In-service Research Articles

Intelligent Bayesian Neural Networks for Stochastic SVIS Epidemic Dynamics: Vaccination Strategies and Prevalence Fractions with Wiener Process

Real-time forecasting of infectious diseases is crucial for effective public health management, particularly during outbreaks. When infectious disease predictions are based on mechanistic models, they can guide resource allocation and help evaluate the potential effects of different interventions. However, accurately parametrizing these models in real time presents a challenge, as timely information on behavioral shifts, interventions and transmission pathways is often lacking. This investigation leverages the artificial neural networks with the Bayesian regularization (BR-ANN) backpropagation approach to examine the dynamical pathogen spread with Wiener process incorporation. The stochastic differential model is structured into susceptible, vaccinated, infectious and susceptible (SVIS) compartments. The Kloeden–Platen–Schurz (KPS) computing paradigm for the stochastic differential system is utilized to generate synthetic datasets by applying transformations to key factors, including the population recruitment ratio, transmission ratio of vulnerable individuals, natural death rate of the population, vaccination rate of vulnerable individuals, total population size, immune loss ratio of susceptible individuals, recovery rate and mortality rate from the disease among infected individuals. Random selection from the generated datasets is exploited for the training and testing procedures for constructing the BR-ANN networks. The significance of the proposed scheme for various stochastic SVIS system scenarios is endorsed by the comprehensive assessments of the BR-ANN approach that are conducted by means of extensive experimentations and comparison with the reference KPS solutions of the SVIS system in terms of MSE optimal performance plots, absolute errors, autocorrelation analysis, regression indices and error histograms.

A two-tier optimization strategy for feature selection in robust adversarial attack mitigation on internet of things network security

Adversarial attacks were commonly considered in computer vision (CV), but their effect on network security apps rests in the field of open investigation. As IoT, AI, and 5G endure to unite and understand the potential of Industry 4.0, security events and incidents on IoT systems have been enlarged. While IoT networks efficiently deliver intellectual services, the vast amount of data processed and collected in IoT networks also creates severe security concerns. Numerous research works were keen to project intelligent network intrusion detection systems (NIDS) to avert the exploitation of IoT data through smart applications. Deep learning (DL) models are applied to perceive and alleviate numerous security attacks against IoT networks. DL has a considerable reputation in NIDS, owing to its robust ability to identify delicate differences between malicious and normal network activities. While a diversity of models are aimed at influencing DL techniques for security protection, whether these methods are exposed to adversarial examples is unidentified. This study introduces a Two-Tier Optimization Strategy for Robust Adversarial Attack Mitigation in (TTOS-RAAM) model for IoT network security. The major aim of the TTOS-RAAM technique is to recognize the presence of adversarial attack behaviour in the IoT. Primarily, the TTOS-RAAM technique utilizes a min-max scaler to scale the input data into a uniform format. Besides, a hybrid of the coati–grey wolf optimization (CGWO) approach is utilized for optimum feature selection. Moreover, the TTOS-RAAM technique employs the conditional variational autoencoder (CVAE) technique to detect adversarial attacks. Finally, the parameter adjustment of the CVAE model is performed by utilizing an improved chaos African vulture optimization (ICAVO) model. A wide range of experimentation analyses is performed and the outcomes are observed under numerous aspects using the RT-IoT2022 dataset. The performance validation of the TTOS-RAAM technique portrayed a superior accuracy value of 99.91% over existing approaches.

Routing Protocol for Intelligent Unmanned Cluster Network Based on Node Energy Consumption and Mobility Optimization

Intelligent unmanned clusters have played a crucial role in military reconnaissance, disaster rescue, border patrol, and other domains. Nevertheless, due to factors such as multipath propagation, electromagnetic interference, and frequency band congestion in high dynamic scenarios, unmanned cluster networks experience frequent topology changes and severe spectrum limitations, which hinder the provision of connected, elastic and autonomous network support for data interaction among unmanned aerial vehicle (UAV) nodes. To address the conflict between the demand for reliable data transmission and the limited network resources, this paper proposes an AODV routing protocol based on node energy consumption and mobility optimization (AODV-EM) from the perspective of network routing protocols. This protocol introduces two routing metrics: node energy based on node degree balancing and relative node mobility, to comprehensively account for both the balance of network node load and the stability of network links. The experimental results demonstrate that the AODV-EM protocol exhibits better performance compared to traditional AODV protocol in unmanned cluster networks with dense node distribution and high mobility, which not only improves the efficiency of data transmission, but also ensures the reliability and stability of data transmission.

