Transactions on Emerging Telecommunications Technologies最新文献

{"title":"Blockchain-Powered IoT Healthcare Framework With Dandelion Depthwise Separable Convolutional Neural Network for Enhanced Security","authors":"Harish Kumar Taluja,&nbsp;Anuradha Taluja,&nbsp;D. Bhuvana Suganthi,&nbsp;L. Guganathan","doi":"10.1002/ett.70396","DOIUrl":"https://doi.org/10.1002/ett.70396","url":null,"abstract":"<div>\u0000 \u0000 <p>Technological trends are evolving fairly quickly within healthcare systems with blockchain and Deep Learning Hybrid technologies seen as at the pinnacle of making patient care, scalability and security better. Indeed, challenges such as Interoperability, privacy, and data integrity are some of the challenges that normal healthcare systems face, especially in the IoT paradigm. Worse still, secure and decentralized management of data is what is needed. Using a combination of deep learning architectures for IoT security and scalability, as well as data protection through blockchain technology, this study aims at designing a new secure healthcare system that can be implemented using the IoT network. In the present work, a Triple Attention Depthwise Separable Convolutional Neural Network (TADSCNN) is designed with the help of Dandelion Optimizer (DO) incorporated with blockchain. Thus, the proposed system achieved F1-score of 0.993, accuracy of 0.999, precision of 0.992, and recall of 0.994, which means that the system's performance is quite high. Furthermore, it supports 220 kbps of throughput and 85 s latency, and 2.9 s processing time for the protocol while providing data secrecy of 99.12%. This framework offers a viable, scalable, and secure means of addressing Internet of Things health care system.</p>\u0000 </div>","PeriodicalId":23282,"journal":{"name":"Transactions on Emerging Telecommunications Technologies","volume":"37 4","pages":""},"PeriodicalIF":2.5,"publicationDate":"2026-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147568192","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Spatiotemporal Graph Neural Network-Driven Anomaly Detection for Cooperative Vehicle Messaging in Dense VANET Corridors","authors":"Ahmed Zohair Ibrahim","doi":"10.1002/ett.70405","DOIUrl":"https://doi.org/10.1002/ett.70405","url":null,"abstract":"<div>\u0000 \u0000 <p>Cooperative messaging in vehicular ad-hoc networks (VANETs) enables safety-critical functions such as collision avoidance, platooning, and traffic optimization. However, in dense urban traffic environments, rapidly changing topology and high-volume broadcast messaging introduce vulnerabilities to spoofing, flooding, and falsified data injection. Traditional anomaly detection approaches, including basic machine learning or static rule-driven models, are insufficient to capture the evolving spatial–temporal dependencies and message correlations inherent to mobile vehicular ecosystems. To overcome these limitations, this paper introduces graph neural network–enabled adaptive resilient intelligence for spatiotemporal event detection (GNN-ARISE). A novel anomaly detection architecture integrating GNN-based reasoning with traffic-aware message intelligence. GNN-ARISE comprises: (1) a Dynamic GNN Graph Constructor, continuously reshaping communication graphs using mobility signatures and message trust indices. (2) a Temporal Evolution Encoder, leveraging gated recurrent attention to model message propagation patterns over time. (3) a Resilient Anomaly Classifier, fusing graph embeddings and vehicle trust scoring for robust detection under real-time constraints. Evaluation using dense VANET simulation datasets demonstrates that GNN-ARISE improves detection accuracy by 21.2%, reduces false-positive rates by 23.5%, and maintains processing latencies under 22 ms, outperforming baseline GNN and spatiotemporal learning models. The results highlight the value of integrating GNN-based adaptive reasoning for securing next-generation intelligent transportation communication infrastructures. The proposed method achieves the anomaly detection accuracy (86%–96%), FPR (6%–11%), detection latency of 45% and 125 ms, robustness under high node (82%–90%), attack type generalization capability (83%–87%).