最新刊期
- 摘要：The movable antenna (MA) technology, which enables manipulation of electromagnetic (EM) radiation characteristics through adjustable antenna positions and postures, has attracted significant attention from both academia and industry in recent years. However, existing interpretations of MA often attribute the reconfigurability of EM radiation characteristics solely to changes in antenna position, while in fact, active reconfiguration at the electromagnetic level is the key factor determining the operational posture of MA. Based on this, the core concept of MA was clarified, emphasizing that electromagnetic reconfigurability was essential for breaking through current communication performance bottlenecks. On this basis, thespatio-electromagnetic programmable antenna (SEPA) was proposed to more comprehensively characterize the synergistic reconfigurability of antennas in both spatial and electromagnetic domains. Finally, several future research directions for SEPA were outlined, including intelligent paradigms for EM radiation reconfiguration, compensation for spatial coverage gaps, platform design, and validation of key technologies.关键词：movable antenna;SEPA;electromagnetic radiation characteristics;degree of freedom2|0|0更新时间：2026-05-15
- 摘要：To address the problems of high bit error rates, and high computational complexity in traditional single-channel blind source separation methods, a single-channel blind separation algorithm based on a dual-encoder β-VAE (variational autoencoder) and attention mechanisms was proposed. A dual-encoder parallel structure was employed to extract signal features, dilated convolutions were introduced to enlarge the receptive field, and a Conformer module was utilized to fuse local and global features. In the decoder, an ECA module was incorporated to improve reconstruction quality, and multi-loss joint optimization was adopted for model training. Experimental results show that the proposed algorithm can effectively separate dual QPSK, dual 16QAM, and BPSK+QPSK mixed signals in simulated scenarios, as well as practical dual BPSK mixed signals. In the separation of dual QPSK signals over stationary channel, the proposed algorithm achieves about 3 dB, 2.5 dB and 2 dB performance gains compared with DSNet, DDAEC and D3Net algorithms at a BER of 10⁻³, respectively. While the channel is non-stationary, the proposed algorithm achieves about 4 dB, 1 dB and 0.5 dB performance gains compared with DSNet, DDAEC and D3Net algorithms at a BER of 5×10⁻3, respectively. In the separation of practical dual BPSK signals, the proposed algorithm achieves about 4 dB, 1 dB, 0.5 dB and 2.5 dB performance gains compared with PSP, DSNet, DDAEC and D3Net algorithms at a BER of 5×10⁻2, respectively.关键词：single-channel blind source separation;β-VAE;attention mechanism;dilated convolution26|40|0更新时间：2026-05-14
-
Handover authentication scheme for mobile data terminal based on secret sharing in the data Internet AI导读
摘要：To address authentication delay and security issues caused by mobile data terminals in the data internet environment, a handover authentication scheme based on secret sharing was proposed. The concept of interoperability domains was introduced, and a Markov process was employed to predict node trust states. Nodes with similar trust levels were dynamically aggregated into logical subdomains sharing authentication information, reducing global authentication to local cooperation within subdomains. For high-trust interoperability domains, the secret-sharing property of bivariate symmetric polynomials was exploited to pre-distribute authentication credentials within each subdomain, enabling terminals to complete handover authentication using only their secret shares. Centralized authentication was thereby transformed into edge authentication among intra-domain nodes, pushing the authentication center down to the edge. The security of the scheme was formally verified using the Tamarin tool, and its computational and communication overheads were evaluated. Results show that the proposed scheme is suitable for highly dynamic access environments in the data internet.关键词：data Internet;confidence prediction;secret sharing;handover authentication1|0|0更新时间：2026-05-14 - 摘要：To address issues such as interference in wireless transmission, routing failure, and low resource utilization in large-scale Ad Hoc networks, a deterministic routing method for large-scale Ad Hoc networks based on time-varying graphs was proposed. A method for large-scale network topology and resource compression representation was introduced, in which the network was divided into clusters and the topology was represented by clusters. This method compressed the large-scale network into a sparse clustered network graph, significantly reducing the scale of the network during routing computation. Based on this, a clustered network time-slot graph model was proposed, which represented the time-varying characteristics of the network topology and link states in terms of time slot. The problem of joint routing and scheduling was converted into a routing search problem within the graph. The joint routing and scheduling algorithm based on Dijkstra was designed, which under the constraints of half-duplex transmission and temporal constraints of inter-cluster resource allocation, was used to obtain the inter-cluster transmission routes in the Ad Hoc network. Simulation results show that the proposed algorithm reduces the running time by approximately 93% compared with the integer linear programming (ILP) solver, while achieving an equivalent level of performance to ILP in terms of end-to-end delay and computing success rate. This algorithm significantly improves the quality of service (QoS) guarantee and resource utilization in Ad Hoc networks.关键词：ad hoc network;time-varying graph;deterministic routing;QoS guarantee3|0|0更新时间：2026-05-14
