ABSTRACT Unmanned Aerial Vehicle (UAV) networks are increasingly deployed in dynamic environments where reliable and low‐latency communication is critical. However, high mobility, intermittent connectivity, spectrum limitations, and energy constraints make conventional static communication protocols inadequate for maintaining stable, dependable links. To address these challenges, this paper proposes TRC‐MAPPO, a topology‐aware reliability‐constrained multi‐agent deep reinforcement learning framework for adaptive UAV swarm communication. The routing problem is formulated as a constrained decision‐making task that jointly considers packet delivery reliability, end‐to‐end delay, link stability, bandwidth usage, and energy consumption. Unlike single‐agent DRL baselines, TRC‐MAPPO represents the swarm as a dynamic communication graph and combines local relay selection with centralized training, enabling cooperative routing decisions under time‐varying network conditions. Simulations are conducted in a controlled, dynamic UAV environment, with the same mobility and traffic settings used for all methods. The proposed framework is compared with DQN and PPO over different swarm densities. Results show that TRC‐MAPPO achieves a higher packet delivery ratio, lower end‐to‐end delay, and more efficient energy behaviour, particularly in dense deployments. These findings indicate that topology‐aware cooperative learning can provide a scalable and practical solution for reliable UAV communication in future intelligent aerial and 6G‐enabled networks.

Accurate traffic flow prediction is essential for intelligent transportation systems, yet most existing methods still forecast future traffic states mainly from the current historical input window and its derived representations. In real traffic systems, however, similar recent observations may correspond to different future evolutions under different latent traffic regimes, while short-term disturbances can further mislead input-local modeling. To address this issue, we propose an Adaptive Semantic Pattern Matching Transformer (ASPMformer) for traffic flow prediction. Rather than departing from the input-driven forecasting paradigm, ASPMformer complements it in three ways: a Context Embedding module enhances local semantic dependencies between adjacent time steps and reduces sensitivity to short-term fluctuations; an explicit spatiotemporal pattern repository enables the current input to be matched with reusable representative traffic patterns in both temporal and spatial dimensions; and a multi-granularity temporal modeling module enlarges the receptive field to capture long-range traffic trends. Extensive experiments on five public benchmark datasets, including PeMS03, PeMS04, PeMS07, PeMS08, and SZ-taxi, show that ASPMformer achieves competitive and consistent improvements over strong baselines. The results further suggest that the proposed pattern repository is particularly beneficial under heterogeneous and disturbance-prone traffic conditions, where relying solely on the current historical window is less sufficient. For the main content of the model, see https://github.com/ccy123q/ASPMformer.

This paper presents HexLock, a compact and energy-efficient ASIC-based digital locking system that employs a4-bit hexadecimal key architecturefor secure hardware-level access control in embedded and consumer electronic applications. Unlike traditional microcontroller-based locks, it eliminates firmware dependencies and operates using fully synchronous, power gated digital logic, significantly reducing power and area overhead. The system accepts parallel 16-bit binary key input or 4-bit sequential hexadecimal key inputs, and verifies them through a pipelined XOR-OR logic against a configurable stored code, enforcing tamper resistance via an on-chip false attempt counter and early mismatch termination logic. Designed and verified on SCL 180nm CMOS node, HexLock records a core layout area of 0.35mm2and post-layout delay of 4.5 ns along with dormant and active power consumption of 4.76 μW and 0.15 mW respectively under typical operating conditions. Functional validation across full PVT corners (-20°C to 120°C) confirms reliable operation up to 85 MHz. As summarized in Table IV, HexLock achieves substantially lower active power and a smaller silicon footprint compared to standard MCU and FPGA based locking alternatives, thereby eliminating firmware dependencies through hardware-only authentication. These properties make HexLock a practical candidate for integration in smart locks, IoT platforms, and safety-critical consumer systems.