The Role of Learning Analytics in Evaluating Course Effectiveness

This study aims to examine the use of learning analytics in course evaluation within higher education institutions, in order to identify effective methodologies and best practices for leveraging data to improve educational effectiveness. Following the PRISMA guidelines, a systematic literature search was conducted in Scopus, yielding 34 relevant studies published between 2015 and 2024 for analysis. The results reveal six key categories of learning analytics applications: sentiment analysis, questionnaire analysis, engagement analysis, topic classification, predictive modelling, and performance analysis. The data sources for learning analytics applications primarily include questionnaires and learning management systems. While descriptive analysis was found to be the most commonly employed analytical technique, advanced techniques such as machine learning, artificial intelligence, and social network analysis are becoming more prominent. The studies addressed a wide range of elements associated with course evaluation, including course design, content quality, assignments, instructional strategies, workload, feedback mechanisms, and the integration of technology. These findings highlight the importance of adopting holistic approaches to capture the multifaceted nature of student experiences. This study also uncovers major limitations in the existing research, such as small sample sizes, potential biases due to the use of survey-based methods, and challenges in generalising findings across disciplines. These insights underscore the need for further research to enhance the methodologies used in course evaluations. This study contributes to advancing learning analytics practices and emphasises the importance of innovative approaches for evaluating and improving course effectiveness.

Intelligent technologies in traffic flow control: a review

With the acceleration of global urbanization, traffic congestion has become a major bottleneck in the development of modern cities, leading to serious economic losses and a decline in the quality of life. To address this challenge, traffic flow prediction techniques have received much attention. This paper reviews the application of three key technologies, including 5G, artificial intelligence (AI), and vehicular networking (V2X) in intelligent traffic management. 5G technology provides a communication foundation with high speed rates, low latency, and large-scale device connectivity, which effectively supports real-time data transmission and communication needs. AI technology, on the other hand, with its powerful data processing capability, is able to make high-precision traffic predictions in dynamic traffic environments. However, the effectiveness of AI models is highly dependent on the support of high-quality data.V2X technology greatly improves road safety and traffic mobility by realizing real-time information exchange between vehicles and infrastructure. However, relying on a single technology alone cannot comprehensively solve complex transportation problems. For this reason, this paper proposes a technology fusion scheme of 5G, AI, and V2X, aiming to optimize the intelligence level of the traffic management system through the complementary advantages of each technology. The study shows that the synergistic application of the technologies can not only effectively alleviate traffic congestion but also improve the overall safety of roads, providing a feasible solution for the future intelligent transportation system in cities.

Technical and economic feasibility analysis of a subsea shuttle tanker for CO2 transport to the troll field

The Subsea Shuttle Tanker (SST) was presented by the authors as an innovative and cost-effective solution in several research works. This new approach offers a viable alternative to subsea pipelines and shuttle tanker ships for transporting liquid CO2 from onshore facilities to marginal offshore reservoirs. A previous technical–economic feasibility study found that the SST is generally economically competitive to the subsea pipelines and shuttle tanker ships for distances below 180 km and CO2 transport volumes of one million tons per annum (mtpa). The economic cost models are based on those developed in Maritime UN-manned Navigation through Intelligence in Network (MUNIN) D 9.3 and the Zero Emission Platform (ZEP) projects. This paper will take this previous study further by focusing on performing the technical and economic feasibility analysis for operation in the Troll field on the Norwegian continental shelf (NCS), which has a transport distance of 65 km and a CO2 volume of 1.5 mtpa. Two SST design solutions are investigated by downscaling and upscaling the reference baseline design to evaluate SST’s technical feasibility. Using the abovementioned cost models, the CO2 transportation cost per ton using SST is compared with subsea pipelines and tanker ships. The numerical results show that it is economically feasible to manufacture SST with cargo capacities of 4453 m3 and 2203 m3. Furthermore, the results show that the SST is the most cost-effective option for transporting low-volume CO2 (1.5 mtpa) over short distances.