-
Hybrid Beamforming Design for Dual-RIS-assisted Multi-user Integrated Sensing and Communications AI导读
摘要：Integrated Sensing and Communications (ISAC) is a core technology that supports the construction of low-altitude economic infrastructure. However, due to its high dependence on line-of-sight links, its performance is limited in complex environments. Reconfigurable Intelligent Surface (RIS) provides an effective way to enhance its performance. Aimed at the complex ISAC scenarios where line-of-sight links were blocked, dual RIS were adopted to assist communication and sensing respectively. Under the constraints of transmit power budget and sensing performance, the multi-user sum-rate maximization problem for the dual-RIS-assisted ISAC system was investigated based on the joint optimization of hybrid sensing-communication beamforming and RIS phase-shift matrices. The problem was demonstrated to be highly non-convex due to the tight coupling among multiple optimization variables, and it was considered extremely difficult to be solved directly. Semi-definite relaxation and successive convex approximation were jointly utilized to reconstruct and decouple the original problem, and a joint optimization algorithm based on alternating optimization was further proposed for efficient solution. The performance improvement brought by dual RIS to the ISAC system was verified by the simulation results, and the superiority of the proposed algorithm was also confirmed.关键词：integrated sensing and communication;reconfigurable intelligent surface;hybrid beamforming;semidefinite relaxation;successive convex approximation5|0|0更新时间：2026-05-14 - 摘要：This paper presents a systematic review of resource management technologies for low-altitude integrated sensing and communication (ISAC) networks, aiming to summarize the research progress and key issues of sensing-communication coordination mechanisms in low-altitude airspace. First, the societal demands, application scenarios, and the evolution of resource management in low-altitude ISAC networks were summarized. Then, frequency band selection and spectrum resource management were classified and summarized, with particular emphasis on sub-6 GHz and millimeter-wave/terahertz bands in both public and private network scenarios. Subsequently, space resource management was discussed, mainly from the perspectives of coordinated beamforming and trajectory optimization. Next, computation and caching, as emerging resource dimensions in low-altitude ISAC networks, Finally, this paper summarized the main challenges in current research and prospects future development trends, including cross-system and cross-scenario collaboration, low-altitude channel knowledge maps, and new dynamic antenna technologies, to further improve multidimensional resource utilization and network adaptability for efficient, intelligent, and secure ISAC networks.关键词：Low‑altitude economy;integrated sensing and communication;spectrum allocation;beamforming design;computation and caching deployment9|0|0更新时间：2026-05-14
- 摘要：To meet the requirements of interactive video services in low Earth orbit satellite networks for low latency, low jitter, and session continuity, a hierarchical collaborative routing strategy, termed H-GMRL, was proposed for medium Earth orbit (MEO)–low Earth orbit (LEO) satellite networks to address complex routing decisions and frequent link switching under highly dynamic topologies and spatiotemporally heterogeneous energy conditions. Graph neural networks (GNNs) and Double Deep Q-Network (Double-DQN) were adopted for multi-constraint global path planning, while multi-agent reinforcement learning (MARL) together with a trigger-based smooth switching mechanism was used for local repair. Simulation results show that the proposed strategy reduces the average end-to-end delay by up to 12.1%, decreases delay jitter by up to 45.3%, lowers the packet loss rate by up to 44.8%, and increases the average path time to live (TTL) by up to 25.9%. It provides more stable and continuous support for interactive video services under high-load scenarios.关键词：Low earth orbit satellite networks;interactive video;hierarchical routing;reinforcement learning2|1|0更新时间：2026-05-14
- 摘要：To address the problem that existing federated distillation methods struggle to handle inconsistent representation spaces and uneven feature distributions across heterogeneous models, a federated heterogeneous knowledge distillation framework based on feature projection and adaptive enhancement was proposed, achieving efficient knowledge fusion across heterogeneous client models. On the server side, client outputs were integrated via distillation; on the client side, lightweight multi-exit branches were employed to project intermediate features into an aligned logits space to overcome feature alignment bottlenecks. Promising performance was demonstrated on benchmark datasets, with reduced communication rounds and data transmission as well as enhanced system robustness, thus providing an effective new solution for heterogeneous model knowledge fusion in federated learning.关键词：federated learning;knowledge distillation;heterogeneous model;feature projection1|0|0更新时间：2026-05-14
