Network Users Research Articles

JORA: Weakly Supervised User Identity Linkage via Jointly Learning to Represent and Align.

The user identity linkage that establishes correspondence between users across networks is a fundamental issue in various social network applications. Efforts have recently been devoted to introducing network embedding techniques that map the different network users into the common representation space, thereby inferring user correspondence based on the similarities of their representations. However, existing studies that separately train the network embedding and space alignment in two stages may lead to conflict between the objectives of the two stages. Besides, the similarities between unlabeled cross-network user pairs are difficult to define and largely impact the result. Moreover, many previous methods still need plenty of labeled aligned user pairs to ensure performance, which may not be available. To address the above problems, we propose to solve the weakly-supervised user identity linkage problem via JOintly learning to Represent and Align, i.e., the JORA model. The architecture of JORA adopts the inductive graph convolutional network (GCN) that learns representations for each network. The model is jointly optimized by the representation learning component and alignment learning component. The former one aims to preserve the similarities between intranetwork users. The latter one aligns the different spaces by a projection function and aims to preserve the similarities between cross-network users. A specific attention mechanism is proposed to learn self-adaptive similarities for unlabeled user pairs during alignment learning and it reduces the error propagation caused by predefined similarities. The joint optimization helps perceive network characteristics during alignment and reduces the number of labeled users required. Experiments conducted on real social networks show that the proposed model achieves significantly better performance than the state-of-the-art methods.

Content Delivery Performance Analysis of a Cache-Enabled UAV Base Station Assisted Cellular Network for Metaverse Users

Content Delivery Performance Analysis of a Cache-Enabled UAV Base Station Assisted Cellular Network for Metaverse Users

American media, Scandinavian audiences: Contextual fragmentation and polarisation among Swedes and Norwegians engaging with American politics

Abstract This article explores the contextual nature of fragmentation and polarisation – subjects that have attracted significant concern in the age of social media. I investigate the media sharing practices of Scandinavian Twitter users discussing the 2020 American presidential election, an event that attracted international attention. Using links in tweets, I map the media networks of users in Sweden and Norway in their national languages and in English. This intranational approach provides a view into whether fragmentation and polarisation are characteristic of the audience or the media milieu. The findings show Scandinavian users exhibit low audience polarisation within their national languages, but they display polarisation similar to American users when engaging with English-language media. At the same time, media fragmentation is higher in the Norwegian language than in any other sphere. This article sheds light on the relationship between the sometimes-conflated concepts of fragmentation and polarisation and provides a discussion of the implications of political information sharing on transnational digital platforms.

A Deep Learning Framework for Diagnosis and Survival Prognosis of Central Nervous System Tumors

Diagnosis and prognosis of central nervous system (CNS) tumors rely on manual and algorithmic approaches that are subject to variations, inefficiencies and bias. With 5-year survival rates as low as 6%, timely tumor assessment is crucial to ensure patient health. Machine learning and deep learning techniques have been used over the past decade to reduce the assessment burden and augment physician diagnoses. Traditional machine learning models require manual feature extraction and engineering, introducing further variability of the results. On the other hand, automated deep learning models require complicated engineering and workflow implementations that need to be managed and updated for new datasets. This study endeavors to define a generalizable, two-phase neural network pipeline and user interface that can be applied to clinical assessment of any tumor with 3D MRI scans, allowing for improved personalization of patient diagnosis and treatment options. In the first diagnostic phase, radiomic features are used to predict tumor severity and extent. The outputs of this phase are then passed to a survival prognosis model along with the patients’ clinical data to predict the 5-year overall survival rate. The diagnostic model achieved a F1-Score, a measure of classification accuracy, of 94% and the prognostic model achieved a risk-adjusted, time-dependent Harrell’s Concordance Index score of 0.92, indicating the framework’s generalizability to new datasets. The mobile app developed as part of this study offer ease of access to physicians and radiologists in reviewing predicted results and subsequent patient interactions.