Applications of Artificial Intelligence in Computer Vision and Network Fields

The rapid development of artificial intelligence (AI) technology has sparked a wave of innovation in the fields of computer vision and networks. This paper explores the applications of AI in image recognition, deep learning, network security, and intelligent network management, systematically reviewing the integration of computer vision and network innovations. It also highlights key application scenarios, such as multimodal data fusion and edge computing. Additionally, this paper addresses challenges such as data privacy, computational resource demands, and model optimization, and forecasts the future potential of AI in creating intelligent vision and network systems. This research provides theoretical support and guidance for further exploration of AI’s integration and innovation in computer vision and network fields.

Vulnerability analysis of power grid structure based on complex network theory

IntroductionThe key nodes of an intelligent distribution network significantly impact the reliability and stability of the distribution network’s operation. The failure of these key nodes can severely affect the safe operation of the distribution network. Therefore, vulnerability analysis of key nodes is particularly important.MethodsThis article proposes a comprehensive weighting method for evaluating indicators,combining the analytic hierarchy process (AHP) and entropy weighting method, while considering the structure and operational status of the power system grid. Key node structural evaluation indicators, such as node degree, node shrinkage centrality, and electric mediator, are established considering “significance” and “destructiveness.” State indicators are established based on the degree of impact of current, voltage, and load changes on the grid, as well as the uniformity of their distribution, including the improved current distribution entropy, voltage terre entropy, and three-phase state indicators of lost load. Subsequently, based on the AHP and entropy weighting method, a comprehensive weighting method is proposed to assign subjective and objective weights to the comprehensive evaluation indicators, obtaining the comprehensive weights of the indicators. Finally, the gray correlation degree is introduced to improve the ideal solution of the multi-objective decision making method, obtaining the criticality of the grid nodes and then identifying the critical nodes.Results and DiscussionThe example analysis presented in this article shows that the identified critical nodes of the power grid have a high degree of overlap with the identification results of different methods, can better identify edge nodes, and validate the effectiveness of the proposed evaluation indicators and key node identification methods.

Application of Artificial Intelligence for Diagnosing Tumors in the Female Reproductive System: A Systematic Review

The diagnosis of tumors in the female reproductive system is crucial for effective treatment and patient outcomes. The advent of artificial intelligence (AI) has introduced new possibilities for enhancing diagnostic accuracy and efficiency. A comprehensive search across PubMed, Scopus, and Web of Science for articles published from 2018 to 2023 on artificial intelligence (AI), machine learning (ML), deep learning (DL), and convolutional neural networks (CNN) in diagnosing cancers of the female reproductive system yielded 15,900 articles. After a rigorous screening process excluding conference proceedings, book chapters, reports, non-English publications, and duplicates, 98 unique peer-reviewed journal articles remained. These were further assessed for relevance and quality, resulting in the final inclusion of 29 high-quality articles. The review includes a summary of various AI methodologies used, their diagnostic accuracy, and comparative performance against traditional diagnostic methods. The findings indicate a significant improvement in diagnostic precision and efficiency when AI is employed. AI holds substantial promise for enhancing the diagnosis of tumors in the female reproductive system. Future research should focus on larger-scale studies and the integration of AI into clinical workflows to fully realize its potential

Intelligent back-propagated neural networks to study nonlinear heat transfer in tangent-hyperbolic fluids

Intelligent back-propagated neural networks to study nonlinear heat transfer in tangent-hyperbolic fluids

Analysis of flood severity using intelligent deep networks and sentinel image for the Kerala region