- 摘要：Aiming at the problems of fingerprint distortion, access point state fluctuation and decreased positioning accuracy caused by multipath effect, spike noise and time difference between online and offline in indoor CSI fingerprint positioning, a CSI fingerprint positioning method integrating tensor robust principal component analysis, slope entropy detection and Gaussian mixture weighted k-nearest neighbor is proposed. Firstly, a three-dimensional CSI tensor composed of subcarriers, amplitudes and timestamps is constructed. Tensor robust principal component analysis is utilized to separate low-rank components from sparse noise, thereby achieving CSI data denoising. Secondly, a slope entropy detection mechanism is introduced to dynamically screen stable access points in both online and offline phases, thereby enhancing the algorithm's adaptability to environmental changes. Finally, by combining the Gaussian mixture model and the weighted K-nearest neighbor algorithm, the offline fingerprint is modeled and the online data is grouped, and the K value is adaptively allocated to complete the location estimation. The results show that this method can effectively improve the accuracy and robustness of CSI fingerprint positioning in complex indoor environments.关键词：Wi-Fi Indoor Positioning;TRPCA;Slope Entropy;AP State Constraint Detection;GWKNN2|0|0更新时间：2026-05-14
- 摘要：Sparse inverse synthetic aperture radar (ISAR) imaging methods are capable of reconstructing target images with high contrast and few artifacts under limited observation conditions. Incorporating sparse transform dictionaries into sparse ISAR imaging can further enhance the reconstruction quality of target contours and scattering distributions. However, these methods still tend to produce incomplete target contours under conditions of low compression ratios. This limitation arises because the sparse representations derived from sparse transform dictionaries primarily capture local structural or scattering features of the target, while failing to sufficiently represent the global structural and scattering features of the target. To strengthen the modeling of global structures within sparse representations, we introduce a self-attention mechanism (SAM) to guide dictionary learning (DL), enabling the sparse transform dictionary to effectively capture global structural features of target from under-sampled measurements. The resulting DL model is referred to as SAM-DL, and we further develop the SAM-DL based sparse ISAR imaging method for target reconstruction under low compression ratios. Experimental results demonstrate that, compared with existing DL-based imaging approaches, the SAM-DL method is able to reconstruct more complete target contours under low compression ratios, achieving superior imaging performance.关键词：inverse synthetic aperture radar (ISAR);sparse imaging;SAM-DL;dictionary learning;self-attention mechanism1|0|0更新时间：2026-05-13
- 摘要：To address the issues of heavy reliance on manual expertise, high time consumption, and increasing model complexity in color image steganalysis network design, a two-stage differentiable steganalysis architecture search framework was proposed to automatically design efficient network architectures. In view of the critical role of preprocessing layers, the first stage constructs a specialized search space oriented towards color channels. It utilizes group convolution and prior knowledge to guide the optimization of noise residual extraction, demonstrating superior high-pass characteristics and search efficiency compared to existing methods. Building upon this foundation, the second stage performs a joint search for the network's operation types and depth. Experimental results demonstrate that the architectures derived by STARS outperform state-of-the-art models on the ALASKA-v2 dataset, achieving superior detection performance in both spatial and JPEG domains with significantly reduced model size.关键词：information hiding;image steganalysis;steganography;neural architecture search;convolutional neural network17|0|0更新时间：2026-05-08
- 摘要：To address the limitations of conventional maximum correntropy criterion (MCC) algorithms in non-Gaussian, non-stationary underwater acoustic channels, specifically their dependency on fixed kernel widths and the vulnerability of center estimation to impulse contamination, a variable-center variable-kernel-width MCC (VC-VKW-MCC) channel estimation method based on median absolute deviation (MAD) was proposed. The robust property of MAD to impulses was utilized, combined with sliding windows and soft clipping, to achieve the adaptive updating of the filtering center and kernel width, thereby effectively suppressing impulsive noise. The mean-square convergence condition of the method was theoretically derived. Simulation results showed that the proposed algorithm obtained more than 70% higher steady-state accuracy than the fixed-kernel-width MCC algorithm, and more than 60% higher accuracy than the Fe-MCC-AKW algorithm.关键词：Underwater acoustic channel estimation;Maximum correntropy criterion;Median absolute deviation;Variable center;Variable kernel width15|0|0更新时间：2026-05-08
