Network Services Research Articles

Federated Learning in 6G Non-Terrestrial Network for IoT Services: From the Perspective of Perceptive Mobile Network

Federated Learning in 6G Non-Terrestrial Network for IoT Services: From the Perspective of Perceptive Mobile Network

End-to-End Data Flows Management in the Decentralized 5G/6G Mobile Networks

The evolution of 5G and the anticipated emergence of 6G networks demand significant enhancements in optical backhaul infrastructure to support higher bandwidth, low latency, and increased reliability. Considering a wide range of feasible applications with different quality requirements, the key challenge for the underlying backhaul and optical transport network is in the high load variance in the optical switching nodes and complicated data flows management. In this paper, a novel approach is proposed for end-to-end data flows management in decentralized 5G/6G mobile networks, which are interconnected by the optical burst switching transport infrastructure. The key idea is to train a deep recurrent neural network over a real network statistic obtain at the different network segments and service slices. Then, predictions made by deep neural network are used for predictive resource allocation in each node of the optical burst switching network to ensure a target quality of service for each end-to-end data flow. The experimental results show that proposed approach provides 90% accuracy of predictions and allows to effectively utilize the resources of optical network.

Prospects for Applying Artificial Intelligence Technologies by Public Libraries of Ukraine

The aim of the article is to study prospects for the artificial intelligence technologies usage by public libraries of Ukraine in conditions of digital transformation of society. Research methods. General scientific research methods are used, in particular, analysis and generalisation of possibilities of language prognostication models based on neural networks in the activity of Ukrainian public libraries. The scientific novelty of the obtained results consists in actualising the problem of using ChatGPT 3.5, Gemini, Microsoft Bing and Grok technologies in the library sphere, and outlining the key possibilities of using these language models of artificial intelligence among public libraries. The usage of new generation chatbots for interacting with users of public libraries, searching the information and generating content are actively gaining popularity, moving from theory to practical level. Linguistic models of neural networks are used to create marketing campaigns, analysis and familiarisation with the content of works and archival materials, interaction with library users, and finding answers to professional questions. Main conclusions. The potential of language prognostication models based on neural networks in the practical activity of public libraries is analysed. By means of the analysis of ChatGPT 3.5, Gemini, Bing Chat and Grok technologies, and their usage in the library sphere, the main potential possibilities of interaction of information institution employees with these technologies are determined. In particular, the integration of ChatGPT functions through API into the system of public libraries will allow to optimise searching the information in the database and and feedback opportunities with library users. Using the ChatGPT 3.5 neural network service will speed up the development of a marketing content plan, instructions, as well as automate book recommendations based on the analysis of the readers’ preferences and books read. It is found out that the methods of implementing innovative models can allow not only to qualitatively improve the service of public libraries users, but also to automate their work in order to optimise the performance of everyday tasks, preserve cultural heritage and access to digital resources. In the future, the level of deepening the involvement of these technologies will inevitably grow. The sooner library institutions start using neural networks in everyday practice, the sooner they will be able to facilitate the work of library sphere workers, provide improved users’ service, and increase the effectiveness of library marketing support. It is emphasised that experiments on the use of artificial intelligence language models still need an empirical research method. Particularly, they require attention not only from the point of view of usage for personal purposes, but also in the professional activity of the library sphere.

Virtual Private Cloud (VPC) & Elastic Compute Cloud (EC2) with Remote Access Using PuTTY Terminal on Ubuntu in a Private VPN

One of the computer technologies that is commonly used by agencies/companies is the internet network which functions as a bridge to connect between one point to another. Apart from having the advantage of being a medium for long-distance communication, the internet also has a lack of security. One of the weakness found is the internet as a transmission medium for important or confidential data. One effort that can be made to overcome this problem is to build a private network in a public network service, which is often known as a Virtual Private Network (VPN). In this research, the VPN was built by combining a Virtual Private Cloud (VPC) with Elastic Compute Cloud (EC2) and using Ubuntu's Terminal in PuTTY Gen as remote access using network protocols for remote server needs from remote control.