Analysis of flood severity using intelligent deep networks and sentinel image for the Kerala region

Intelligent Control of the Dynamic Voltage Restorer for Fault Ride through Capability Enhancement of a Grid-connected Photovoltaic Power Plant in accordance with Recent Moroccan Grid Code

Background: The recent development of small-scale, decentralized generation from renewable sources and the fall in the price of the equipment needed for this operation have given a new role to the distribution networks, which is to collect the energy produced by the smallest generation plants and deliver it to the end customers. However, the national Grid Codes present technical requirements in terms of FRT and particularly LVRT and HVRT which are imposed on PV plants connected to medium voltage distribution networks, to ensure the energy needed by the loads connected to the network at the time of the failure and especially sensitive ones. Methods:: In this paper, an intelligent neural network approach is applied to the DVR control circuit to enable the requirements of the sensitive load connected near the PCC, and the system is tested in the presence of a non-linear load to demonstrate its efficiency for all situations. The proposed strategy is based on the implementation of an improved ANFIS and ANN control which are compared to a tuned PI controller, the approach intends to meet the technical requirement of the recently approved Grid Code in Morocco. The simulation is performed using MATLAB Simulink. Results: The proposed approach brings great improvement to the load side voltage waveforms, and numerical experiment findings demonstrate that it can successfully guarantee the technical requirements of the electrical grid code. Conclusion: The results obtained show better behavior of the system using ANFIS and ANN control strategy in the presence of a nonlinear load and a significant improvement of the voltage THD.

End-to-end latency upper bounds and service chain deployment algorithm based on industrial internet network

The diverse service requests in industrial Internet networks require flexible and efficient service chain deployment to ensure the quality of service (QoS). However, current deployment algorithms for service chains are primarily designed to guarantee only low end-to-end latency; they often overlook the amount of service chains that can be accommodated by the network and could lead to severe network load imbalances, significantly reducing service efficiency and causing serious network congestion issues. To address the above issues, we develop a mathematical model of the network topology and service request chains by integrating Network Function Virtualization (NFV) and Software Defined Networking (SDN). Utilizing network calculus theory, we derive the upper bound of end-to-end delay for service chain routing and analyzed the relationship between the upper bound of service chain routing delay and the resource allocation of Virtual Network Function (VNF) nodes. Based on the aforementioned model, we propose a novel service chain deployment algorithm named the Delay-Aware Load-Balanced Routing Algorithm (DLBRA). DLBRA comprehensively considers network traffic load balancing and end-to-end latency of service chains, rationally allocating VNF node resources to complete the determined service chain routing deployment. Experimental results indicate that, compared to the shortest path and load balancing algorithms, DLBRA not only ensures that the end-to-end delay of the service chain meets its QoS requirements, but also effectively reduces network load imbalance, significantly increasing the number of service chain requests that the network can accommodate. Additionally, DLBRA provides tailored deployment guidance for different types of service chains, such as latency-sensitive and data-intensive service chains, ensuring optimal utilization of network resources. This algorithm enhances the efficiency of service chain deployment in industrial internet scenarios and possesses broad application potential in other network environments where delay optimization and load balancing are critical, such as intelligent transportation, cloud computing, and 5G networks.

Signal Detection in Intelligent Reflecting Surface-Assisted NOMA Network Using LSTM Model: A ML Approach

Signal Detection in Intelligent Reflecting Surface-Assisted NOMA Network Using LSTM Model: A ML Approach

Toward 6G: An Overview of the Next Generation of Intelligent Network Connectivity

Toward 6G: An Overview of the Next Generation of Intelligent Network Connectivity

Intelligent Network Selection Mechanisms in the Internet of Everything System

Intelligent Network Selection Mechanisms in the Internet of Everything System

Artificial Intelligence, Cybersecurity, and Human Trafficking Networks

This study aimed to examine the role of artificial intelligence (AI) in dealing with human trafficking by analyzing social networks. Human trafficking is a global concern that exists in the anonymity of social connections and online platforms. There are important transformative tools that facilitate the identification and disruption of trafficking networks, including AI techniques like natural language processing, social network analysis, and machine learning. The study tests AI applications, ethical considerations, and cybersecurity measures that importantly safeguards data integrity and promotes the efficacy of AI-driven systems. The outcomes of the study show the potential of AI in pattern recognition, network mapping, and predictive analytics to support law enforcement and advocacy groups.