The rapid expansion of the Internet of Things (IoT) demands effective communication protocols that accommodate mobile and static end devices (EDs). LoRaWAN (Long Range Wide Area Network), a pioneering low-power wide-area network (LPWAN) technology, uses Adaptive Data Rate (ADR) approaches to optimize resource allocation, particularly for static EDs. However, traditional ADR approaches are ineffective in mobile contexts as they struggle to adapt to changing network conditions, resulting in significant packet loss and higher retransmission rates. Although innovative technologies, such as the Blind ADR (BADR), have been devised to improve the performance of mobile EDs, they still fall short of dealing with the unpredictable nature of mobile EDs. To address these challenges, this paper presents a novel HybridQ-ADR mechanism suitable for static and mobile EDs. This approach addresses the constraints of BADR and related methods in mobile scenarios. In particular, it provides a more efficient solution to reduce packet loss and collisions in dense and dynamic LoRa-based IoT networks. This is achieved by allocating Spreading Factors (SF) using signal orthogonality to minimize interference and provide reliable communication. Furthermore, the proposed HybridQ-ADR mechanism provides a new clustering technique based on estimated path loss. Specifically, it divides EDs into clusters and assigns different channels to each cluster, improving SF allocation and data transmission speeds. The proposed HybridQ-ADR mechanism includes a mobility-aware, Doppler-constrained SF allocation strategy, limiting each ED’s maximum SF based on its Doppler/mobility load to maintain reliable performance at high speeds. Performance evaluations using simulations and testbed implementations show that HybridQ-ADR improves latency, packet success rate, power consumption, and throughput for both static and mobile EDs.

While service-oriented low Earth orbit (LEO) satellite edge computing (LSEC) frameworks enable diverse edge services for user tasks, the heterogeneous distribution of terrestrial users causes substantial imbalance in computational task loads across satellites. This asymmetric workload leads to inefficient resource utilization and degraded edge computing performance. To address these challenges, we propose a joint optimization framework that integrates edge service deployment and task offloading, supported by service popularity analysis and spatiotemporal user-task modeling. The framework employs a two-timescale design: at the large timescale, an improved atomic orbital search (iAOS) heuristic dynamically optimizes service placement, configuration, and resource allocation; at the small timescale, a direction-selective multi-agent double deep Q-network (DS-MDDQN) leverages deep reinforcement learning to route tasks to the most suitable processing nodes. Extensive simulations show that our approach significantly outperforms six representative baselines in both user-perceived performance and system-level efficiency. Replacement studies further verify the effectiveness of each component: iAOS enhances resource utilization and reduces task failure through optimized service deployment, while DS-MDDQN mitigates network dynamics and lowers task completion latency via adaptive task offloading.

Multi-access Edge Computing (MEC) technology has been widely considered as a paradigm for offloading computation-intensive and latency-sensitive tasks from ground devices (GDs). However, the deployment of ground edge servers to provide ubiquitous computing services for GDs may incur extremely high costs, primarily due to the uneven distribution of devices and the complexity of geographical environments. As a promising solution, deploying edge servers on Low Earth Orbit (LEO) satellites can offer superior coverage and reduced latency for processing remote terrestrial computational tasks. Nevertheless, considering the limitations in computing resources and energy supply on LEO satellites, it is crucial to enhance task processing efficiency while taking energy consumption into account. In this paper, we consider a multi-satellite cooperative edge computing network (MSCECN) where time-sensitive tasks can be offloaded to an Access Satellite (AS) and multiple Edge Satellites (ESs) through Inter-Satellite Links (ISLs). We formulate a delay-minimization offloading problem by jointly optimizing satellite selection, computing resource allocation, task scheduling, and transmit power control. To solve this problem effectively, we propose a novel joint iterative algorithm called Multi-Satellite Cooperative Resource Allocation (MSCRA), which integrates the relaxation method, the Lagrangian multiplier framework, and the CVX toolbox. Simulation results demonstrate that the proposed optimization scheme achieves a 35.5% reduction in total delay compared to benchmark algorithms and effectively minimizes offloading latency across various resource constraints.

With the popularization of face recognition technology in IoT-Cloud, the problem of privacy leakage caused by it is becoming more and more serious. Although traditional privacy protection schemes can improve security to a certain extent, there is still a risk of data leakage when facing semi-trusted cloud servers. To this end, this paper proposes an anonymized face verification scheme for IoT convergence scenarios, which achieves real-time retrieval and secure matching of dense face features in virtual device copies by combining homomorphic encryption (CKKS) and privacy information retrieval (PIR) for anonymized face verification. The scheme ensures that the semi-trusted cloud server cannot obtain user-specific index information and matching results. Experiments show that the scheme’s verification accuracy in the ciphertext state on the LFW dataset is consistent with the plaintext, up to 97.06%, and can complete a privacy-protected anonymized facial verification process within seconds. The scheme is feasible in security demanding scenarios.

