Transactions on Emerging Telecommunications Technologies最新文献

Nowadays, this society relies more and more on large-scale intelligent networking to operate the desired functions, which leads to a great and tremendous amount of Internet traffic, particularly at peak time. Such exponential traffic increase has caused a great challenge to network infrastructure, which in turn reflects the importance of network traffic prediction. Reliable traffic prediction can help the Internet service provider to manage their resource efficiently, so as to guarantee the service quality even at high demand and prevent the network congestion from happening. However, with the access to a tremendous smart devices, the corresponding traffic grows exponentially. In this way, it becomes vitally important to accurately capture and predict such traffic status. Traditional prediction models are usually applied to short-term prediction scenarios, which are not suitable for real-world scenarios, because the traffic is more complex. On the other hand, deep learning has been frequently used for network prediction due to its non-linear modeling capability. Nevertheless, these methods may encounter trouble when dealing with the problems related to the long dependence relationship and dynamic space relevance among traffic data with a large amount of data. To address these challenges well, we propose a novel prediction architecture using the transformer structure. It takes the time and space factors into consideration when fulfilling traffic prediction. Specifically, on one hand, we separate the input sequence along the timeline, so as to better capture the dynamic space relevance to traffic. For each part of the captured sequence, we build the sub-model for relevance modeling. Then, with these discrete traffic models with time and space features, we introduce the multi-head attention mechanism to integrate them, so as to finally build the perfect relevance matching among the local and global traffic space. Our experiments indicate that the proposed transformer-based architecture implement a highly accurate traffic prediction model while reducing the training time. Compared to the state-of-the-art methods, the proposed one achieves high performance in terms of the mean absolute error, root mean square error, R-squared, and efficiency in training time.

The Space–Air–Ground Integrated Network (SAGIN) enables seamless connectivity across satellite, aerial, and terrestrial nodes. However, its heterogeneous architecture, resource-constrained nodes, and dynamic link conditions pose significant challenges for deploying deep learning models-particularly for detecting AI-generated artistic content. These challenges include limited on-board computational capacity, fluctuating bandwidth, and the requirement for fine-grained visual-semantic reasoning under weak supervision. To overcome these limitations, we propose the Weakly-Aligned Region-Language Transformer (WARL-Transformer), a novel framework designed for robust AI-generated content detection under realistic SAGIN constraints. WARL-Transformer incorporates: (1) A vision-language alignment mechanism that integrates local visual features with high-level semantic cues derived from textual descriptions, and (2) a weakly supervised local feature alignment strategy that learns region-language correspondences without relying on costly fine-grained annotations. Laboratory-based SAGIN emulation experiments further verify that WARL-Transformer maintains high detection accuracy across diverse artistic styles while preserving robustness against network interference. In particular, WARL-Transformer achieves an F1-score of 96.78%, outperforming the baseline by +0.63 percentage points, and even under bandwidth-constrained SAGIN emulation still reaches 99.7% of the full-model F1, demonstrating strong robustness. This work establishes a foundation for reliable AI-generated content detection in resource-limited SAGIN settings, bridging the gap between visual content authentication and practical network-driven constraints.

Internet of Vehicles (IoV) networks face significant security and privacy challenges due to dynamic topologies and high mobility, exposing them to threats like unauthorized tracking and data tampering. This study aims to develop a robust, privacy-preserving authentication protocol for IoV using blockchain technology. We propose a novel approach integrating a Cascaded and Dilated Residual Recurrent Neural Network (CD-RRNN) for malicious attack detection, blockchain for secure data storage, and an Optimized Key in El-Gamal Encryption (OKEE) with keys selected via Modified Manta-Ray Foraging Optimization (MMRFO). Results demonstrate a 94.34% accuracy in attack detection and a 28.57% reduction in decryption time compared with baselines, validated against state-of-the-art methods. This protocol enhances IoV security, privacy, and scalability, offering a practical solution for smart transportation systems. The rapid expansion of the IoV has introduced significant challenges related to security, privacy, and efficient data management. Traditional centralized architectures struggle with scalability and vulnerability to cyber threats. This article proposes a blockchain-based security framework to enhance trust, authentication, and data integrity in IoV networks. The proposed model leverages Cascaded and Dilated Residual Recurrent Neural Network (CD-RRNN) for detecting malicious activities, coupled with El-Gamal encryption optimized using the Modified Manta-Ray Foraging Optimization (MMRFO) algorithm for secure communication. The system effectively balances privacy and traceability in vehicular networks. Performance evaluations demonstrate improved attack detection accuracy, reduced computational overhead, and higher efficiency compared with existing methods. The proposed solution ensures a decentralized, scalable, and robust security model, making it a viable framework for next-generation IoV ecosystems.

