IEEE Transactions on Network Science and Engineering最新文献

{"title":"CoATF: Convolution and Attention Based Tensor Factorization Model for Context-Aware Recommendation","authors":"Hao Li;Jianli Zhao;Qingqian Guan;Lutong Yao;Jianjian Chen;Guojun Sheng","doi":"10.1109/TNSE.2025.3563947","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3563947","url":null,"abstract":"Tensor factorization is an effective tool that has been successfully applied in the field of context-aware recommendation. However, most existing factorization models assume a multilinear relationship between recommendation rating entries and their corresponding factors, whereas in reality, real-world tensors often contain more complex interactions. In addition, recommendation data usually exhibits sparsity, which limits the amount of information that can be learned. In order to solve the above problems, this paper proposes a new nonlinear tensor factorization model called Convolution and Attention based Tensor Factorization (CoATF). First, we introduce a more generalized implicit feedback to comprehensively represent user preference. Next, a two-layer convolutional neural network is used to model the interactions between tensor factors. Finally, the attention mechanism is utilized to weight the features and improve the robustness of the model. The results of extensive experiments on multiple context-aware recommendation tensors show that the CoATF model significantly outperforms linear and nonlinear state-of-the-art tensor decomposition correlation models with superior recommendation performance.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 5","pages":"3682-3693"},"PeriodicalIF":7.9,"publicationDate":"2025-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144891287","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Energy-Based Cell Association in Nonuniform Renewable Energy-Powered Cellular Networks: Analysis and Optimization of Carbon Efficiency","authors":"Yuxi Zhao;Vicente Casares-Giner;Vicent Pla;Luis Guijarro;Iztok Humar;Yi Zhong;Xiaohu Ge","doi":"10.1109/TNSE.2025.3565065","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3565065","url":null,"abstract":"The increasing global push for carbon reduction highlights the importance of integrating renewable energy into the supply chain of cellular networks. However, due to the stochastic nature of renewable energy generation and the uneven load distribution across base stations, the utilization rate of renewable energy remains low. To address these challenges, this paper investigates the trade-off between carbon emissions and downlink throughput in cellular networks, offering insights into optimizing both network performance and sustainability. The renewable energy state of base station batteries and the number of occupied channels are modeled as a quasi-birth-death process. We construct models for the probability of channel blocking, average successful transmission probability for users, downlink throughput, carbon emissions, and carbon efficiency based on stochastic geometry. Based on these analyses, an energy-based cell association scheme is proposed to optimize the carbon efficiency of cellular networks. The results show that, compared to the closest cell association scheme, the energy-based cell association scheme is capable of reducing the carbon emissions of the network by 13.0% and improving the carbon efficiency by 11.3%.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 5","pages":"3744-3757"},"PeriodicalIF":7.9,"publicationDate":"2025-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144891069","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Hybrid Event-Triggered $Hinfty$ Control for Networked Control Systems Under Denial of Service Attacks","authors":"Ya-Li Zhi;Zeng Nie;Xu Liu;Shuping He","doi":"10.1109/TNSE.2025.3564482","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3564482","url":null,"abstract":"This paper proposed a novel hybrid event-triggered strategy (HETS) and an <inline-formula><tex-math>$Hinfty$</tex-math></inline-formula> control method for networked control systems (NCSs). The NCSs are vulnerable to denial of service (DoS) attacks and bandwidth-constrained. Firstly, by considering the malignancy of attacks and defense of network, the DoS attacks are divided into successful attacks and failed attacks. Meanwhile, a more flexible HETS is presented to counter intermittent DoS attacks. Secondly, the effects of DoS attacks, network-induced delays, and the proposed HETS are investigated in NCSs. Subsequently, a stability criterion is derived under the constraint of the maximum allowable number of successfully lost packets due to DoS attacks. The expected <inline-formula><tex-math>$Hinfty$</tex-math></inline-formula> control performance can be ensured in parallel with saving limited communication resources. At last, the validity of the presented approach is verified by a networked inverted pendulum on a cart.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 5","pages":"3709-3718"},"PeriodicalIF":7.9,"publicationDate":"2025-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144891314","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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 6-bit S-Boxes With DPA Resistance","authors":"Liuyan Yan;Lang Li;Qingling Song","doi":"10.1109/TNSE.2025.3564598","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3564598","url":null,"abstract":"Lightweight S-boxes have a significant impact on cryptographic algorithms for resource-constrained devices in the Internet of Things (IoT). Previous research on such S-oxes has focused on low area and good cryptographic properties, which neglects the resistance to side-channel analysis, especially differential power analysis (DPA). The reVisited transparency order (VTO) is one of the best indicators for evaluating S-boxes against DPA attacks so far. Therefore, this paper presents a scheme for designing 6-bit S-boxes. The designed S-boxes are suitable for lightweight block ciphers and have a certain ability to resist DPA attacks. Specifically, we first identify 23 3-bit S-boxes with the optimal cryptographic properties and the smallest hardware area through systematic screening. Then, the paper investigates the constructions of lightweight 6-bit S-boxes based on traditional algorithm structures. Finally, a novel structure named F-LM-F is proposed for designing lightweight 6-bit S-boxes by combining Feistel structure and Lai-Massey structure. It has been proven through comparison that the S-boxes under F-LM-F structure achieve fewer fixed points and lower VTO than the 6-bit S-box of BipBip cipher, with a 17.61<inline-formula><tex-math>$%$</tex-math></inline-formula> reduction in hardware area and a 13.58<inline-formula><tex-math>$%$</tex-math></inline-formula> decrease in CPU cycles.