With the widespread adoption of Internet of Things (IoT) devices, device identification has emerged as a critical challenge for ensuring the security of wireless communications. Radio Frequency (RF) fingerprinting, a physical-layer security approach that requires no hardware modifications, has attracted considerable attention for its cost-effectiveness and robust security properties. Conventional RF fingerprinting models insufficiently exploit signal characteristics, thereby constraining recognition accuracy. To address this limitation, we propose a Multi-Channel Attention Residual Fusion (MCARF) method. It integrates five heterogeneous signal representations, including raw IQ data, individual in-phase (I) and quadrature (Q) components, and features derived from the Fast Fourier Transform (FFT) and Short-Time Fourier Transform (STFT), to comprehensively capture device-specific characteristics. To effectively manage the heterogeneity across these channels, a Dual Attention Residual Block (DARB) is introduced to amplify critical feature responses while mitigating the vanishing gradient issue in deep neural networks. Additionally, a Multi-Channel Feature Fusion (MCFF) module is developed to adaptively learn inter-channel feature weights through attention mechanisms, thereby enhancing relevant information and suppressing redundant or noisy data. Extensive experiments conducted on two representative datasets, namely a simulated dataset under varying SNR conditions and the real-world ORACLE dataset, demonstrate that MCARF consistently outperforms state-of-the-art methods in terms of accuracy, precision, recall, and F1-score. Moreover, the MCARF method exhibits superior discriminative capability, particularly in challenging low-SNR environments.

Summary In the fields of wireless communication and data processing, there are varieties of mathematical optimization problems, especially nonconvex and nonsmooth problems. For these problems, one of the biggest difficulties is how to improve the speed of solution. To this end, here we mainly focused on a minimization optimization model that is nonconvex and nonsmooth. Firstly, an inertial Douglas–Rachford splitting (IDRS) algorithm was established, which incorporate the inertial technology into the framework of the Douglas–Rachford splitting algorithm. Then, we illustrated the iteration sequence generated by the proposed IDRS algorithm converges to a stationary point of the nonconvex nonsmooth optimization problem with the aid of the Kurdyka–Łojasiewicz property. Finally, a series of numerical experiments were carried out to prove the effectiveness of our proposed algorithm from the perspective of signal recovery. The results are implicit that the proposed IDRS algorithm outperforms another algorithm.

Rate-distortion optimization (RDO) is widely applied in video coding, which aims at minimizing the coding distortion under a target coding rate. Conventionally, RDO in video coding does not take into account the coding complexity. However, because of the diversity of video applications, the video encoders in different applications may have different requirements of or limitation on the computational complexity. Therefore, it is desirable for video encoders to perform RDO in flexible computational complexity. In this paper, we propose a novel RDO scheme under the given computational complexity for the latest H.265/HEVC standard. A model for prediction of the rate-distortion cost (RD cost) is first established based on a pre-searching process. Then according to the predicted RD cost, the rate-distortion-complexity (R-D-C) characteristics of different coding tree units (CTUs) are analyzed. Finally, the total complexity budget is properly allocated to different CTUs according to their R-D-C characteristics. Experimental results demonstrate that, compared with x265, the proposed algorithm can reduce, on average, the BD-rate by 18.8% under the same requirements of encoding speed.