Technology of protection of authentication data of computer network users

The article is devoted to the problem of perfect protection of authentication data of users of computer systems, especially in the case of a large number of different rights and powers that are personally granted to users. The importance of this problem increases especially when the number of such users in the system is hundreds or thousands. At the same time, each of them must create conditions for access only to their data and ensure protection against any outside interference, both by other users and by staff. A typical example of such conditions are secret electronic voting systems. The software and technical solutions described in this work have passed many years of testing and continue to be practically used in the electronic voting system of the Kyiv National University of Civil Engineering and Architecture. This system is regularly used for conducting elections to student self-government bodies and for surveys among students regarding the quality of teaching subjects. With the help of this system, elections of leaders of the Red Cross Society of Ukraine were held during the pandemic, which was associated with the Covid-19 virus. The mathematical basis of the described authentication data protection technology is the theory of algebraic groups, namely, the problem of discrete logarithmization over large Galois fields. Thanks to the use of cryptographic transformations over these fields, instead of known hash functions, it was possible to get rid of the possibility of collisions and neutralize the disclosure of passwords by attackers who were able to do it with the help of specialized Internet resources. It was also possible to increase resistance to brute-force password cracking, since conversions to Galois fields take ten times more time than hash function calculations.

Passive reputation method with hybrid optimized deep model for spectrum sensing in cognitive radio network based on blockchain

SummaryThe discovery of malevolent users in cognitive radio networks (CRNs) is done by using blockchain‐based technique. For diagnosing the availability of frequency resources, the spectrum sensing (SS) plays an essential role in CRN. It is critical to enable cognitive radio (CR) technology in wireless communication systems for the next generation. Due to the increasing demand of the users, some bands are overloaded and others become underutilized. The CR applied models for vigorously assigning unlicensed users. The missed detection problem occurs in the conventional spectrum sensing schemes, which hampers the proper utilization of the spectrum. These motivated the development of a newly devised passive reputation method with an optimized deep model for spectrum sensing in CRN‐based blockchain. The sensing spectrum in CRN is designed using the cooperative spectrum sensing algorithm. The spectrum sensing is done with the decision made using AlexNet where the weights of AlexNet are trained with a hybrid optimization algorithm, named Honey Badger Remora Optimization (HBRO) algorithm. Thus, the output attained from the Alexnet_HBRO algorithm is considered. Meanwhile, the data are recorded in the blockchain, and then, the passive reputation is performed, and the determined output is considered. At last, the spectrum sensing is carried out by fusing AlexNet and passive reputation output where weights are optimally generated using the proposed Snake Honey Badger Remora Optimization (SHBRO) algorithm. The proposed SHBRO offered a high detection probability of 1, false alarm probability of 0.003, sensing time of 551.567s, and computation time of 210.102s.

Exploring the potential of AI-driven optimization in enhancing network performance and efficiency

The exponential growth of network complexity and data volume in modern digital ecosystems has underscored the need for innovative approaches to optimize network performance and efficiency. This paper delves into the potential of AI-driven optimization techniques in addressing this imperative. Leveraging artificial intelligence (AI) algorithms such as machine learning and deep learning, the study investigates how AI can revolutionize network management and operation to achieve higher levels of performance and reliability. Through a comprehensive review of existing literature and case studies, this paper elucidates the fundamental principles, methodologies, and applications of AI-driven optimization in diverse network environments. It examines how AI algorithms can analyze vast amounts of network data, identify patterns, and make data-driven decisions to optimize network configurations, routing protocols, and resource allocation strategies. Moreover, the study explores how AI-driven optimization can enhance network security, fault tolerance, and scalability by autonomously detecting and mitigating potential threats and vulnerabilities. The Review succinctly encapsulates the main findings and insights derived from the analysis, emphasizing the transformative potential of AI-driven optimization for network performance and efficiency enhancement. It underscores the benefits of AI-driven approaches in automating complex optimization tasks, reducing operational overhead, and adapting dynamically to changing network conditions and user demands. Additionally, the Review discusses the challenges and considerations associated with the implementation of AI-driven optimization techniques, including algorithmic bias, data privacy concerns, and ethical implications. In conclusion, the Review underscores the critical role of AI-driven optimization in addressing the evolving challenges of network management and operation. It advocates for continued research and development efforts aimed at harnessing the full potential of AI-driven optimization to unlock new levels of performance and efficiency in network infrastructures. By embracing AI-driven approaches, organizations can streamline network operations, improve user experience, and drive innovation in the digital era.