- 摘要：In response to the insufficient research on digital twins for electromagnetic spectrum communication relationships, digital twin methodologies for communication-link modeling was explored, and a digital twin framework for communication links in wireless local area networks was proposed by integrating incomplete cooperative prior exploitation, node signal separation, and link inference. The framework addressed two key challenges, multi-source heterogeneous data alignment across link-related time scales and link representation from high-rate sampled electromagnetic signals. A digital twin system was further developed to visually present the inferred communication links. The digital twin of electromagnetic spectrum communication relationships for Wi-Fi 6 signals was tested. The experimental results show that the proposed method effectively enables digital twin modeling for wireless local area network spectrum communication, achieving 98% accuracy with a runtime of 0.26 s.关键词：electromagnetic spectrum digital twin;intelligent spectrum sensing;communication relationship;topology inference;Wi-Fi 6;USRP13|0|0更新时间：2026-05-08
- 摘要：Spectrum situation prediction could infer the evolutionary trends of future spectrum states by exploiting the spatiotemporal and frequency-domain characteristics embedded in historical spectrum measurements. It provided prior information for spectrum sensing, decision-making, and sharing, thereby effectively alleviating spectrum resource scarcity. From the perspective of deep feature learning, the limitations of traditional linear modeling approaches was overcomed, and the current research progress of deep feature learning in time-frequency, spatiotemporal, and cross-domain spectrum prediction was reviewed. Subsequently, with time, frequency, and spatial-domain self-attention feature learning as the core, for the first time, a three-dimensional classification framework was established for deep spectrum situation prediction. It further presented the key technical implementation routes for deep time-frequency spectrum prediction, deep spatiotemporal spectrum prediction, and deep cross-domain spectrum prediction. Further experimental analysis was conducted on real-world spectrum data to validate the effectiveness of the key technologies. The experimental results demonstrate that the proposed methods 1 and 2 achieve an average prediction performance improvement of over 10% compared to existing mainstream baselines (i.e., the minimum value among the averages of all evaluation metrics). The proposed framework provides valuable insights for improving spectrum utilization efficiency and intelligent management capabilities in 6G networks and low-altitude intelligent networking systems.关键词：low-altitude intelligent networks;spectrum situation prediction;deep feature learning;graph self-attention;Mamba;diffusion network19|0|0更新时间：2026-05-08
-
Channel estimation algorithm for OTFS based on basis expansion model with bidirectional LSTM network
摘要：Accurate channel estimation is critical for the reliable deployment of orthogonal time frequency space (OTFS) systems in 6G high-mobility scenarios. To further improve the channel estimation accuracy in OTFS systems, this paper proposes a channel estimation algorithm integrating the basis expansion model (BEM) and a bidirectional long short-term memory (LSTM) network. The proposed algorithm first uses BEM to reformulate the channel estimation problem in the delay-Doppler (DD) domain into a basis coefficient estimation problem. A bidirectional LSTM network is then introduced for offline training and online prediction of the basis coefficients, and a self-attention (SA) mechanism is incorporated to strengthen global perception of temporal features, enabling high-accuracy estimation and dynamic tracking of the basis coefficients. Building on this, a low-complexity two-stage equalizer is further designed. Channel information is reconstructed from the estimated basis coefficients, multipath effects are mitigated via a single-tap equalizer, and a log likelihood ratio based iterative interference cancellation (LLR-IIC) algorithm is employed in the DD domain to suppress residual interference induced by Doppler spread. Simulation results demonstrate that the proposed algorithm offers significant advantages in channel estimation accuracy, generalization capability, and complexity. When combined with the proposed equalizer, superior bit error rate (BER) performance is achieved while maintaining low complexity.关键词：channel estimation;OTFS;high-mobility scenarios;BEM;bidirectional LSTM;two-stage equalizer19|5|0更新时间：2026-04-30 - 摘要：To address difficult ownership definition, easy circulation loss of control, and hard value evaluation challenges caused by data's high replicability and non-rivalry in data factorization, a new data capsule circulation paradigm was proposed. Based on the triangular model of "controlled environment, tangible data, and identified personnel", a four-layer theoretical system covering ontology, ownership, circulation, and pricing was constructed. Through in-depth binding of data with processing and usage strategies and support of trusted execution environments, it enables secure data circulation and value release. Multi-dimensional analysis shows that the paradigm outperforms traditional solutions in data factorization support and comprehensive performance. This paradigm is applicable to scenarios such as dataset delivery, controlled circulation of special files, compliant data sharing, and controllable circulation of personal privacy data, providing a vital technical supplement for Trusted Data Space to ensure ownership circulation and full-process controllability.关键词：Data elementization;data capsule;data circulation;trusted execution environment18|2|0更新时间：2026-04-29