Eddy current testing (ECT) is a widely adopted electromagnetic non-destructive testing (NDT) technique for detecting defects in conductive materials. In practical deployments, however, ECT systems often suffer from low signal-to-noise ratio, strong sensitivity to lift-off and environmental variations, and complex multi-parameter coupling, which makes robust signal interpretation challenging. Meanwhile, the growing demand for portable and always-on inspection pushes data processing toward resource-constrained embedded hardware. Tiny machine learning (TinyML) provides a promising pathway for enabling on-device intelligence by deploying compact models with low latency and low power consumption. This review summarizes recent progress in integrating TinyML into ECT, covering the ECT signal characteristics and key technical bottlenecks, the TinyML workflow and optimization techniques for embedded deployment, and representative application scenarios including pipeline inspection, corrosion detection, and thickness evaluation. We further analyze the main barriers to adoption, such as limited computing power and memory, data scarcity, calibration overhead, and generalization across materials, probes, and defect types, and we outline future research directions including physics-guided learning, federated learning, and standardized benchmarks for ECT-oriented TinyML evaluation.

Application areas such as real-time visual analytics over high-bandwidth 6G networks, low-power camera networks in remote or low-light environments and surveillance drones, usually operate under insufficient lighting conditions. The captured images are often of low quality, poor resolution and poor visual clarity, leading to reduced visibility, color distortion, and amplified noise. Existing methods of Low-light image enhancement suffer from low accuracy with compromised reliability, trust and fairness. Inspired by the zero-reference learning paradigm of Zero-DCE++, this work aims to investigate the impact of data pre-processing and augmentation strategies for improving the performance of real-time, mission-critical security systems where low-light surveillance images are used for critical decision making. The proposed method uses FFDNet for denoising, exposure fusion for illumination improvement and data augmentation for bias mitigation and performance optimization through diverse training samples. The method is curated for edge deployment on constrained IoT hardware, with low latency and energy efficient usage in 6G-IoT visual systems. The proposed model is aimed at performance improvement on trust driven visual improvements, reduced distributional bias, and deployment fairness across diverse lighting conditions and scenarios. Comparative analysis demonstrates that with the help of zero-reference deep curve estimation, the proposed,DA-Zero-DCE++, pipeline achieves improved performance as compared to state-of-the-art low-light image enhancement methods. Our best configuration, which combines exposure fusion-based augmentation and mild denoising using FFDNet, achieves an average PSNR of 15.34dB, SSIM of 0.4869, and MAE of 40.87 on theSICE datasetat 1200 × 900 resolution. For high-level vision applications such as real-time visual analytics over highbandwidth 6G networks, low-power camera networks in remote or low-light environments, the performance is further validated on DarkFace dataset where high average precision at intersection over union of 0.5 is achieved.

With the advent of the 5G era, online healthcare has rapidly developed, and medical efficiency has been greatly enhanced through medical data sharing. However, as cloud services are not fully trusted, users who have lost physical control of their data urgently require a provable data possession scheme to regularly verify the integrity of their outsourced data. Moreover, the scheme must protect the user’s real identity and the security of the data content. To meet these needs while overcoming issues such as complex certificate management, high operational costs, and the key escrow problem, scholars have proposed many certificateless provable data possession schemes. Among them, we analyze the ReCIP scheme which supports privacy preservation and efficient revocation, identify its limitations, and propose an enhanced ReCIP+ scheme tailored for medical data sharing. Under the assumption that the discrete logarithm problem and the computational Diffie–Hellman problem are hard, we formally prove the correctness and security of the ReCIP+ scheme. Furthermore, comparative evaluation demonstrates that the ReCIP+ scheme offers improved security and relatively lower computational costs compared to existing schemes.