Video quality adaptation using CNN and RNN models for cost-effective and scalable video streaming Services

Video streaming services require adaptive bit rate strategies that optimize video quality based on network conditions and user preferences to provide a cost-effective and scalable solution. In this manuscript, we present a novel architecture that utilizes a combination of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) to extract features from the video stream and predict optimal bit rates for each frame. The CNN feature extractor extracts relevant features from the input video stream, which are then passed on to the RNN predictor, where the optimal bit rate is predicted to ensure a personalized viewing experience tailored to the current network conditions and specific user preferences. Our experimental results demonstrate that the proposed architecture achieves significant improvements in video quality while minimizing bandwidth usage and providing a better user experience. Specifically, our results show a 37.1% improvement in average bit rate, indicating that the proposed architecture optimizes the video quality and reduces bandwidth usage by 37.1% on average. We also observed a 16.6% improvement in Quality of Experience (QoE), meaning that users will perceive the video quality as better. Additionally, rebuffering was reduced by 87.5%, indicating that users enjoy smoother video playback without interruptions. Importantly, our architecture is optimized for Dynamic Adaptive Streaming over HTTP (DASH), addressing the need for efficient streaming over the most widely used protocol in the industry.

Optimization of the LEACH algorithm in the selection of cluster heads based on residual energy in wireless sensor networks

This research has a research object, namely the optimization of the LEACH (Low-Energy Adaptive Clustering Hierarchy) algorithm in the context of wireless sensor networks. The problem in this research is the imbalance in energy consumption across clusters, which has an impact on battery life and affects network performance. Other problems include selecting a cluster head that is not focused so that it is difficult to balance network performance as well as computational limitations that require optimization. The results obtained from this research are in the form of optimizing the leaching algorithm by modifying the clustering-based leaching algorithm that will be used in wireless sensor networks. In carrying out modifications, this research uses several stages in the process of selecting sensor nodes that will become members who function as cluster heads in a cluster that will be used in a wireless sensor network. In the LEACH (Low-Energy Adaptive Clustering Hierarchy) algorithm the cluster head will be selected based on the modified probability value. Modifying the algorithm by considering two factors, namely distance and remaining energy used in the Cluster Head selection process on the network and increasing network usage time must be based on the energy consumption used and then compared with the remaining energy. When modifying the LEACH (Low-Energy Adaptive Clustering Hierarchy) algorithm, it is necessary to pay attention to the distance factor between the nodes on a sensor and the selected cluster so that it can result in increased network performance. Network lifetime is indicated by the average death time of the first Node in the network. This research is novel in producing a modified leaching algorithm by improving network performance and extending battery life so that it can be used for wireless sensor networks in the context of natural disaster mitigation

Implementation of a Lossless Moving Target Defense Mechanism

The contemporary world, dominated by information technologt (IT), necessitates sophisticated protection mechanisms against attacks that pose significant threats to individuals, companies, and governments alike. The unpredictability of human behavior, coupled with the scattered development of applications and devices, complicates supply chain maintenance, making it impossible to develop a system entirely immune to cyberattacks. Effective execution of many attack types hinges on prior network reconnaissance. Thus, hindering effective reconnaissance serves as a countermeasure to attacks. This paper introduces a solution within the moving target defense (MTD) strategies, focusing on the mutation of Internet protocol (IP) addresses in both edge and core network switches. The idea of complicating reconnaissance by continually changing IP addresses has been suggested in numerous studies. Nonetheless, previously proposed solutions have adversely impacted the quality of service (QoS) levels. Implementing these mechanisms could interrupt Transmission Control Protocol (TCP) connections and result in data losses. The IP address mutation algorithms presented in this study were designed to be fully transparent to transport layer protocols, thereby preserving the QoS for users without degradation. In this study, we leveraged the benefits of software-defined networking (SDN) and the Programming-Protocol-Ondependent Packet Processors (P4) language, which specifies packet processing methodologies in the data plane. Employing both SDN and P4 enables a dynamic customization of network device functionalities to meet network users’ specific requirements, a feat unachievable with conventional computer networks. This approach not only enhances the adaptability of network configurations but also significantly increases the efficiency and effectiveness of network management and operation.