The IoV Meets Open RAN: An O-RAN-based IoV Architecture

The race towards a better-connected world has led to innovations in network connectivity and the embedding of intelligence into various types of devices. Intelligent devices require an intelligent network infrastructure and design in order to reach their maximum potential. Recently, the concept of Open Radio Access Networks (Open RAN, O-RAN) has gained a lot of attention with the formation of the O-RAN Alliance which seeks to usher in the next phase of cellular network interoperability, intelligence and design. Another key concept that has emerged in recent years is the Internet of Vehicles (IoV) which has been described as a driver for next generation Intelligent Transportation Systems (ITS). This paper proposes an architecture that brings together these two concepts and explores how the design principles of the O-RAN can be incorporated into the IoV by using a bottom-up approach. It also discusses the benefits of an O-RAN-based IoV, some perceived challenges with its implementation and the way forward.

6G autonomous radio access network empowered by artificial intelligence and network digital twin

AbstractThe sixth-generation (6G) mobile network implements the social vision of digital twins and ubiquitous intelligence. Contrary to the fifth-generation (5G) mobile network that focuses only on communications, 6G mobile networks must natively support new capabilities such as sensing, computing, artificial intelligence (AI), big data, and security while facilitating Everything as a Service. Although 5G mobile network deployment has demonstrated that network automation and intelligence can simplify network operation and maintenance (O&M), the addition of external functionalities has resulted in low service efficiency and high operational costs. In this study, a technology framework for a 6G autonomous radio access network (RAN) is proposed to achieve a high-level network autonomy that embraces the design of native cloud, native AI, and network digital twin (NDT). First, a service-based architecture is proposed to re-architect the protocol stack of RAN, which flexibly orchestrates the services and functions on demand as well as customizes them into cloud-native services. Second, a native AI framework is structured to provide AI support for the diverse use cases of network O&M by orchestrating communications, AI models, data, and computing power demanded by AI use cases. Third, a digital twin network is developed as a virtual environment for the training, pre-validation, and tuning of AI algorithms and neural networks, avoiding possible unexpected losses of the network O&M caused by AI applications. The combination of native AI and NDT can facilitate network autonomy by building closed-loop management and optimization for RAN.

Management of the technical condition of agricultural machinery using digital technologies

The studies were conducted to substantiate the development of devices and software for managing the technical condition of agricultural machinery using elements of artificial intelligence. The use of artificial intelligence makes it possible to implement a strategy for predictive maintenance and repair of C3 equipment – an integrated approach that allows you to determine the condition of a machine in operation and estimate when maintenance should be carried out. To do this, it is necessary to develop electronic diagnostic devices and sensors that can be combined into a single intelligent information complex that allows you to quickly collect and process large amounts of data on the parameters of the technical condition of agricultural machinery through the use of artificial intelligence. The object of the study is the hydromechanical gearbox of the Kirovets tractor for agricultural and industrial purposes. In 2022–2024, developed data collection devices, software and methods for assessing the technical condition of machines using artificial intelligence and neural network algorithms, and also described the manufactured digital diagnostic devices. Using the example of analyzing the operating parameters of the hydromechanical gearbox of the Kirovets tractor, the introduced concept of technical condition is specified, which consists in calculating the Yn parameter using a neural network, characterizing the nominal, permissible, limiting or emergency technical condition, and establishing recommendations to the owner on the type of possible work and service. Thanks to monitoring and analyzing the operating parameters of the gearbox using AI and continuous updating of the technical condition, technical maintenance and repair are carried out in a timely manner, which ensures technical condition management and increased reliability of agricultural machinery, minimizes failures and related equipment downtime.