- 摘要：To address the inadequate optimization of performance indicators, such as end-to-end delay, jitter, and bandwidth utilization, as well as the poor scalability in the joint routing and scheduling of Time-Sensitive Networking (TSN), a multi-objective joint scheduling optimization algorithm based on an improved Non-dominated Sorting Genetic Algorithm was proposed. Specifically, a multi-objective network architecture utilizing TSN performance indicators as optimization objectives was established, feasible traffic paths were comprehensively analyzed, and the global optimal multi-objective solution was identified. Furthermore, the effectiveness of the proposed algorithm was evaluated through extensive experiments. The proposed algorithm significantly improves the comprehensive traffic performance in terms of end-to-end delay, jitter, and bandwidth utilization in large-scale complex scenarios.关键词：Time-Sensitive Networking, Non-dominated Sorting Genetic Algorithm;multi-objective optimization;joint routing and scheduling15|15|0更新时间：2026-04-29
- 摘要：Electronic voting is an important approach for the digitalization of elections and voting procedures, in which cryptographic techniques are used to provide anonymity, verifiability, and tamper resistance. To address the low tally-verification efficiency and insufficient support for diverse voting modes identified in existing schemes, an anonymous and auditable aggregate ring signature scheme supporting multiple voting modes was proposed. The proposed construction was designed to preserve voter privacy while ensuring the legitimacy of voting operations. Ring signatures were employed to hide verifier identities and reduce the risk of tracing or manipulation during verification, while an aggregation mechanism was introduced to compress multiple ballots into compact verification objects to improve tally-verification efficiency. To regulate the number of votes cast by the same signer, a linking authority was introduced together with linkable tags, enabling support for both single-vote and multiple-vote settings. Security analysis and experimental results were conducted to validate the proposed scheme. The results demonstrate that the proposed scheme achieves a good balance between anonymous regulation and efficiency, and reduces the time overhead in the linking phase by about 98.29% on average compared with the k-LRS scheme.关键词：e-voting;ring signature;identity hiding;linkability24|12|0更新时间：2026-04-27
- 摘要：In multi-terminal downlink semantic communication scenarios, employing a uniform semantic compression ratio caused difficulty in semantic decoding for low-computing-power terminals, as well as underutilized computing power resources and insufficiently refined semantic data for high-computing-power terminals. To address this issue under constraints of limited terminal computing power and link bandwidth, this paper proposed a lightweight Swin Transformer-based resource-adaptive semantic compression strategy. The semantic encoder integrated a gating network and a sparse attention mechanism to customize differentiated semantic compression ratios for individual terminals. A joint computing and bandwidth allocation model was formulated to minimize total system energy consumption. The proximal policy optimization (PPO) algorithm was employed to solve the optimization problem. Simulation results demonstrate that, compared with fixed compression ratio schemes, the proposed strategy reduces total system energy consumption by 39%.关键词：semantic communication;Swin Transformer;sparse attention mechanism;proximal policy optimization algorithm30|17|0更新时间：2026-04-27
-
A Shortwave Autonomous Signal Detection and Localization Method Based on Deep Reinforcement Learning AI导读
摘要：In the process of real-time shortwave signal detection and localization, problems such as data association and error propagation were frequently observed, by which a mismatch between detection and localization results was easily induced, and the timely output of outcomes was impeded. To address the above issues, an integrated shortwave signal detection and localization algorithm based on Multi-agent Proximal Policy Optimization (MAPPO-DL) was proposed. By constructing a reinforcement learning environment using shortwave signal time-frequency diagrams, spectral characteristics of shortwave signals were effectively captured. A filtering-window agent with hybrid action space was designed for adaptive signal selection. Furthermore, localization error ellipse probability, signal matching degree, and multi-agent collaboration strategies were incorporated into the reward function design. Optimal policies were explored by the optimized MAPPO to achieve autonomous shortwave signal detection and localization. Simulation results demonstrate that compared with baseline algorithms, our approach reduces average recognition-localization time by 0.12s while improving accuracy by 22%, thereby providing a novel solution for autonomous cooperative target detection and localization in complex electromagnetic environments.关键词：Shortwave signal detection and localization;Multi-Agent Proximal Policy Optimization;reinforcement learning;Hybrid action space;Localization error ellipses18|9|0更新时间：2026-04-23
- Technical support is provided by Beijing Founder electronics co., LTD 京ICP备09064830号-19
京公网安备11010802024621 - It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
- Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.
- Total Visits：686514
0