Discovering patterns and trends in customer service technologies patents using large language model

The definition of service has evolved from a focus on material value in manufacturing before the 2000s to a customer-centric value based on the significant growth of the service industry. Digital transformation has become essential for companies in the service industry due to the incorporation of digital technology through the Fourth Industrial Revolution and COVID-19. This study utilised Bidirectional Encoder Representations from Transformer (BERT) to analyse 3029 international patents related to the customer service industry and digital transformation registered between 2000 and 2022. Through topic modelling, this study identified 10 major topics in the customer service industry and analysed their yearly trends. Our findings show that as of 2022, the trend with the highest frequency is user-centric network service design, while cloud computing has experienced the steepest increase in the last five years. User-centric network services have been steadily developing since the inception of the Internet. Cloud computing is one of the key technologies being developed intensively in 2023 for the digital transformation of customer service. This study identifies time series trends of customer service industry patents and suggests the effectiveness of using BERTopic to predict future trends in technology.

SNSMiner_VAC: Analyzing vaccination based on social network service data for safety surveillance

COVID-19 has created a major issue around the world, posing a serious threat to socioeconomic and human health, and there is still fear of new infectious diseases like this. In Korea, in response to COVID-19, the COVID-19 vaccine approved by the Ministry of Food and Drug Safety was sequentially administered to each group, raising national interest in the safety, side effects, and effectiveness of the vaccine, and securing the basis for related policies. Many attempts have been made for this. We are interested in a methodology to establish a scientific basis for how to respond to issues regarding vaccine stability due to the emergence of new infectious diseases. In this study, we use comments posted on Naver, the largest social platform in Korea, to obtain consumer sentiment information about vaccines and understand the change in Korean public sentiment in the first half of 2021 for each vaccine based on the analysis pipeline (SNSMiner_VAC). We investigated the Korean public’s response to the COVID-19 vaccination on social media from November 30, 2021, to January 31, 2022. We collected comments related to the COVID-19 vaccination using the Korean words for “COVID-19 vaccination” as keywords. Of the 329,559 comments, 240,322 were analyzed after preprocessing. We developed three lexicons (stopwords, sentiment words, and custom words related to COVID-19) for Korean natural language processing. Furthermore, we extracted five clusters — including symptoms, side effects, vaccine hesitancy, pro-vaccination, and infectious disease control policy — through network analysis. The sentiment analysis revealed that negative public opinion was prominent even after the commencement of the phased recovery of daily life. From these results, we were able to automatically collect data-based information on patients’ symptoms and side effects for the new vaccine and prepare and analyze the basis for collecting public opinions about vaccination. We hope that the pipeline proposed in this study can be used as a tool to create a data source for effective management policies for vaccines being developed against the emergence of new infectious diseases.

EXAMINING THE ROLE OF SERVICE QUALITY DIMENSIONS OF MOBILE PHONE SERVICE PROVIDERS; AN EMPIRICAL STUDY

Service quality has become a critical factor for the competitive advantage of mobile phone service providers in the telecommunication industry. This study explores the key factors influencing service quality in mobile phone service providers and their impact on customer satisfaction and loyalty. The analysis focuses on dimensions such as network quality, customer support, pricing, service reliability, and value-added services. The research aims to identify how these factors contribute to the overall perception of service quality and determine the most significant determinants of customer satisfaction. The non-probability convenience sampling technique is the most suitable method when it is not possible to obtain information from every member of the sample population. Additionally, the precise population frame of mobile phone service consumers in the study area could not be determined, as the number of users could not be ascertained. The interview schedule was employed to acquire the primary data from the respondents. The data that has been collected is coded and inserted into a primary table. The data are analysed in accordance with the nature of the data and the intent of the analysis (nature of the problem) using the SPSS software. For the purpose of the research, a sample size of 100 respondents is selected from an infinite population. A random sample strategy was used by the researcher in order to choose the objects that would be used for sampling. The findings highlight the need for service providers to continuously adapt and enhance their service offerings to meet evolving customer expectations and maintain competitiveness in a rapidly changing market