A comprehensive survey of low‐carbon planning and operation of electricity, hydrogen fuel, and transportation networks

AbstractThe trend of global energy systems towards carbon neutrality has led to an escalating interdependency between electricity, hydrogen fuel, and transportation networks. However, the means of surmounting the many challenges confronting the optimal coupling and coordination of electric power, hydrogen fuel, and transportation systems are not sufficiently understood to guide modern infrastructure planning operations. The present work addresses this issue by surveying the extant literature, relevant government policies, and future development trends to evaluate the present state of technology available for coordinating these systems and then determine the most pressing issues that remain to be addressed to facilitate future trends. On the one hand, the users of transportation networks represent flexible consumers of electric power and hydrogen fuel for those connected via devices such as electric vehicles and hydrogen fuel cell vehicles through charging stations and hydrogen refuelling stations. On the other hand, power grids can mitigate the negative effect of random charging behaviours on grid security through time‐of‐use electricity pricing, while excess renewable energy outputs can be applied to generate hydrogen fuel. The findings of this overview offer support for infrastructure planning and operations. Finally, the most urgent issues requiring further research are summarised.

Optimizing energy efficiency in heterogeneous networks: An integrated stochastic geometry approach with novel sleep mode strategies and QoS framework.

The quest for energy efficiency (EE) in multi-tier Heterogeneous Networks (HetNets) is observed within the context of surging high-speed data demands and the rapid proliferation of wireless devices. The analysis of existing literature underscores the need for more comprehensive strategies to realize genuinely energy-efficient HetNets. This research work contributes significantly by employing a systematic methodology, utilizing This model facilitates the assessment of network performance by considering the spatial distribution of network elements. The stochastic nature of the PPP allows for a realistic representation of the random spatial deployment of base stations and users in multi-tier HetNets. Additionally, an analytical framework for Quality of Service (QoS) provision based on D-DOSS simplifies the understanding of user-base station relationships and offers essential performance metrics. Moreover, an optimization problem formulation, considering coverage, energy maximization, and delay minimization constraints, aims to strike a balance between key network attributes. This research not only addresses crucial challenges in creating EE HetNets but also lays a foundation for future advancements in wireless network design, operation, and management, ultimately benefiting network operators and end-users alike amidst the growing demand for high-speed data and the increasing prevalence of wireless devices. The proposed D-DOSS approach not only offers insights for the systematic design and analysis of EE HetNets but also systematically outperforms other state-of-the-art techniques presented. The improvement in energy efficiency systematically ranges from 67% (min side) to 98% (max side), systematically demonstrating the effectiveness of the proposed strategy in achieving higher energy efficiency compared to existing strategies. This systematic research work establishes a strong foundation for the systematic evolution of energy-efficient HetNets. The systematic methodology employed ensures a comprehensive understanding of the complex interplay of network dynamics and user requirements in a multi-tiered environment.

University campus network planning and design based on GPON technology

With the continuous development of Internet applications, in order to meet the increasing demands of teachers and students for the campus network in teaching, scientific research, office work and daily life, it is necessary to build a network environment that can meet the needs of smart campuses and future new applications. This paper makes an in-depth analysis of the current situation of campus networks, uses Gigabit Passive Optical Network (GPON) technology to upgrade and transform the existing network, reduces the cost of switching equipment and maintenance difficulty, improves the network transmission rate, increases the upper limit of campus network user access, and effectively solves the problem of separation between wired and wireless networks.