Future network technology provides a new stage for industrial production systems, especially smart manufacturing system (SMS), which is a fully integrated and collaborative factory platform that responds in real time to meet changing demands and conditions in the factory. In this paper, we propose a new spectrum allocation scheme for the macro/small cell overlaid SMS. To improve the communication performance, we develop a new solution concept, called the multi-criteria bargaining solution (MCBS), according to the combination of multi-criteria decision strategy and cooperative bargaining ideas. Through an interactive two-step manner, the main feature of MCBS is to harness the full synergy of heterogeneous cell coexisting infrastructure while maximizing mutual advantages in the two-tier cellular network. In an indoor smart factory environment, our hierarchical approach can effectively handle the multi-agent multi-criteria resource sharing problem. Finally, the extensive simulation results are presented to illustrate the potential advantages of our spectrum sharing policy. Especially, our proposed approach increases the network throughput, service payoff, and operator fairness by about 10%, 10%, and 20%, respectively, than the existing baseline protocols.

This paper introduces an AI-driven soccer training optimization method based on the space–air–ground integrated network, named SAGIN-Play, which integrates real-time multimodal data from ground sensors, aerial surveillance (drones), and cloud-based processing. The system is designed to optimize player performance, enhance tactical positioning, and provide real-time feedback during soccer training and matches. By leveraging wearable motion sensors, drone-based aerial surveillance, and cloud computing, the method enables precise tracking of player actions and interactions, facilitating personalized performance improvements. This paper evaluates the proposed method across various datasets, including SoccerNet, Kaggle Football, UCF101 Sports, and the player event system (PES), highlighting the effectiveness of SAGIN-Play in action recognition, tactical positioning, and real-time feedback precision. The method outperforms traditional techniques, such as object detection models, multi-object tracking, and reinforcement learning (RL), in key metrics, demonstrating its potential in dynamic soccer training environments. Additionally, an ablation study reveals the critical contributions of each SAGIN-Play component, particularly aerial surveillance and cloud-based processing, in optimizing player positioning and tactical execution. The study further demonstrates the system's ability to improve player performance through personalized feedback, showing significant progress in key skill areas like passing, shooting, and defense. Simulated live training sessions demonstrate substantial improvement in coordination, decision-making, and overall performance. The results underscore the importance of integrating multilayered data for real-time tactical adjustments in soccer training. Experimental results show that SAGIN-Play achieves 94.2% action recognition accuracy on SoccerNet and 92.8% tactical positioning accuracy on Kaggle Football, while reducing the average feedback latency from 650 ms to 240 ms compared with baseline models.

Industrial countries are moving toward digitizing the manufacturing processes in their factories by integrating the expected next-generation technologies such as software-defined networking (SDN), cloud computing, and industrial Internet-of-Things (IIoT). However, developing smart factories that combine these physical and cyber components faces critical challenges, particularly regarding the efficiency and security domains. For example, Distributed Denial of Service (DDoS) attacks in industrial environments could impact the progress of the automated processes and the availability of SDN-based networks. In this paper, we present a novel collaborative intrusion detection system (CIDS) approach for SDN-based industrial environments that integrates edge computing techniques to enhance security and operational efficiency. Our model optimizes resource utilization across dispersed industrial sites by uniquely combining three different IDSs: centralized-based IDS, edge-based Anomaly IDS (AIDS), and signature-based IDS (SIDS). The proposed approach establishes consistent, network-wide security policies to accommodate the varying processing capabilities. Moreover, the use of edge computing techniques minimizes the overhead introduced by the SDN controller located in the cloud layer and addresses scalability challenges in large-scale networks with heavy traffic loads. Evaluation is performed using the Mininet emulator, and the results reveal a detection accuracy of up to 98%. Furthermore, profiling outcomes of the centralized controller indicate a 50% reduction in traffic monitoring function calls, highlighting the efficiency and superiority of the proposed methodology, particularly for geographically dispersed industrial sites.

Vehicular ad hoc networks (VANETs) enable the exchange of safety-critical messages, but their open and dynamic nature makes them vulnerable to message falsification and denial-of-service attacks. Federated learning (FL) offers a distributed defense mechanism, yet conventional approaches such as FedAvg degrade severely under non-IID client data and are highly sensitive to adversarial updates. To address these limitations, we propose FedCross-VAN, a novel FL framework that incorporates cross-domain behavioral priors with a similarity-weighted aggregation scheme. On the client side, FedCross-VAN employs a dual-objective loss that balances anomaly classification with alignment to external priors, improving generalization under heterogeneous data. On the server side, updates are aggregated proportionally to their embedding similarity with the priors, suppressing the influence of poisoned or noisy clients. Experiments on two benchmark datasets show that FedCross-VAN achieves up to approximately 2%–4% higher accuracy on HAR and 13% on KWS, converges in fewer rounds, and exhibits stronger robustness than FedAvg and No-Transfer FL. These findings establish FedCross-VAN as a practical and resilient framework for anomaly detection in next-generation intelligent transportation systems.

