Deploying uncrewed aerial vehicles (UAVs) in vehicular networks overcomes the inherent limitations of terrestrial infrastructure by dynamically enhancing coverage and line-of-sight (LoS) connectivity. However, further enhancement of the data rate necessitates the deployment of additional terrestrial base stations (BSs) and UAVs, which incur high costs and consume a large amount of energy. To address these challenges, synergistically integrating UAVs equipped with intelligent reflecting surfaces (IRS) and multiple-input multiple-output (MIMO) techniques can effectively improve the channel capacity of air-to-ground integrated vehicular networks, while maintaining low cost and low power consumption. The key idea is to partially replace some of the required terrestrial relays with high-flexibility and energy-efficient UAVs equipped with IRS. Specifically, in IRS-MIMO air-to-ground integrated vehicular networks, we formulate a joint precoding design, phase shift optimization, and UAV deployment problem with the objective of maximizing the weighted sum-rate. To tackle this non-convex problem, an iterative optimization algorithm with polynomial-time complexity is developed, which enables a gradual approximation of a feasible solution to the formulated problem. Finally, simulation results demonstrate that the proposed scheme is superior to the state-of-the-art schemes in terms of the weighted sum-rate. Additionally, the impact of network parameters on transmission performance and the convergence of iterative optimization are thoroughly analyzed.
Yi-Xin He, Fang-Hui Huang, Da-Wei Wang et al.· IEEE Transactions on Communi...· 0 citations
Accurate delineation of infarct core and ischemic penumbra in acute ischemic stroke primarily relies on computed tomography perfusion (CTP), where the arterial input function (AIF) is essential for reliable perfusion quantification. However, reliable and fast AIF selection remains challenging in clinical practice due to noise, vascular heterogeneity, and inter-patient variability in bolus dynamics. In this study, we propose TriAIF-RWKV, a three-stage framework for robust and automated AIF extraction. Specifically, ACSANet is first employed for spatial vascular localization using axial and channel-aware attention mechanisms, thereby narrowing the candidate arterial region and reducing the AIF search space. Then, a Dilated-RWKV network is introduced to model temporal intensity dynamics from a global sequence perspective, allowing robust identification of AIF-consistent patterns. Finally, a physiology-informed scoring strategy is used to select the optimal AIF by evaluating baseline stability, peak enhancement, and washout characteristics. Extensive experiments on CTP datasets were conducted from multiple perspectives, including AIF waveform fidelity, perfusion parameter estimation, and lesion-level analysis. The results demonstrate that the proposed method achieved high agreement with expert-selected AIFs, with a global waveform PCC of 0.973, peak correlation of 0.942, and TTP correlation of 0.973 with a mean error of 0.923 s. Furthermore, the proposed method provides more consistent downstream perfusion quantification, achieving higher consistency of CTP-derived parameters and improved lesion-to-normal tissue discrimination compared with existing approaches. These results highlight its potential for reliable clinical perfusion assessment.
Lei Lei, Yu Shen, Dawei Wang et al.· Entropy· 0 citations
This letter investigates a dynamic sensing and covert communication network enabled by a reconfigurable intelligent surface (RIS), where a base station continuously senses an illegal autonomous aerial vehicle (AAV) and utilizes the sensing signals to achieve covert transmission for legitimate ground users. To address the time-varying target states induced by AAV motion, this letter employs an extended Kalman filter (EKF) to perform real-time estimation of the AAV’s 3D position. Then, a covert rate maximization problem is formulated with sensing performance, transmit power, and covertness constraints. To tackle this non-convex problem, a dynamic online resource allocation scheme based on a graph neural network (GNN) is proposed. By leveraging heterogeneous graph features and a constraint-aware loss function, the proposed GNN scheme optimizes the communication and sensing beamforming vectors and the RIS phase shifts. Simulation results show the superiority of the proposed scheme in terms of covert rate. Compared with the alternating optimization scheme, the proposed scheme achieves a 22% improvement in covert rate.