Network-adjusted covariates for community detection

Summary Community detection is a crucial task in network analysis that can be significantly improved by incorporating subject-level information, ie, covariates. Existing methods have shown the effectiveness of using covariates on the low-degree nodes, but rarely discuss the case where communities have significantly different density levels, ie, multiscale networks. In this paper, we introduce a novel method that addresses this challenge by constructing network-adjusted covariates, which leverage the network connections and covariates with a node-specific weight for each node. This weight can be calculated without tuning parameters. We present novel theoretical results on the strong consistency of our method under degree-corrected stochastic blockmodels with covariates, even in the presence of misspecification and multiple sparse communities. Additionally, we establish a general lower bound for the community detection problem when both the network and covariates are present, and it shows that our method is optimal for connection intensity up to a constant factor. Our method outperforms existing approaches in simulations and a LastFM app user network. We then compare our method with others on a statistics publication citation network where 30% of nodes are isolated, and our method produces reasonable and balanced results. Our method is implemented in the R package NAC.

Community detection based on nonnegative matrix tri-factorization for multiplex social networks

Abstract Nowadays, community detection is one of the important fields for understanding network topology and has many applications in information diffusion, interaction mining and migration behaviour analysis. Therefore, community detection in social networks can help to understand user behaviour and network characteristics. There are many community detection methods, which are often designed for single-layer social networks. However, real-world networks use several types of relationships to establish connections between users, each of which has different characteristics. Hence, real-world networks can be modelled as multiplex networks. In general, multiplex networks are an example of multilayer networks in which the relationships between users in different networks can be considered simultaneously. In these networks, each layer represents the connections between users in a social network. Meanwhile, communities in multiplex networks are identified based on the structure and connections between overlapping users in different layers of the network. In this article, the nonnegative matrix tri-factorization (NMTF) strategy is used to model multiplex social networks, and a solution for community detection is developed based on it. According to this strategy, a common consensus matrix and then an alignment matrix are extracted based on similarity metrics and network structure. The use of these matrices as a flexible modelling framework enables the detection of coherent community between overlapping users in multiplex social networks. We evaluate the proposed NMTF method through various metrics on a multiplex social network. The results of this evaluation show the better performance of NMTF in terms of community quality compared to equivalent methods.

Text sentiment analysis based on the LSTM method

Sentiment analysis is an important research direction in the field of natural language processing. With the rise of various social network platforms, a large number of network users have begun to express and publish their opinions on X, LINE, Weibo, and other platforms, which makes sentiment analysis more and more important. However, as more and more people use social platforms, the number of comments from Internet users has surged, and Internet buzzwords and Internet popular topics are constantly changing. This phenomenon leads to an increase in the error rate of traditional text emotion detection methods, which in turn leads to a reduction in the operating efficiency of some network platforms. In addition, nowadays, sentiment analysis has a wider and more urgent need in many fields, especially in the business field. In order to cope with this change and demand, this paper focuses on a text sentiment analysis model based on a neural network model.

Why it does not work? Metaheuristic task allocation approaches in Fog-enabled Internet of Drones

Several scenarios that use the Internet of Drones (IoD) networks require a Fog paradigm, where the Fog devices, provide time-sensitive functionality such as task allocation, scheduling, and resource optimization. The problem of efficient task allocation/scheduling is critical for optimizing Fog-enabled Internet of Drones performance. In recent years, many articles have employed meta-heuristic approaches for task scheduling/allocation in Fog-enabled IoT-based scenarios, focusing on network usage and delay, but neglecting execution time. While promising in the academic area, metaheuristic have many limitations in real-time environments due to their high execution time, resource-intensive nature, increased time complexity, and inherent uncertainty in achieving optimal solutions, as supported by empirical studies, case studies, and benchmarking data. We propose a task allocation method named F-DTA that is used as the fitness function of two metaheuristic approaches: Particle Swarm Optimization (PSO) and The Krill Herd Algorithm (KHA). We compare our proposed method by simulation using the iFogSim2 simulator, keeping all the settings the same for a fair evaluation and only focus on the execution time. The results confirm its superior performance in execution time, compared to the metaheuristics.