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 5","pages":"3719-3730"},"PeriodicalIF":7.9,"publicationDate":"2025-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144891315","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"RCNet: Resilient Collaborative DNN Inference for Wireless Networks With High Packet Loss","authors":"Yumeng Liang;Jianhui Chang;Mingyuan Zang;Jie Wu","doi":"10.1109/TNSE.2025.3563980","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3563980","url":null,"abstract":"The limited computation resources of mobile devices hinders the real-time Deep Neural Network (DNN) inference, which is critical in many Internet of Things (IoT) applications. To meet the real-time responses demands, the cloud-end collaborative DNN inference is promising, which partially offloads the inference workloads from mobile devices to the cloud server with powerful computation resources through wireless networks. However, in many IoT applications, the wireless networks are of poor link conditions with high packet loss rates, which has posed a substantial obstacle to the intermediate feature transmission. In such scenarios, it is rather challenging to achieve efficient and resilient collaborative DNN inference. In this paper, we tackle this challenge by proposing a <bold>R</b>esilient <bold>C</b>ollaborative DNN inference framework, named <bold>RCNet</b>, to maintain high accuracy under high packet loss conditions in wireless networks. It leverages an unequal redundant encoding mechanism to efficiently prioritize the successful transmission of important features on the mobile devices, and a Transformer-based feature reconstruction module to fully leverage the powerful computation resources on the cloud server to recover the missing features. We implement a real-world testbed and conduct extensive experiments. The experimental results verify that RCNet enables robust collaborative inference with an accuracy surpassing 90%, even under extremely harsh network conditions with over 90% of features being lost.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 5","pages":"3694-3708"},"PeriodicalIF":7.9,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144891235","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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 Rumor Dissemination Control Model Based on Evolutionary Game and Multiple User States","authors":"Qian Li;Fu Jiang;Hongjie Sun;Rong Wang;Chaolong Jia;Tun Li;Yunpeng Xiao","doi":"10.1109/TNSE.2025.3563360","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3563360","url":null,"abstract":"Rumor spreading in social networks involves complex dynamic causes. This paper constructs a new rumor spreading dynamics model based on evolutionary game theory to account for the possible skepticism of users during the dissemination of rumors, and introduces control theory for the directional management of public opinion in social networks. Firstly, based on the infectious disease dynamics model, we introduce users who exhibit skepticism when exposed to rumor information and continue to pay attention to it, classifying them as in a rumor-suspecting state during the rumor propagation process. Taking into account the impact of rumor information on users, as well as their intrinsic tendency to seek profit in the face of rumors, we quantify the influence of rumor news. This paper innovatively introduces the “rumor-suspecting state” into the traditional rumor propagation model, enabling a more comprehensive representation of skeptical user behaviors during rumor dissemination. By combining this with evolutionary game theory, we construct the driving force mechanism for users' rumor propagation, providing a foundation for understanding the transformation of users' states within the rumor-suspecting context. Secondly, to reduce the impact of rumor information and limit its spread, we develop a hybrid control strategy that combines two approaches: prevention and isolation. After implementing these hybrid control measures, we address the imbalance between control costs and effectiveness by establishing an optimal control problem with constraints. This aims to achieve optimal control with time-varying properties, and we theoretically derive the optimal solution to minimize costs. Finally, considering the complexity of rumor information and the need for effective rumor control, we propose an improved model of rumor propagation dynamics that combines the infectious disease model with optimal control theory. This model defines state transfer equations based on multiple user states and optimal control.The effectiveness of the control strategy is validated through theoretical proofs and experiments, and the impact of various factors on information diffusion is analyzed. On a real dataset we show that the model can effectively explain the diffusion process of complex rumor information in the network and manage it.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 5","pages":"3625-3640"},"PeriodicalIF":7.9,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144891116","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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 Probabilistic Model for Information Diffusion in Social Networks: Insights From Twitter Data","authors":"Emad Alizade;Naghmeh S. Moayedian;Faramarz Hendessi;T. Aaron Gulliver","doi":"10.1109/TNSE.2025.3563901","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3563901","url":null,"abstract":"Social networks have become a part of the daily lives of most people and are a significant influence in a variety of fields including economics, culture, and politics. This has motivated research on social networks. One aspect is evaluating the impact of messages on society which is a function of the information spread. Thus, a probabilistic model is proposed for the information spread in a social network. In this model, the probability of a user retweeting is based on metrics such as the trending degree, the importance of users retweeting the message, message freshness, and the influence of users on each other. The message viewing time is also considered as it is a critical spread factor. We propose three algorithms based on the proposed model. The first is based on a Kalman filter that simply estimates the number of retweeting users in the near future. The second considers in what order and at what times users retweet the message. The third employs some simplifications to reduce the complexity of the second algorithm. A real Twitter dataset is used to evaluate the performance. The results obtained show that the proposed model accurately predicts the number of users who spread a message.