</p>\u0000 </div>","PeriodicalId":23282,"journal":{"name":"Transactions on Emerging Telecommunications Technologies","volume":"37 4","pages":""},"PeriodicalIF":2.5,"publicationDate":"2026-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147568182","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Trust-Centric Federated Edge Learning Paradigm in Healthcare for Decentralized Threat Intelligence Sharing","authors":"Syed Thouheed Ahmed,&nbsp;Afifa Salsabil Fathima,&nbsp;Marwah A. Halwani,&nbsp;Ahlam Almusharraf,&nbsp;Abdullah Albuali","doi":"10.1002/ett.70401","DOIUrl":"https://doi.org/10.1002/ett.70401","url":null,"abstract":"<div>\u0000 \u0000 <p>Growing adoption of consumer applications powered by edge intelligence and federated learning (FL) enables real-time personalization and rapid cyber response. The conventional FL remains vulnerable to adversarial attacks and lacks secure mechanism for collaborative intelligence sharing. To address this, the blockchain-enhanced FL framework that integrates decentralized model training with blockchain based threat intelligence exchange is proposed. Edge (IoT) devices collaboratively train lightweight FL models for localized detection, while blockchain ensure secure validation and dissemination on updates. A dynamic trust scoring system identifies and penalizes the malicious participants, thereby improving model reliability and resilience. Experimental results demonstrate that the proposed system has secured an accuracy of 92.8%, reduces communication overhead by 35% and maintain stable convergence across heterogeneous edge-IoT environments.</p>\u0000 </div>","PeriodicalId":23282,"journal":{"name":"Transactions on Emerging Telecommunications Technologies","volume":"37 4","pages":""},"PeriodicalIF":2.5,"publicationDate":"2026-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147567528","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Federated Security Framework: A Heterogeneous Federated Learning Architecture for Privacy-Preserving Intrusion Detection in IoT Networks","authors":"Umar Islam,&nbsp;Fakhrud Din,&nbsp;Anwar Ul Haq,&nbsp;Inayat Ali","doi":"10.1002/ett.70402","DOIUrl":"https://doi.org/10.1002/ett.70402","url":null,"abstract":"<div>\u0000 \u0000 <p>Internet of things (IoT) applications are growing at an accelerating pace in the various infrastructures of critical systems, with cyber threats growing as well, making intrusion detection systems (IDS) significant. Some reflections of the traditional centralized IDS systems include privacy of data, lag time and low scalability of distributed networks. In this paper, a new framework federated security framework (FSF), a fresh model of federated learning, is introduced, which is an intrusion detector that integrates local ensemble learning and global feature extraction to improve the security of the network. The FSF uses the models of the random forest and XGBoost to issue local decisions concerning the IoT devices, whereas global 1D-CNN carries out the extracting of the features centrally without jeopardizing the privacy of the information. Much of the literature on studying three benchmark datasets underpins the fact that XGBoost has an immensely high performance with an accuracy of 98.09% on NSL-KDD, 97.94% on TON-IoT, and 96.15% on CICEVSE2024. The architecture saved the communication overhead that was 67.3% of centralized methods and enhanced the computing performance by 89.2%. The performance of model distillation methods proved the accuracy of 95.65% and complexity reduction of 78%; this means that the paradigm has potential applications in supporting resource-limited IoT applications. It is a federated solution which offers privative-aware intrusion diagnosis solutions which are required in the contemporary distributed network infrastructure.</p>\u0000 </div>","PeriodicalId":23282,"journal":{"name":"Transactions on Emerging Telecommunications Technologies","volume":"37 4","pages":""},"PeriodicalIF":2.5,"publicationDate":"2026-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147566393","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Spatial–Temporal Graph Learning for Taxi Origin–Destination Demand Prediction","authors":"Mingxia Huang,&nbsp;Bingyan Zheng,&nbsp;Dan Peng","doi":"10.1002/ett.70393","DOIUrl":"https://doi.org/10.1002/ett.70393","url":null,"abstract":"<p>Accurate prediction of taxi origin–destination demand contributes to optimizing operational management, relieving traffic congestion, and improving the transportation capacity of urban road networks. To address the challenges of origin–destination semantic differentiation