Evaluation of User-Centric Cell-Free Massive Multiple-Input Multiple-Output Networks Considering Realistic Channels and Frontend Nonlinear Distortion

Future 6G networks are expected to utilize Massive Multiple-Input Multiple-Output (M-MIMO) and follow a user-centric cell-free (UCCF) architecture. In a UCCF M-MIMO network, the user can be potentially served by multiple surrounding Radio Units (RUs) and Distributed Units (DUs) controlled and coordinated by a single virtualized Centralized Unit (CU). Moreover, in an M-MIMO network, each transmit frontend is equipped with a Power Amplifier (PA), typically with nonlinear characteristics, that can have a significant impact on the throughput achieved by network users. This work evaluates a UCCF M-MIMO network within an advanced system-level simulator considering multicarrier transmission, using Orthogonal Frequency-Division Multiplexing (OFDM), realistic signal-processing steps, e.g., per resource block scheduling, and a nonlinear radio frontend. Moreover, both idealistic independent and identically distributed (i.i.d.) Rayleigh and 3D ray-tracing-based radio channels are evaluated. The results show that under the realistic radio channel, the novel user-centric network architecture can lead to an almost uniform distribution of user throughput and improve the rate of the users characterized by the worst radio conditions by over 3 times in comparison to a classical, network-centric design. At the same time, the nonlinear characteristics of the PA can cause significant degradation of the UCCF M-MIMO network’s performance when operating close to its saturation power.

Handover algorithm based on Bayesian-optimized LSTM and multi-attribute decision making for heterogeneous networks

Heterogeneous networks (HetNets) which can satisfy the diverse requirements of future terminal tasks through providing different network access services for terminals, have emerged as a vital technology for the development of next-generation networks. However, frequent access to different networks often leads to high handover delay and handover failure, resulting in a degradation of user experience. Therefore, maintaining seamless network connectivity has become a challenging problem for applications with high real-time and reliability requirements in HetNets. To address this problem, we propose a handover algorithm based on Bayesian-optimized Long Short-Term Memory (BO-LSTM) and multiple attribute decision making (HO-BLM) to reduce handover latency and failure, ensuring seamless network connectivity. To reduce handover delay, we designed a handover decision prediction algorithm based on BO-LSTM to trigger handover in advance by predicting the network state of users in the future. Additionally, we propose a preselection mechanism based on current network status to further reduce the calculation delay. Moreover, a multi-attribute decision making (MADM)-based selection approach is designed to select the best alternative network for a specific user, where the utility value of the best alternative network is calculated by weighing the users’ preferences for network parameters of different business types and the actual status of the candidate networks. Simulation results show that the proposed algorithm decreases the handover failure by up to 42.1% and the handover delay by up to 68% compared with traditional handover approaches.

SVM‐SFL based malicious UAV detection in wireless sensor networks

SummaryIn the modern era, unmanned aerial vehicle (UAV) based wireless sensor networks (WSN) are rising technologies in wireless communication. Through UAV, the sensed data can be forwarded to the base station. However, the increase in network users leads to several malicious attacks on UAVs. Hence, it affects the performance of a WSN platform while transmitting private information through UAVs. Therefore, the proposed study intends to develop an effective malicious UAV detection approach using a machine‐learning algorithm. Initially, the deployed sensor nodes in WSN are utilized to collect the environmental data. These sensor nodes transmit the collected data to the UAV. During data transmission, the sensor nodes generate a feed packet (authentication parameter) and forward it to the UAV along with the sensed information. The feedback packet is encrypted through a proxy re‐encryption scheme to secure the input data. These encrypted packets with the sensed input data are then transmitted to the base station. Finally, the feedback packet is decrypted and attains the actual input information. From the received data, the classification is performed using a proposed support vector machine with a shuffled frog leap (SVM‐SFL) approach. The proposed approach is implemented with the NS3 Python tool, and the results are analyzed by evaluating several performance matrices. Compared with other existing methods, the proposed study obtained improved results in terms of accuracy (98.61%), precision (98.5%), sensitivity (98.63%), and F‐measure (98.62%).