This study presents an innovative authentication scheme that integrates Physical Unclonable Functions (PUFs) and Zero-Knowledge Proofs (ZKP) to provide efficient and secure authentication for Internet of Things (IoT) devices. Traditional PUF-based protocols offer strong security but incur high resource costs and slow authentication. To address this, we propose a joint scheme. First, a unified architecture combining a PUF–True Random Number Generator (TRNG) is introduced. This architecture utilizes a feedback permutation obfuscation mechanism and an arbitration delay deviation with a metastable design from a ring oscillator, ensuring the PUF–TRNG system possesses both attack resistance and true random properties. The architecture provides synchronization for both PUF and TRNG in the protocol. Next, we integrate Schnorr’s ZKP with a PUF-based key encapsulation and reconstruction scheme to construct an end-to-end anonymous identity authentication protocol that does not require real-time participation of a trusted third party. The protocol requires only two handshakes, significantly reducing the number of protocol rounds compared to related protocols. Finally, the PUF–TRNG architecture has been implemented on the Xilinx XC7A100T development board. Experimental results show that the PUF circuit effectively resists various modeling attacks. Formal verification with ProVerif demonstrates confidentiality, mutual authentication, and robustness against mainstream attacks. The protocol reduces area overhead and computational time by 43.04% and 42.99%, respectively, compared to similar protocols.

Accurate traffic prediction is crucial for intelligent transportation systems and urban mobility optimization. Despite substantial progress in prior research, existing methods face limitations in capturing detailed spatial-temporal synchronous features and delivering precise predictions in data-deficient regions. To address these challenges, this study introduces transfer learning with spatial-temporal synchronous graph sample and aggregation (TLSTS-GraphSAGE), a novel model designed to enhance predictive accuracy in cross-region traffic forecasting. Specifically, TLSTS-GraphSAGE constructs spatial-temporal synchronous graphs to learn intricate spatial and temporal dependencies. Then, a generative adversarial network (GAN)-based transfer learning mechanism is employed to facilitate prediction in the data-deficient target region by utilizing data from the source region. This mechanism integrates a parameter-shared spatial-temporal synchronous GraphSAGE generator enhanced by attention coefficients for improved feature aggregation and a Wasserstein distance-based similarity discriminator for effective domain alignment. These components enable robust and transferable spatial-temporal representations, ultimately producing accurate forecasts via the prediction layer. Beyond predictive accuracy, the proposed framework also supports intent-driven networking in smart transportation by enabling traffic-aware decision-making and adaptive resource coordination across regions. Extensive experiments are conducted on six cross-region prediction tasks derived from three real-world datasets. Results show that TLSTS-GraphSAGE consistently outperforms state-of-the-art baselines, achieving average improvements of 4.64%, 3.48%, and 5.06% in MAE, MAPE, and RMSE, respectively. These results highlight its potential to address the challenges of heterogeneous and data-limited scenarios while contributing to intelligent and adaptive network management in transportation systems.

ABSTRACT Objective To design a secure Federated Learning (FL) framework for Internet of Medical Things (IoMT) that protects sensitive patient data from both classical and quantum attacks. Methods Proposed the QSFedMA‐IoMT protocol integrating quantum and classical security techniques. Utilized entanglement‐based E91 protocol for generating a highly secure root key to establish trust. Applied BB84 protocol for efficient generation of per‐round session keys during FL updates. Incorporated classical cryptographic scheme AES‐GCM for secure communication. Employed privacy‐enhancing techniques such as norm‐clipping and Gaussian noise to mitigate information leakage during model training. Results Our work demonstrates robust resistance against both classical and quantum adversaries, while enhancing data privacy through secure key distribution and differential privacy mechanisms. It ensures the integrity of model updates within the federated learning process and achieves an effective balance between strong security guarantees and computational efficiency, making it well‐suited for IoMT environments. Conclusion The QSFedMA‐IoMT protocol delivers a robust and practical hybrid framework for securing federated learning in healthcare systems. By integrating E91 and BB84 protocols, it strengthens key management and trust establishment. The combination of quantum security with classical privacy‐preserving techniques ensures resilience, scalability, and efficiency. Overall, this work provides a promising direction for secure and privacy‐aware federated learning in next‐generation IoMT applications.

ABSTRACT Urban transportation systems are essential in fulfilling the requirements of residents while guaranteeing the normal functioning of cities. These systems encompass various modes of transportation, infrastructure, and services that enable people to move within and between urban areas. However, the challenges posed by escalating urbanization, particularly the growing menace of traffic congestion, underscore the pressing need for effective solutions. We propose an Adaptive and Dynamic Spatio‐Temporal Network (ADSTN) as an innovative solution to the complexities associated with traffic congestion. The identified shortcomings in existing models, such as their limitations in capturing authentic spatial dependencies, insufficient understanding of the heterogeneous relationship between the temporal and spatial domains, and the oversight of local trend information, motivate the development of ADSTN. The model integrates three key components: a learnable adaptive attention module, a local temporal self‐attention block, and a spatio‐temporal dynamic graph convolution block. ADSTN stands out for its outstanding performance in handling local spatio‐temporal dependencies, periodicity, and dynamics within traffic flow forecasting. Evaluation on three public real‐world datasets underscores the competitive achievements of ADSTN contrasted with state‐of‐the‐art models, all while maintaining computational efficiency.