Traffic data classification in SDN network based on machine learning algorithms

Traffic classification plays a crucial role in various domains of network management, including service measurement, architectural design, security monitoring, and advertising. Software-defined networks (SDN) is a new technology that has the potential to solve typical network problems by simplifying network management, the introduction of network programmability, and the provision of a global perspective of a network. In recent years, SDN has brought new opportunities to classify traffic. Traffic classification techniques in SDN have been investigated, proposed, and developed. This survey delves into traffic classification under SDN, which is a vital component for improving network services, administration, and security. We give an in-depth assessment of traffic categorization algorithms adapted for SDN, emphasizing the fresh opportunities and problems they present. We cover the many metrics for assessing the effectiveness of these traffic classification algorithms, such as accuracy, precision, recall, and F1 score, and we examine the numerous datasets that serve as performance benchmarks. The study also synthesizes the findings of existing research, revealing trends and the efficacy of various techniques in the context of SDN-enabled settings. This document serves as a resource for scholars and practitioners seeking to optimize traffic classification strategies by providing a complete review and assessment of existing traffic classification approaches

Performing Encrypted Cloud Data Keyword Searches Using Blockchain Technology on Smart Devices

Data owners seeking to boost processing power, storage, or bandwidth can take advantage of cloud computing services. However, this shift poses new challenges related to privacy and data security. Searchable Encryption (SE), which combines encryption and search techniques, addresses these issues (violation of data users' privacy) by allowing user data to be encrypted, transmitted to a cloud server, and searched using keywords. Despite its benefits, several recent real-world attacks have raised concerns about the security of searchable encryption. Ensuring forward and backward privacy is likely to become a standard requirement in the development of new SE systems. To address these issues, we propose a scheme that exclusively uses symmetric cryptographic primitives, achieving high communication efficiency and forward and backward privacy. In addition, we emphasize improved I/O efficiency because only the results of subsequent updates are loaded when searching. The time required to retrieve results is so significantly reduced compared to existing SE methods that we have shown that our scheme achieves superior efficiency. Moreover, by integrating blockchain network services with cloud services, we have developed a searchable intelligent cryptosystem suitable for lightweight smart devices. In our study conducted on the Ethereum network, we found our method to be both efficient and secure, especially when compared to methods such as PPSE and Jiang. The results indicate that our system delivers results in terms of performance and privacy within dynamic cloud environments making it a solution for protecting confidential information.

Faktor Anteseden yang Mempengaruhi Brand Trust dan Brand Loyalty pada Restoran Fastfood di Indonesia

The research findings and discussions indicate that advertising and social network service content have a positive impact on customer engagement and brand trust. Additionally, customer engagement also positively influences brand trust and brand loyalty. Thus, advertising, social network service content, and customer engagement are important precursor factors in building brand trust, which in turn affects brand loyalty. This highlights the importance of addressing and managing these aspects in marketing strategies to achieve long-term goals in building and maintaining customer loyalty. Keywords: Antecedent Factors, Brand Trust and Brand Loyalty of Fast Food Restaurants.

내현적 자기애, SNS 중독 경향성, 자기초점주의 및 대인관계능력의 구조적 관계

The purpose of this study is to investigate the relationship between covert narcissism, social network service addiction tendency, self-focused attention, and interpersonal ability. A structural equation model including the four variables was formulated based on previous studies. 324 middle school students who lived in Gyeongsangnam-do answered the survey and the data were analyzed. Results indicated that covert narcissism was positively related to SNS addiction tendency and self-focused attention, and negatively related to interpersonal ability. Also, self-focused attention and interpersonal ability had a mediation effect, respectively, in the relationship between covert narcissism and SNS addiction tendency. Lastly, all direct and indirect effects were verified in the paths from covert narcissism to SNS addiction tendency. Based on the results, the ways to support adolescent with SNS addiction were discussed.

Social Comparison on Social Networking Service and Social Isolation among Youth: The Mediating Role of Relative Deprivation and Moderating Effect of Victim Justice Sensitivity

Social Comparison on Social Networking Service and Social Isolation among Youth: The Mediating Role of Relative Deprivation and Moderating Effect of Victim Justice Sensitivity

ECONOMIC BENEFITS OF DEPLOYING FOLDABLE CONTAINERS: REDUCING BUNKER AND CONTAINER MANAGEMENT COSTS IN A MULTI-PORT SHIPPING NETWORK

This study seeks to explore the effectiveness of employing foldable containers (FLDs) in liner shipping to reduce relocation and the empty containers and bunker costs (BCs) associated with ship operations. This resolves a minimum-cost multi-commodity network flow problem by optimizing container fleet size and empty container relocation in a multi-port shipping service network. Port handling time and sailing speed provided by obtained optimal solutions enable the determination of ship BCs as a secondary step. The numerical experiments demonstrate the comparative effect of FLDs against standard ones on the reduction of the costs of empty containers and containership bunker oil.

