconstruction and a metric module. The former module learns useful features by disrupting and reconstructing low-level features, and the latter utilizes similarity learning to process low-level features. A symmetric dual-branch neural network (SDNN) model is also designed to facilitate these two modules. Simulation experiments on the open-source datasets RadioML2016.10a and RadioML2016.10b demonstrate that the proposed method outperforms current SSL methods.