The hybrid model combines deep neural networks (DNN) and large AI models, such as large language models (LLM), for enhanced clinical information retrieval (CIR) from electronic clinical records (ECR). While LLMs show promise for encoding complex medical data, they face challenges in user-dependent information, such as patient reports with encoded knowledge, accessing real-time data, and requiring extensive fine-tuning for clinical decision-making in online communication systems. To overcome these limitations, we introduce a Transformer-based Sequence (TBS) multimodal method that integrates representation learning with human expertise to encode and analyze intricate relationships within clinical data. This model improves predictive tasks and medical search accuracy, achieving F1-scores of 0.83-0.80, and outperforms baseline methods. Integrating AI-driven methodologies in healthcare has the potential to transform medical record analysis and utilization, resulting in enhanced patient outcomes and more personalized healthcare solutions.

For integrated sensing and communication (ISAC) systems in complicated propagation scenarios, achieving precise multi-target sensing still faces many challenges. In particular, dynamic target perception is severely affected by clutter generated from static environmental factors, making accurate target distinction difficult. To address this issue, we propose an effective ISAC scheme designed for clutter suppression and efficient multi-target sensing. Unlike conventional methods that depend on prior information and complex computations, the proposed method eliminates long-term dependencies and reduces computational complexity. Specifically, we first construct a hybrid channel model that jointly considers static environments and dynamic targets. Upon receiving the ISAC signal, the base station (BS) estimates the static channel and applies an efficient spatial-domain filter to extract the effective dynamic channel. Subsequently, a reduced-complexity perception algorithm is employed to estimate key parameters, including distance, velocity, and angle. Simulation results demonstrate the feasibility and performance benefits of the proposed method in detecting numerous targets within complex cluttered environments.

Interference cancellation has always been a crucial task in wireless communications, especially in the presence of nonlinear distortions caused by power amplifier. However, when considering the ultra-wideband (UWB) orthogonal frequency division multiplexing (OFDM) systems, this task becomes more challenging as the channel estimation will be severely impacted by the nonlinearity, thus leading to significant performance degradation. Driven by solving this problem, this paper proposed a novel nonlinear signal processing method, referred to as log-sum-minimization sparse channel estimation based nonlinearity cancellation (LSMSCE-NC). In detail, an optimization model based on the log-sum norm minimization and nonlinearity cancellation is first established and then its iterative solution is also presented. The numerical results reveal that the proposed LSMSCE-NC method achieves significant bit error rate (BER) and normalized mean square error (NMSE) advantages compared to the state-of-the-art algorithm.

The rapid proliferation of Internet of Things (IoT) devices has revolutionized various industries by enabling smart grids, smart cities, and other applications that rely on seamless connectivity and real‐time data processing. However, this growth has also introduced significant security challenges due to the scale, heterogeneity, and resource constraints of IoT systems. Traditional intrusion detection systems (IDS) often struggle to address these challenges effectively, as they require centralized data collection and processing, which raises concerns about data privacy, communication overhead, and scalability. To address these issues, this paper investigates the application of federated learning for network intrusion detection in IoT environments. We first evaluate a range of machine learning (ML) and deep learning (DL) models, finding that the random forest model achieves the highest classification accuracy. We then propose a federated learning approach that allows distributed IoT devices to collaboratively train ML models without sharing raw data, thereby preserving privacy and reducing communication costs. Experimental results using the UNSW‐NB15 dataset demonstrate that this approach achieves promising outcomes in the IoT context, with minimal performance degradation compared to centralized learning. Our findings highlight the potential of federated learning as an effective, decentralized solution for network intrusion detection in IoT environments, addressing critical challenges, such as data privacy, heterogeneity, and scalability.