A Novel intelligent SAV oriented QL-based task offloading in mobile edge environments

Edge computing is a novel and potential computing model which moves storage and computing capabilities to the network edge, substantially decreasing service latency and network traffic. The existing Internet of Things (IoT) network offloading algorithm faces limitations such as a fixed number of applications, high edge-to-edge delay, and reliance on a single Mobile Edge Computing (MEC) server, posing security and privacy concerns. Moreover, resource-constrained mobile devices need more effective data integration and compression strategies. Addressing these challenges, this study suggests an approach based on deep reinforcement learning (DRL), specifically the SAV (State Action Value) Oriented QL (Q-Learning) based Task Offloading method, to optimise task offloading and resource allocation in edge-cloud computing. The model aims to empower Mobile Devices (MDs) to develop optimal offloading decisions for long-term Quality Perception, utilising a neural network to establish the relationship between MD state and action value. The paper introduces a Recurrent Extended Memory Network (REMN) to capture dynamic workload behaviour at Edge nodes (ENs). It incorporates Quality Mapping, Quality Estimation, and a Quality-Aware DRL Task Offloading Algorithm to improve the accuracy and efficiency of the offloading procedure in MEC systems. This systematic approach improves overall system performance and enables MDs to leverage ENs for neural network training, reducing computational burdens. As a result, it can accomplish a more significant number of tasks, reducing latency from 0.74 ms to 7.168 ms and decreasing energy consumption from 270 J to 1820.39 J for tasks ranging from 10 to 50, respectively.

Anomaly Detection Integration-Framework for Network Services in Computer Education Systems

Public computer education systems provide students essential opportunities to enhance computer literacy and information skills. However, the widespread adoption of online education technology exposes the field to several critical security risks. Threats, such as malware infections, data breaches, and other network intrusions, are all challenging the security of education systems, posing potential hazards to students’ personal information and even the entire teaching environment. To spur further work into specialized anomaly detection techniques for computer education, this paper presents an anomaly detection framework tailored for network services in computer education environments to safeguard these systems. Specifically, the proposed approach learns from large-scale online educational traffic data to classify the security state into five alert levels, enabling more granular anomaly detection and analysis. To assess their detection performance, deep learning and traditional machine learning algorithms are implemented and compared for multi-class intrusion classification. The results show that the proposed framework provides an effective security solution to bolster the integrity and stability of computer education systems against evolving network threats, enhancing threat intelligence to inform proactive security by detecting and characterizing anomalies through multilevel classification.

The Development of a Named Entity Recognizer for Detecting Personal Information Using a Korean Pretrained Language Model

Social network services and chatbots are susceptible to personal information leakage while facilitating language learning without time or space constraints. Accurate detection of personal information is paramount in avoiding such leaks. Conventionally named entity recognizers commonly used for this purpose often fail owing to errors of unrecognition and misrecognition. Research in named entity recognition predominantly focuses on English, which poses challenges for non-English languages. By specifying procedures for the development of Korean-based tag sets, data collection, and preprocessing, we formulated directions on the application of entity recognition research to non-English languages. Such research could significantly benefit artificial intelligence (AI)-based natural language processing globally. We developed a personal information tag set comprising 33 items and established guidelines for dataset creation, later converting it into JSON format for AI learning. State-of-the-art AI models, BERT and ELECTRA, were employed to implement and evaluate the named entity recognition (NER) model, which achieved an 0.943 F1-score and outperformed conventional recognizers in detecting personal information. This advancement suggests that the proposed NER model can effectively prevent personal information leakage in systems processing interactive text data, marking a significant stride in safeguarding privacy across digital platforms.