and data sparsity in taxi origin–destination demand prediction, we propose a multilevel continuous - time dynamic node - based attention network model (MCNAT). In the spatial–temporal graph construction unit, this model utilizes a dual-strategy meta-path random walk to achieve semantic differentiation and an attenuation function to update node representation. In the spatial–temporal correlation unit, this model employs multilevel spatiotemporal perception layers based on multi-head attention mechanisms to aggregate local spaces and share parameter space. To mitigate the effects of data sparsity, L-sparse is introduced in the prediction states to make the model more focused on edges with lower travel demand. We conducted simulations using two real datasets and compared MCNAT with other baselines. The results show that MCNAT outperforms the base model in all metrics, with MAE and RMSE improved by 11.11% and 11.87% compared to the optimal model, and the <i>F</i>1 score metrics are above 0.69, which is improved by 11.1%.</p>","PeriodicalId":23282,"journal":{"name":"Transactions on Emerging Telecommunications Technologies","volume":"37 4","pages":""},"PeriodicalIF":2.5,"publicationDate":"2026-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ett.70393","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147566037","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"AI Driven VANET Assisted Prediction and Anomaly Detection in Active Suspension Systems: Modeling and Performance Analysis","authors":"Fengkai Guo,&nbsp;Caiyun Duan","doi":"10.1002/ett.70385","DOIUrl":"https://doi.org/10.1002/ett.70385","url":null,"abstract":"<div>\u0000 \u0000 <p>Active suspension systems provide ride comfort and vehicle stability under dynamically altering road conditions, but onboard-only control designs are sensitive to mechanical defects, anomalous vibrations, and external disturbances. This paper suggests an AI-driven, VANET-assisted architecture for real-time active suspension system prediction and anomaly detection. It uses deep learning–based anomaly detection and machine learning prediction models to monitor suspension dynamics and detect early departures from normal operational behavior. VANET-enabled cooperative vehicle-to-vehicle and vehicle-to-infrastructure communication improves situational awareness by exchanging suspension and road-state information. A dynamic simulation environment simulates road disruptions and communication situations during framework evaluation. Performance results show 95% anomaly detection accuracy, 26% false-positive/false-negative rate, 92% communication reliability, 0.2 m/s² RMS body acceleration for ride comfort, and 1 s suspension settling time, surpassing onboard-only systems. We found that cooperative AI-VANET integration enables predictive maintenance and intelligent suspension control for next-generation connected and autonomous automobiles. Detection accuracy, false-positive/false-negative rates, communication reliability, RMS body acceleration, and settling time are computed by comparing predicted suspension states and detected anomalies against ground-truth fault injections within the simulation. This comparative setup ensures that the reported improvements arise from the integration of AI-driven anomaly prediction and cooperative VANET communication, with all results reflecting repeatable simulation outcomes under consistent baseline conditions.</p>\u0000 </div>","PeriodicalId":23282,"journal":{"name":"Transactions on Emerging Telecommunications Technologies","volume":"37 4","pages":""},"PeriodicalIF":2.5,"publicationDate":"2026-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147566192","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Lightweight Multi-Hop Clustering With Cross-Layer Intelligence for VANET Malicious Behavior Detection","authors":"Hana Almagrabi,&nbsp;Hend Khalid Alkahtani,&nbsp;Lyan Alwakeel,&nbsp;Mohammed Maray,&nbsp;Haidar Almubarak,&nbsp;Nadiyah Almutairi,&nbsp;Haitham Assiri,&nbsp;Shouki A. Ebad","doi":"10.1002/ett.70397","DOIUrl":"https://doi.org/10.1002/ett.70397","url":null,"abstract":"<div>\u0000 \u0000 <p>Future vehicular ad hoc networks (VANETs) require fast, secure communication to support road-safety applications. However, high vehicle congestion, sudden link failures, and malicious behaviors make it difficult to maintain stable communication. To accurately detect and mitigate such