This paper presents a novel basketball shooting performance optimization method that integrates deep pose estimation with a Space-Air-Ground Integrated Network (SAGIN)-enabled feedback mechanism. The core idea is to leverage advanced 3D human pose estimation techniques to capture the fine-grained body kinematics during shooting, decompose these movements into interpretable motion phases, and utilize SAGIN to provide ultra-low-latency corrective feedback. Compared to existing methods that either focus solely on biomechanical analysis or network-based performance enhancement, our framework establishes a closed-loop system capable of real-time analysis, correction, and adaptive learning. The proposed method is composed of four key components: (A) a deep pose estimation module that accurately reconstructs 3D body joints, (B) a phase-wise motion decomposition mechanism tailored to basketball shooting, (C) a SAGIN-based feedback pipeline that ensures low-latency information delivery, and (D) a unified learning objective that simultaneously optimizes pose estimation accuracy and shooting biomechanics. Experimental results demonstrate that the proposed system significantly outperforms existing methods, achieving 25.4 mm MPJPE (15%–40% reduction compared to baseline methods), 90.4% shooting accuracy (12%–18% improvement over existing systems), and 38 ms feedback latency (63% reduction compared to ground-based systems), offering a promising direction for intelligent sports training.

Fall Detection Systems (FDS) are an integral part in many Ambient Assisted Living (AAL) systems for ensuring the safety of senior citizens, especially in the underserved, isolated, and remote areas where there is unavailability of conventional communication systems. The conventional FDS systems mainly rely on cameras and wearable devices that impose significant challenges like privacy and acceptability. This paper presents a non-invasive and non-intrusive FDS leveraging ultrasonic sensors for fall detection, mitigating the challenges posed by camera systems and wearable devices, resulting into privacy preserving human fall detection. We propose a hybrid deep learning fusion approach that fuses Recurrent Neural Networks (RNN), Long Short Term Memory (LSTM), and Bi-directional LSTM (BLSTM), which achieves an accuracy of 98.14% for fall detection from time-series data. The main motivation of this study is to integrate our Fall detection system with the Space-Air-Ground-Integrated Network (SAGIN) framework to facilitate real-time alerts and emergency responses in the remote and isolated areas affected by unreliable communication systems. The integration of the FDS with the SAGIN framework presents a multi-tier processing at three levels, including Ground, Air, and Space. At the Ground level, the edge devices at the local site facilitate initial fall detection with lower latency. At the Air level, the aerial platforms like drones present an extended coverage range and facilitate data relay. And at the Space level, the satellites facilitate global connectivity, data analysis, and management for a longer course of time. Thus, the SAGIN integration with FDS systems ensures precise and real-time fall detection in remote and isolated areas, guaranteeing the availability of the communication networks. The proposed approach reduces the latency with the help of edge computing and showcases a resilient and scalable architecture for emergency response and health monitoring.

Quick Service Laboratories (QSL) provide the necessary diagnostic services that have to be performed within limited time frames and rely on coordinated solutions across its supply chain to operate successfully. The application of standard supply chain management approaches often fails to recognize the variable and unpredictable nature of QSL operations, which significantly contributes to stockouts, delays, or surplus inventory. This study looks into a different approach to the traditional methodologies of supply chain management by investigating the means when machine learning algorithms with the purpose of discovering anomalous behavior patterns are applied to QSL supply chain practices and generate value. In examining and evaluating the historical demand forecasting patterns, inventory levels, and operational performance metrics will be more easily identifiable as anomalous behaviors or dissenting levels such as demand spikes, unanticipated inventory shortfall levels, and atypical arrival patterns of inventory to generate disruption to laboratory operations. Machine learning models can be supervised or unsupervised to learn normal operation behaviors, and even detect anomalies in real time through model training. These models facilitate proactive interventions that would improve inventory management and distribution planning, as well as service delivery in general. When building on the results of our detection modeling, we found that machine learning anomaly detection could provide actionable suggestions and improved supply chain resiliency, and reduce stockouts and excess inventory, all while maintaining more controlled service levels. Our comparative evaluation of conventional monitoring and forecasting methods demonstrates superior capabilities over traditional methods in our results, by resorting to fully utilizing the complexity of simple linear and rare events found in QSL supply chains and their digital transformation story.