Understanding complex traffic patterns has become more challenging in the context of rapidly growing city road networks, especially with the rise of Internet of Vehicles (IoV) systems that add further dynamics to traffic flow management. This involves understanding spatial relationships and nonlinear temporal associations. Accurately predicting traffic in these scenarios, particularly for long‐term sequences, is challenging due to the complexity of the data involved in smart city contexts. Traditional ways of predicting traffic flow use a single fixed graph structure based on the location. This structure does not consider possible correlations and cannot fully capture long‐term temporal relationships among traffic flow data, making predictions less accurate. We propose a novel traffic prediction framework called Multi‐scale Attention‐Based Spatio‐Temporal Graph Convolution Recurrent Network (MASTGCNet) to address this challenge. MASTGCNet records changing features of space and time by combining gated recurrent units (GRUs) and graph convolution networks (GCNs). Its design incorporates multiscale feature extraction and dual attention mechanisms, effectively capturing informative patterns at different levels of detail. Furthermore, MASTGCNet employs a resource allocation strategy within edge computing to reduce energy usage during prediction. The attention mechanism helps quickly decide which services are most important. Using this information, smart cities can assign tasks and allocate resources based on priority to ensure high‐quality service. We have tested this method on two different real‐world datasets and found that MASTGCNet predicts significantly better than other methods. This shows that MASTGCNet is a step forward in traffic prediction.

With the rapid advancement of unmanned aerial vehicle (UAV) technology, its high mobility and ease of deployment have demonstrated tremendous potential in integrated sensing and communication (ISAC) systems. However, as user demands diversify, network architectures become increasingly distributed, and as the number of UAVs grows rapidly, ISAC systems face significant challenges in optimizing communication and sensing resources. In particular, UAV communication in collaborative UAV missions is highly susceptible to hostile signal disruptions, leading to degraded communication quality, weakened sensing performance, resource wastage, and increased energy consumption. To address these challenges, this paper proposes a game-theoretic optimization method for multi-UAV ISAC networks. First, a multi-UAV communication-sensing network model is constructed to characterize the impact of interference sources on communication and sensing performance. Based on this model, under energy constraints, a joint optimization of transmission power and UAV trajectory is performed. The problem is formulated as a utility maximization framework for the ISAC network and modeled as a game-theoretic approach. The proposed model is rigorously proven to be an exact potential game, ensuring the existence of at least one pure-strategy Nash equilibrium. To solve for the equilibrium, a distributed optimization algorithm—the electric eel foraging optimization (EEFO) algorithm is developed. Simulation results validate the effectiveness of the proposed method, showing that it significantly enhances the communication and sensing performance of multi-UAV networks while effectively reducing energy consumption. This work provides a novel solution to the resource optimization challenges in multi-UAV ISAC networks, offering both theoretical and practical contributions to advance ISAC technology.

Spectrum management for the coexistence of multiple unmanned aerial vehicle (UAV) networks is a challenging issue, considering both space and frequency reuse. To address this issue, we propose a joint bandwidth and spectrum usage zone (SUZ) flexible allocation scheme, leveraging interference graph. We formulate a joint spectrum bandwidth allocation and SUZs adjustment problem to maximize the system utility, which is a binary nonlinear programming (BNLP) problem. Then we decompose it into two subproblems: the high-priority UAV networks subproblem and the low-priority UAV networks subproblem. The high-priority subproblem is solved using a graph coloring method based on the interference graph, whereas the low-priority subproblem is addressed through a sequential one-step block coordinate descent (SOBCD) approach by constructing a spectrum assignment hypergraph. Simulation results demonstrate that the total utility with the proposed scheme outperforms benchmark schemes, and there exists an optimal SUZ grid adjustment to maximize the total utility.

With the increasing demand of consumers for food safety, the application of Internet of Things (IoT) in agriculture is more and more extensive, especially the use of technologies such as QR codes and sensors for food information traceability. However, the Internet of Things still faces challenges in ensuring the authenticity of food data transmission and the integrity of food anti-counterfeiting authentication, especially the traditional digital signature algorithm that the Internet of Things relies on is vulnerable to the security threat brought by future quantum computers. In order to solve this problem, we propose a domestic replacement solution for the post-quantum digital signature algorithm SPHINCS-α(an improvement of the standardized post-quantum digital signature scheme SPHINCS+), and use the chinese national standard cryptographic hash function Shang Mi 3 (SM3) to replace its underlying hash function. Finally, we conducted experiments, gave the benchmark test results under three security parameters, and compared the performance with the original scheme using SHA256 and Shake256 hash function. The results prove the feasibility of our method, although there is a small rate drop, but in exchange for a more secure domestic hash function. It provides strong support for the early deployment of post-quantum cryptography algorithm in the Internet of Things environment of sustainable agriculture and industry, and ensures the integrity of the Internet of Things data in the practice of sustainable agriculture.