Analysis of the Network, Staffing, and Activity of the Healthcare System and Cardiology Service of Kyiv Oblast

Providing high-quality cardiac care for the population is impossible without a thorough analysis of the number of healthcare facilities that can provide such services, the distribution of cardiologists and cardiovascular surgeons per appropriate number of the population, and proper monitoring of specialized examinations required for patients seeking such care. The aim. Getting inside the scope of the network, staffing, and activities of the healthcare system and cardiology service of Kyiv oblast. Materials and methods. Data on mortality, morbidity of the population, the structure of healthcare institutions, and the performance of the network of healthcare facilities of Kyiv oblast were the material of the study. The general scientific approach, i.e. synthesis, generalization, interpretation, system analysis, and medical statistics, was used to attain the aim. Results. The absence of cardiologists was noted in some territorial units of Kyiv oblast, either entirely or at certain time intervals. At the same time, the supply of cardiovascular surgeons was also inadequate. The dynamics of the number of beds in the region showed negative trends from 2018 to 2021. The increase in the workload of cardiac surgeons had a steady upward trend during 2018-2021, along with a peak number of operations and a statisticallysignificant correlation with an increase in patient mortality. The number of specialized cardiology examinations carried out for the population in the region is also insufficient. Conclusions. The network, staffing and activities of the cardiology service of Kyiv oblast do not meet the needs of the population and require a systematic approach to provide reforms at the level of the regional leadership to solve the issue of optimizing cardiac care for the population, taking into account the formation of local communities.

Building trust in cybernetic payment network: Insights from an emerging economy

This study investigates customers' trust and behavioural intentions regarding the use of cybernetic payment network services in an emerging country, focusing on perceived quality, system quality, and perceived image. Data from 324 respondents in Bangladesh were collected via a self-administered Google survey form distributed through email, WhatsApp, and Messenger using purposive sampling. The SmartPLS-4 software was used to assess construct validity and hypothesized path coefficients. Results indicate that perceived quality, system quality, and image significantly influence perceived trust in cybernetic payment network services. Additionally, perceived trust and system quality positively impact behavioural intention to use these services. Furthermore, perceived trust mediates the relationship between behavioural intention and system quality, perceived quality, and image. The study underscores the importance for cybernetic payment network service providers to enhance perceived quality, system quality, and perceived image to foster trust and promote adoption. It highlights the pivotal role of trust in driving customers' intention to adopt these services, urging providers to prioritize efforts in building trust among users. This study contributes to the limited literature on the impact of perceived quality, system quality, and perceived image on customers' inclination to use cybernetic payment network services, offering valuable insights for bank managers and policymakers to formulate effective strategies for sustaining innovation and enhancing adoption rates.

Intelligent decision modeling for optimizing railway cold chain service networks under uncertainty

Railway cold chain service network design (RCC-SND) aims to optimize the utilization of stations and lines as well as train allocations in a manner that minimizes costs while satisfying the service requirements of shippers. Furthermore, the uncertainties associated with freight demand, transportation costs, quality loss, station handling capacity, and arc capacity make the RCC-SND a complex decision-making problem. To tackle this challenge, we first formulate a Mixed-Integer Nonlinear Programming (MINLP) model to determine hub locations, freight wagon flows, and service frequency. To cope with uncertain parameters with varying degrees of uncertainty incorporated in the model, we extend the problem using fuzzy programming and further convert it to its crisp counterpart. A real-world cases study in Southwest China is performed to validate the proposed model, whose results provide different strategies for decision-makers with varying preferences. There are some main findings: As the number of hubs increases from 5 to 6, a maximum total cost savings of 1.99% can be achieved. Railway operators may opt for different decision preferences, for decisions prioritizing economic efficiency, the cost can decrease by 2.69% compared to deterministic optimization.

Analysis of the Application of Artificial Intelligence in Computer Network Technology

The application of artificial intelligence (AI) technology in computer network technology is becoming increasingly extensive and in-depth. This paper analyzes the application of artificial intelligence in network security, network management, Internet of Things, edge computing and network services in detail. In network management, AI technology realizes network traffic optimization, automatic configuration and fault prediction, and improves the efficiency of network management. In the field of Internet of Things, AI technology helps manage and analyze a large amount of device data, supporting the development of smart homes and smart cities. In edge computing, AI technology enhances the data processing capabilities of edge nodes and reduces latency. In network services, artificial intelligence technology optimizes routing, voice recognition and personalized recommendation services. However, the application of artificial intelligence in network technology also faces challenges such as data privacy, computing resources and laws and regulations. This paper aims to provide a comprehensive reference for industry insiders to promote the application and development of artificial intelligence technology in computer networks.