attacks and failures, several security and coordination strategies are established. Specifically, clustering groups of vehicles enhances coordination and attack detection. However, existing clustering models often fail to deliver the expected results in behavioral analysis due to sudden cluster breakdowns, high communication overhead, and poor coordination. To address these challenges, we propose a Lightweight Multi-Hop Clustering framework with Cross-Layer Intelligence (LMHC-CI) for real-time malicious detection in VANETs. The study aims to enhance cluster stability and detection accuracy while maintaining low computational and communication costs. The suggested research also leverages cross-layer intelligence to enable efficient clustering and detection decisions. The model is simulated using two publicly available datasets: The Vehicular Clustering Dataset and the VANET Malicious Node Dataset. Simulation results indicate that the proposed model achieves 99.6% detection accuracy. The adaptive H-node remains within 0.15–0.35 and reduces unnecessary role changes after convergence. Also, multi-hop aggregation reduces EPC packet overhead as hop count increases. This will reduce cluster reformation and routing complexity compared to existing methods.</p>\u0000 </div>","PeriodicalId":23282,"journal":{"name":"Transactions on Emerging Telecommunications Technologies","volume":"37 4","pages":""},"PeriodicalIF":2.5,"publicationDate":"2026-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147566466","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Malicious Client Defense Scheme in Federated Learning for Large-Scale Edge Nodes","authors":"Hongle Guo,&nbsp;Wanghu Chen,&nbsp;Xin Li","doi":"10.1002/ett.70399","DOIUrl":"https://doi.org/10.1002/ett.70399","url":null,"abstract":"<div>\u0000 \u0000 <p>In federated learning for large-scale edge nodes, the problem of malicious clients submitting anomalous parameters is becoming increasingly prominent. This seriously affects the accuracy and reliability of the model. For the problem of malicious client defense in a large number of clients with decentralized distribution, to reduce the detection time of malicious clients in federated learning and improve the accuracy of model training, a Blockchain-based Grouped Federated Learning malicious client defense Scheme (BGFLS) is proposed. Specifically, to detect malicious clients quickly and accurately, a grouped federated learning architecture is proposed, which applies blockchain technology to each grouping. In addition, an algorithm is designed to detect anomalous parameters, and a block structure that supports backtracking of malicious clients is proposed. Theoretical analysis and experiments show that the BGFLS scheme has improved accuracy compared with the GeoMed scheme and Krum scheme, and its backtracking efficiency is better than that of traditional blockchain implementations. Therefore, the BGFLS scheme can quickly detect malicious clients and protect shared parameters. This study provides a practical and high-performance solution for detecting malicious clients using federated learning in large-scale edge computing environments, with excellent technical specifications and high operational efficiency, effectively optimizing the overall system performance and stability.</p>\u0000 </div>","PeriodicalId":23282,"journal":{"name":"Transactions on Emerging Telecommunications Technologies","volume":"37 4","pages":""},"PeriodicalIF":2.5,"publicationDate":"2026-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147566002","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"QoE Fairness-Aware MADRL-Based Bitrate Allocation in Adaptive Video Streaming","authors":"Shijia Liu,&nbsp;Yong Wang,&nbsp;Fei Zhou,&nbsp;Danqing Wang,&nbsp;Junqi Chen","doi":"10.1002/ett.70398","DOIUrl":"https://doi.org/10.1002/ett.70398","url":null,"abstract":"<div>\u0000 \u0000 <p>In the field of multimedia, conventional video streaming remains the dominant playback format. Current research predominantly focuses on optimizing adaptive bitrate (ABR) algorithms to enhance quality of experience (QoE), delivering improved viewing experiences to users. However, the majority of existing approaches consider only single-user scenarios, whereas practical environments necessitate addressing the challenge of multiple users sharing bottleneck link bandwidth. These methods fail to holistically consider