17 April 2025 in IEEE Sensors Journal
Radio Frequency Fingerprint Identification (RFFI) is a promising technology for Internet of Things (IoT) device authentication, which uses a device’s unique hardware imperfections patterns as the “fingerprint”, providing a highly secure, device-specific form of authentication for IoT devices. Due to the influence of inherent hardware imperfections of receivers, the performance of RFFI is markedly reduced when the receiver is changed. In engineering practice, when the receiver changes, the data on the new receiver needs to be relabeled and retrained, resulting in significant resource consumption. To address this limitation, a few studies utilized Domain Adaptation (DA) to avoid relabeling data on the new receiver. However, existing DA methods focused exclusively on aligning the domain distribution at the feature level, resulting in performance limitations and neglecting the utilization of unlabeled target domain data. To address these shortcomings, we propose a two-stage Domain Adaptation method for cross-receiver RFFI. The proposed method sequentially performs data-level domain alignment based on Tensor Alignment Invariant Subspace Learning and feature-level domain alignment based on Subdomain Adaptation to achieve a comprehensive domain alignment. In addition, we introduce a pseudo-labeling method based on Confident Learning to improve the utilization of unlabeled data. Experimental results on the publicly available WiSig dataset show that the proposed method achieves at least 30% performance improvement in cross-receiver scenarios, and outperforms other existing Domain Adaptation methods.
26 March 2025 in IEEE Communications Letters
Orthogonal time frequency space (OTFS) modulation has been shown to support reliable communication in high mobility scenarios. Due to the sparsity of the delay-Doppler (DD) domain, most existing algorithms utilize compressed sensing (CS) for OTFS channel estimation, while requiring a known channel sparsity. However, in cases that the sparsity is not readily accessible, the estimation accuracy of these CS algorithms decreases dramatically. In this letter, we propose a Smoothed ℓ0 (SL0) algorithm free of prior knowledge about channel sparsity for OTFS channel estimation. We obtain a novel vector expression of the input-output relationship in the DD domain and formulate it as a sparse signal recovery problem. In the case of unknown sparsity, a low-complexity SL0 algorithm is introduced to solve the problem with a faster reconstruction speed. Simulation results show that the proposed algorithm has significant advantages in estimation accuracy and complexity compared to algorithms that also do not require channel sparsity.
25 June 2025 in IEEE Transactions on Cognitive Communications and Networking
Specific emitter identification (SEI) is essential for enhancing the security of Internet of Things (IoT) devices and wireless communication networks. Incremental learning, capable of adapting to real-time data streams with new categories, performs effectively when abundant labeled samples are available. However, the identification accuracy of current incremental learning-based SEI methods decreases in the presence of limited labeled samples. To address this issue, we integrate self-supervised learning (SSL) into incremental learning, structured into three stages: pre-training task, pretext task, and downstream task. The proposed method utilizes contrastive learning in the pretext task to effectively utilize unlabeled samples, thus reducing the necessary number of labeled samples and improving recognition accuracy even with small samples. Experimental results on real radio stations and ADS-B datasets demonstrate that the proposed method achieves an average accuracy of 80.50% on the ADS-B dataset and 92.97% on the radio stations dataset with 100 labeled new category training samples. The code can be downloaded from https://github.com/Simple-up/ISSL.
1 May 2021 in Journal of Physics: Conference Series
In this paper, we propose a tunable ultra-broadband terahertz absorber based on hybrid gold-graphene resonator to achieve an ultra-broadband, ultra-thin, and tunable metasurface, which has not only the high absorption rate of gold metamaterials but also the tunable properties of graphene metamaterials, compared with the traditional single gold-based and graphene-based methods. By simulating the response frequencies by the finite element method, we found that the absorber achieves a broadband 2.68-7.48 THz range (absorption>80%) absorbance with a relative bandwidth of 94.5%, where the center frequency is f c=5.08THz. The physical mechanism of the absorber was analyzed using the electric field of the surface plasmon resonance, due to the design structure presents periodic geometric symmetry, the polarization angle and large angle incidence both present better advantages. The dynamic tuning of the metamaterial absorber is achieved by changing the Fermi energy level of graphene by adjusting the bias voltage to effectively control the metamaterial absorption intensity and resonant frequency. Our proposed absorber has important application prospects in sensing, optical communication, detection, and optical devices.
1 January 2026 in IEEE Transactions on Cognitive Communications and Networking