Network Utilization Research Articles

Enhanced anomaly network intrusion detection using an improved snow ablation optimizer with dimensionality reduction and hybrid deep learning model

With the enlarged utilization of computer networks, security has become one of the critical issues. A network intrusion by malicious or unauthorized consumers may cause severe interruption to networks. So, the progress of a strong and dependable network intrusion detection system (IDS) is gradually significant. Intrusion detection relates to a suite of models employed to recognize attacks against network infrastructures and computers. There are dual main intrusion detection models, such as misuse and anomaly detection. Anomaly detection is a central part of intrusion detection in which disruptions of normal behaviour propose the presence of unintentionally or intentionally induced attacks, defects, faults, etc. With the arrival of anomaly-based IDS, many models have progressed in tracking new threats to the systems. Machine learning (ML) and deep learning (DL) models are currently leveraged for anomaly intrusion detection in cybersecurity. This manuscript proposes an Enhanced Anomaly Intrusion Detection using an Optimization Algorithm with Dimensionality Reduction and Hybrid Model (EAID-OADRHM) technique. The proposed EAID-OADRHM technique presents a new approach for perceiving and migrating attacks in cybersecurity. Min–max scaling normalization is primarily employed at the data pre-processing level to clean and transform input data into a consistent range. Furthermore, the proposed EAID-OADRHM technique utilizes the equilibrium optimizer (EO) model for the dimensionality reduction process. Additionally, the classification is performed by employing the long short-term memory and autoencoder (LSTM–AE) model. Finally, the improved Snow Ablation Optimizer (ISAO) model optimally tunes the hyperparameters of the LSTM–AE model, leading to enhanced classification performance. The simulation validation of the EAID-OADRHM approach is examined under the CIC-IDS2017 dataset, and the outcomes are computed using numerous measures. The experimental assessment of the EAID-OADRHM approach portrayed a superior accuracy value of 99.46% over existing methods in the anomaly intrusion detection process.

CFD-Guided Design of Non-Uniform Flow Channels in PEMFCs for Waste Heat Utilization in District Heating Networks

Proton exchange membrane fuel cells (PEMFCs), recognized as promising sources of waste heat for space heating, domestic hot water supply, and industrial thermal applications, have garnered substantial interest owing to their environmentally benign operation and high energy conversion efficiency. Since the uniformity of oxygen diffusion toward catalytic layers critically governs electrochemical performance, this study establishes a three-dimensional, non-isothermal computational fluid dynamics (CFD) model to systematically optimize the cathode flow channel width distribution, targeting the maximization of power output through enhanced reactant homogeneity. Numerical results reveal that non-uniform flow channel geometries markedly improve oxygen distribution uniformity, reducing the flow inhomogeneity coefficient by 6.6% while elevating maximum power density and limiting current density by 9.1% and 7.8%, respectively, compared to conventional equal-width designs. There were improvements attributed to the establishment of longitudinal oxygen concentration gradients and we alleviated mass transfer limitations. Synergistic integration with gas diffusion layer (GDL) gradient porosity optimization further amplifies performance, yielding a 12.4% enhancement in maximum power density and a 10.4% increase in limiting current density. These findings validate the algorithm’s efficacy in resolving coupled transport constraints and underscore the necessity of multi-component optimization for advancing PEMFC design.

Brain Tumor Detection from MRI Images using Enhanced Transfer Learning

Brain tumor detection is vital for the diagnosis and treatment of one of the most lethal diseases in both children and adult. Traditional ways of analyzing brain tumour include reviewing Magnetic Resonance Imaging (MRI) images and interpreting results manually by radiologists; this technique has several problems including; complexity of the tumour type, size and location of the tumours may complicate the results of the analysis. Due to this, the above challenges are even more challenging to overcome in areas of scarcity of qualified human resource in healthcare. This study aims at suggesting a novel approach to resolve these challenges together with the utilization of Convolutional Neural Network (CNN) models such as EfficientNet-B2, Xception, Xception with Attention Mechanism. This paper is presented based on how these models can be employed in the classification and detection of the presence of brain tumours; these findings has seen the Xception with Attention Mechanism model register the highest accuracy at 95% among all the employed models. The refinement of the researchers’ strategy is as follows, notably Synthetic Minority Over-sampling Technique (SMOTE) which caters for the issues of class imbalance in the set data. In addition to performing better than conventional non-automated techniques, the system provides a reliable solution for the detection of brain tumors that can be applied globally, benefiting physicians, particularly those to from developing countries, determine the patient’s condition and choose the right treatment plan. Automated medical testing also means that the results are delivered quickly and with greater accuracy also resulting to positive outcomes for the patients.