Along with the development of Internet of Things systems, numerous edge intelligent devices can obtain a large amount of user data, and the analysis of this user data can be applied to business scenarios, such as user click-through rate (CTR) prediction. In the recommendation, advertising and other scenarios, the users at the edge have high response requirements for CTR prediction model training and inference. In the current edge scenario of CTR prediction, there are problems of overly complex model structure and highly sparse original features, which makes it difficult to deploy CTR prediction models at the edge. Therefore, we propose KD-based graph attention FI model (KD-GAFIM), a lightweight recommendation algorithm that combines graph neural networks (GNNs) with knowledge distillation (KD). The approach uses graph attention networks to flexibly capture feature dependencies in a way that maintains a small model size while augmenting the feature vector with feature dependencies. And by sharing the embedding layer of the teacher model, KD-GAFIM improves the efficiency of user CTR prediction. On top of that, we also propose a feature compression strategy guided by model interpretability, which identifies high-contributing features for inference and model refinement based on their performance in model interpretability. This strategy improves efficiency, making KD-GAFIM suitable for training and inference on edge devices. We conducted extensive experiments on multiple datasets. The experimental results show that KD-GAFIM outperforms various state-of-the-art CTR prediction models, demonstrating that GNN-based KD models can improve model performance while reducing model size and feature dimensionality, and have significant potential for application at the edge.

ABSTRACT Introduction With the development and integration of satellite and terrestrial networks, mobile traffic prediction has become more important than before, which is the basis for service provision and resource scheduling when supporting various vertical applications. However, existing traffic prediction methods, especially deep learning‐based methods, require massive data for model training. Due to data privacy concerns, mobile traffic data are not easily shared among different parties, making it difficult to obtain a precise prediction model. Methods To mitigate the data leakage risk, a federated learning framework is proposed in this study for mobile traffic prediction in satellite‐terrestrial integrated networks to achieve a tradeoff between data privacy and prediction accuracy. In the proposed framework, local models are trained in base stations on the ground, and a global model is aggregated in the satellite edge server in space. Results A deep learning‐based prediction model with an adaptive graph convolutional network (AGCN) and long short‐term memory (LSTM) modules is proposed and validated in numerical experiments, which achieves the lowest prediction error with a real‐world traffic dataset when compared with other graph neural network (GNN) variants in the federated learning setting. Conclusion Numerical experiments with a real‐world mobile traffic dataset demonstrate the effectiveness of the proposed approach, which outperforms other GNN variants with lower prediction errors.

The rapid expansion of satellite mega-constellations has highlighted the potential of satellite edge computing as a promising solution for mobile multimedia communications. While reinforcement learning has been explored in satellite communication systems, significant challenges remain, including high latency and limited resources. This study addresses these challenges by focusing on the joint optimization of communication, computing, and caching resources in satellite edge computing to support mobile multimedia applications. A mixed-integer nonlinear programming (MINLP) problem is formulated with the objective of minimizing the total delay experienced by mobile users, subject to multidimensional resource capacity constraints, which are NP-hard and computationally intractable to solve in polynomial time. To address this complexity, we propose a multi-agent federated reinforcement learning (MAFRL) approach as an efficient solution. In this framework, each satellite operates as an autonomous learning agent equipped with an actor-critic network structure. The proposed MAFRL method demonstrates superior performance, achieving lower delays compared to all baseline approaches. It effectively optimizes delay-sensitive mobile multimedia communications by minimizing total delay and improving task-offloading ratios. To the best of the authors’ knowledge, this study is the first to introduce an MAFRL-based approach for resource allocation in satellite edge computing, marking a significant contribution to the field.

Satellite-terrestrial integrated networks (STINs) have been recognized as an important key technology for future 6G networks. With the introduction of large-scale satellite constellations, traditional network management schemes cannot fully meet the requirements for network operation and software defined networking (SDN) is introduced as a promising tool. However, existing network simulators fail to meet the simulation purposes for software-defined STINs and we aim to fill this research gap by implementing a network simulation framework with open-source simulation platforms including Geomview, SaVi and Mininet.