the multiple factors influencing QoE and provide insufficient consideration for QoE fairness. While bandwidth allocation fairness is achieved, ensuring fairness in user QoE remains challenging. Furthermore, these ABR algorithms rely solely on bitrate for adaptation, resulting in limited control dimensions and an inability to provide fine-grained ABR decisions. Additionally, certain methods require the deployment of additional control equipment to obtain global network states for achieving fairness, which increases deployment complexity in existing networks. To address the issue of QoE fairness in multi-user video streaming, this paper models it as a Markov decision process (MDP) for multi-agent cooperative fair allocation of limited bottleneck link resources, and proposes a multi-agent reinforcement learning-based ABR algorithm. The algorithm incorporates several improved Multi-Agent Deep Reinforcement Learning (MADRL) techniques to collaboratively select optimal chunk bitrate and download delay for different users, allowing for fine-grained control of the chunk download strategies. Furthermore, this paper designs and implements a video streaming distribution framework that operates without relying on additional network-assisted devices. This framework can efficiently acquire global client state, overcome performance disparities among clients, and achieve centralized and scalable ABR decision-making. Experimental results demonstrate that compared to existing methods, the proposed approach achieves a significant rightward shift in the CDF curve of average user QoE at the 50th percentile. Furthermore, it adeptly selects appropriate bitrate strategies for different types of devices. Consequently, the total transmitted data volume is reduced by 30.4% to 54.3%, leading to optimized bandwidth occupancy while ensuring user QoE fairness.</p>\u0000 </div>","PeriodicalId":23282,"journal":{"name":"Transactions on Emerging Telecommunications Technologies","volume":"37 3","pages":""},"PeriodicalIF":2.5,"publicationDate":"2026-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147565796","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Personalized Federated Learning for the Security of Satellite-Terrestrial Integrated Networks","authors":"Jupen Wang,&nbsp;Bo Hu,&nbsp;Shanzhi Chen,&nbsp;Tian Fan,&nbsp;Jingxin Wang,&nbsp;Chunmei Li,&nbsp;Yilei Wang","doi":"10.1002/ett.70390","DOIUrl":"https://doi.org/10.1002/ett.70390","url":null,"abstract":"<div>\u0000 \u0000 <p>The proposal of PFL (personalized federated learning) for STINs (satellite-terrestrial integrated networks) is a recent development in the field, with the aim of enhancing the accuracy of models through the utilization of personalized models for each client. These models are derived from diverse devices within the STINs, thereby ensuring a comprehensive and representative dataset. In the context of prevailing PFL schemes, clients receive local models from a server and subsequently aggregate these local models using identical weights. Nevertheless, this equal weighting approach engenders a lower accuracy of the aggregated local models. Conversely, the lower accuracy rate has been observed to trigger DoS (denial-of-service) attacks. In this paper, we propose PFL-Sec, a PFL framework for STINs security, with the aim of optimizing the distribution of weights and improving the model's accuracy against DoS attacks. Specifically, an optimization method of weights for local models based on gradient descent is proposed, with the aim of strengthening the weights of models with high contribution to the model in personalized aggregation. The experimental results indicate that PFL-Sec outperforms the other three baselines and improves the accuracy by 2.61% under the same settings. Furthermore, PFL-Sec demonstrates efficacy in the realm of DoS attacks. The experimental results indicate that the success rate of DoS in PFL-Sec is only 50% when the accuracy threshold for local models is set at 70%. It is evident that clients will only engage in the aggregation process if the accuracy of their local model exceeds 70%.</p>\u0000 </div>","PeriodicalId":23282,"journal":{"name":"Transactions on Emerging Telecommunications Technologies","volume":"37 3","pages":""},"PeriodicalIF":2.5,"publicationDate":"2026-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147564037","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}