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 5","pages":"3671-3681"},"PeriodicalIF":7.9,"publicationDate":"2025-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144891118","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Mitigating Degree Bias in Graph Representation Learning With Learnable Structural Augmentation and Structural Self-Attention","authors":"Van Thuy Hoang;Hyeon-Ju Jeon;O-Joun Lee","doi":"10.1109/TNSE.2025.3563697","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3563697","url":null,"abstract":"Graph Neural Networks (GNNs) update node representations through message passing, which is primarily based on the homophily principle, assuming that adjacent nodes share similar features. However, in real-world graphs with long-tailed degree distributions, high-degree nodes dominate message passing, causing a degree bias where low-degree nodes remain under-represented due to inadequate messages. The main challenge in addressing degree bias is how to discover non-adjacent nodes to provide additional messages to low-degree nodes while reducing excessive messages for high-degree nodes. Nevertheless, exploiting non-adjacent nodes to provide valuable messages is challenging, as it could generate noisy information and disrupt the original graph structures. To solve it, we propose a novel Degree Fairness Graph Transformer, named DegFairGT, to mitigate degree bias by discovering structural similarities between non-adjacent nodes through learnable structural augmentation and structural self-attention. Our key idea is to exploit non-adjacent nodes with similar roles in the same community to generate informative edges under our augmentation, which could provide informative messages between nodes with similar roles while ensuring that the homophily principle is maintained within the community. By considering the structural similarities among non-adjacent nodes to generate informative edges, DegFairGT can overcome the imbalanced messages while still preserving the graph structures. To enable DegFairGT to learn such structural similarities, we then propose a structural self-attention to capture the similarities between node pairs. To preserve global graph structures and prevent graph augmentation from hindering graph structure, we propose a Self-Supervised Learning task to preserve p-step transition probability and regularize graph augmentation. Extensive experiments on six datasets showed that DegFairGT outperformed state-of-the-art baselines in degree fairness analysis, node classification, and node clustering tasks.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 5","pages":"3656-3670"},"PeriodicalIF":7.9,"publicationDate":"2025-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144891248","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Modeling and Analysis of Delayed Matthew Effect in Social Systems via $k$-Winners-Take-All Network","authors":"Jiayi Wang;Suibing Li;Long Jin;Shuai Li","doi":"10.1109/TNSE.2025.3562075","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3562075","url":null,"abstract":"A new time-delayed Matthew effect model is developed in this paper, aiming to depict the Matthew effect in social systems. Based on the construction of a social network with information transmission delay, the development speed and development potential of each agent in the social network are defined as some specific parameters, and these parameters are used to describe the status and evolutionary trend of each agent. Furthermore, this paper theoretically derives the value of the maximum time delay allowed by the proposed time-delayed Matthew effect model in a social network and verifies its convergence. Through a series of simulations, the correctness and feasibility of the proposed model are demonstrated. This work takes the time delay in information transmission into account in the Matthew effect model for the first time so that the model is capable of describing this social phenomenon accurately.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 5","pages":"3555-3564"},"PeriodicalIF":7.9,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144891286","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Secure and Dynamic Route Navigation Through RSU-Based Authentication in IoV for Smart City","authors":"Bimal Kumar Meher;Ruhul Amin;Mohammad Abdussami;Muhammad Khurram Khan;Md Abdul Saifulla;Sanjeev Kumar Dwivedi","doi":"10.1109/TNSE.2025.3563297","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3563297","url":null,"abstract":"One of the significant services provided by IoV in Smart cities is vehicular navigation. Drivers often find it difficult and time-consuming to complete their trip in a crowded city without real-time knowledge about the traffic and road conditions. So, a proper routing mechanism can help drivers reach their destination in minimum time and with less fuel consumption. However, it has been found that such protocols often face security challenges. In this paper, we have proposed an authenticated navigation scheme with the help of pseudonym-based asymmetric-key cryptography that discovers and secures the route to the destination in real time. The architecture embodies a geolocation provider (GLP) to get the possible static routes to a particular destination. Further, it uses the message-forwarding capability of RSUs to develop a dynamic route, after receiving feedback from the respective RSUs about the traffic conditions. While doing so, this protocol ensures proper message integrity, anonymity, unlinkability and robust protection from important security threats. Our approach ensures minimal end-to-end delay and efficient real-time route finding from a source to a destination with no extra overhead on the vehicles. We have simulated our authentication protocol using the Scyther simulator and found it safe from various adversarial attacks.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 5","pages":"3590-3599"},"PeriodicalIF":7.9,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144891064","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}