With the increase in satellite meg-constellations, network management has become increasingly complex, and the software-defined network idea has been introduced into modern satellite networks. This study considers the multi-controller placement problem in software-defined satellite networks and decomposes the problem into two sub-problems: SDN controller placement and switch-controller assignment. A meta-heuristic approach based on AVOA is proposed to solve the two sub-problems step-by-step, with the optimization objective of network reliability maximization, which has often been neglected in previous studies. Numerical experiments demonstrate that the AVOA-based solution outperforms baselines based on the NSGA-II and particle swarm optimization algorithms in terms of control delay, load-balancing capability, and reliability.

The wine industry has a significant socioeconomic impact. Recent advancements in smart agriculture have greatly influenced vine growth and wine-making processes. In this study, we evaluate wine ratings by relating them to multiple wine characteristics. A novel dataset with various features is curated, and an interpretable learning paradigm is proposed. Several different learning models are employed, leading to promising experimental results. Furthermore, through feature contribution analysis, we discover that climate-related factors have become less influential on wine ratings in recent years, highlighting the effectiveness of recent advancements in smart agriculture.

Internet of Things (IoT) is an important infrastructure for supporting vertical applications. However, existing IoT systems are still facing some challenges, e.g., lack of coverage in rural areas and lack of efficient data collection methods. To overcome these challenges, a satellite IoT framework is proposed in this study as a promising solution, and smart agriculture is used as a typical application scenario. A satellite edge computing workflow is further proposed, with computer vision as a case study. In the case study, a lightweight deep learning model named MobileViT is proven effective for aphid detection and infestation severity classification on lemon leaves.

Drought has been a global concern and an effective prediction method is needed. Meteorological data are seen as an efficient and economic approach. Challenges arise with the large volume and high nonlinearity between meteorological variables and the drought level. In this study, deep learning is proposed as an effective solution for drought level prediction as multivariate time series classification. The synthetic minority oversampling technique is further adopted to alleviate the class imbalance problem and improve the classification performance. Experimental results on an open dataset named DroughtED demonstrate the effectiveness of the proposed deep learning method.

Network slicing is one the key features of software-defined networks (SDNs) and can be used in next-generation communication networks. Admission control of network slices is the basis of providing the heterogeneous quality-of-service performance guarantee and maximizing the optimization objectives of the network operator. Various admission control mechanisms have been proposed in the literature, including those based on traffic forecasting. However, recurrent neural network-based probabilistic forecasting models have not been given thorough consideration for slice admission control. In this study, the network slicing scheme design problem is formulated mathematically, with an equivalent formulation of the constrained bandwidth-sharing scheme. Then, a DeepAR-based slice admission control mechanism is proposed for sequential decision making for network slice requests in SDN, with the support of the SDN controller. An improved variant is further proposed with a closed-loop parameter update mechanism. The experiments based on real-world historical traffic data validate the effectiveness of the proposed mechanisms, with metrics, including revenue, resource reservation and utilization ratios, and service admission ratio.

As an alternative to traditional meteorological methods, rain attenuation in satellite-to-Earth microwave communication signals has been used for rainfall reconstruction in recent years. In this article, the existing 2-D rain field reconstruction problem is extended to a 3-D scenario by leveraging the low Earth orbit satellite system. A compressive sensing approach is further proposed to solve the 3-D rain field reconstruction problem. The Starlink system is used as a reference, and two synthetic rain events near the Great Barrier Reef in Australia, which are generated from the weather research and forecasting model, are used to evaluate the reconstruction performance. Simulation results show that the compressive sensing approach performs better than both the traditional least squares and the least absolute shrinkage and selection operator approaches.

In this study, we propose a crowd sensing framework with the existence of execution uncertainty and a given budget. Our framework consists of three stages: Task Selection, Task Allocation, and Payment. Within each stage, we define the design problems and give a preliminary solution with desirable theoretic properties.

The Chinese Spring Festival travel season (Chunyun) has been called the largest annual human migration in the world with approximately 3.6 billion trips in 2014. Understandably, all forms of transportation are stressed at or near saturation during this period and many people, especially lower-income individuals fail to get to their destinations. We present CountryRoads, a ridesharing system to address the transportation shortage during Chunyun. The CountryRoads system collects users' route information, and matches drivers and passengers as an online bipartite matching problem based on the proximity of the passenger's origin and destination and the route of the driver. The system is evaluated during four Chunyun periods from 2012 to 2015 with up to 17272 users and forms 4777 ridesharing tuples in 2015.