Simultaneous prediction of porosity, saturation, and lithofacies from seismic data via multi-task deep learning

Prediction of reservoir parameters, including porosity, gas saturation, and lithofacies, from seismic data is of great significance for hydrocarbon reserves evaluation, reservoir quality assessment, and geological model building. Multi-task learning exhibits robust capabilities in simultaneously predicting multiple related parameters, which is desirable for estimating multi-reservoir parameters from seismic data. We propose the utilization of a seismic multi-reservoir parameter prediction network based on multi-task learning (SeisMRMTNet) informed by joint data distribution and physical constraints for the simultaneous inversion of porosity, gas saturation, and lithofacies. The SeisMRMTNet comprises two essential components: a shared feature extraction network and three task-specific networks. These networks adopt a three-dimensional sequence-to-sequence prediction paradigm to capture spatial features, hence improving seismic prediction stability. The shared feature extraction network extracts and maintains shared features between reservoir parameters and seismic information through the hard-sharing mechanism. Then, three task-specific networks establish nonlinear relationships between the shared features and the three different parameters, respectively. We incorporate physical constraints between reservoir parameters and integrate them into the network’s feature layer. Simultaneously, a two-dimensional joint data distribution constraint is applied between the predicted and actual values of gas saturation and porosity, which is incorporated into the loss function for optimization. The blind well tests on a deep heterogeneous carbonate reservoir demonstrate that the SeisMRMTNet achieves systematic improvement in prediction accuracy and better generalization performance compared to single-task learning. In particular, SeisMRMTNet can more effectively characterize formations where porosity and saturation vary significantly. Furthermore, SeisMRMTNet enhances the geological consistency and plausibility of reservoir prediction, yielding more reasonable results and data distribution for seismic reservoir characterization.

Utilisation of Deep Neural Networks for Estimation of Cajal Cells in the Anal Canal Wall of Patients with Advanced Haemorrhoidal Disease Treated by LigaSure Surgery.

Interstitial cells of Cajal (ICCs) play a key role in gastrointestinal smooth muscle contractions, but their relationship with anal canal function in advanced haemorrhoidal disease (HD) remains poorly understood. This study uses deep neural network (DNN) models to estimate ICC presence and quantity in anal canal tissues affected by HD. Haemorrhoidectomy specimens were collected from patients undergoing surgery with the LigaSure device. A YOLOv11-based machine learning model, trained on 376 immunohistochemical images, automated ICC detection using the CD117 marker, achieving a mean average precision (mAP50) of 92%, with a recall of 86% and precision of 88%. The DNN model accurately identified ICCs in whole-slide images, revealing that one-third of grade III HD patients and 60% of grade IV HD patients had a high ICC density. Preoperatively, pain was reported in 35% of grade III HD patients and 41% of grade IV patients, with a significant reduction following surgery. A significant decrease in bleeding (p < 0.0001) was also noted postoperatively. Notably, patients with postoperative bleeding, diagnosed with stage IV HD, had high ICC density in their anorectal tissues (p = 0.0041), suggesting a potential link between ICC density and HD severity. This AI-driven model, alongside clinical data, may enhance outcome prediction and provide insights into HD pathophysiology.

Equivalence of electronic health record data for measuring hypertension prevalence: a retrospective comparison to BRFSS with data from two Indiana health systems, 2021

BackgroundPublic health surveillance requires timely access to actionable data at every level. Current approaches for accessing chronic disease surveillance data are not sufficient, and health departments are increasingly looking to augment surveillance efforts using electronic health records (EHRs). While proven effective for acute syndromic surveillance, the utilization of EHR systems and health data networks for monitoring chronic conditions remains sparse. This study tested the generalizability of a previously validated hypertension computable phenotype.MethodsA previously developed phenotype was used to estimate prevalence of hypertension in a geographically and clinically distinct region from its development. To test validity, the results were compared to available, statewide Behavioral Risk Factor Surveillance System (BRFSS) data using the two one-sided t-test (TOST) of equivalence between BRFSS- and EHR-based prevalence estimates. The TOST was performed at the overall level as well as stratified by age, gender, and race/ethnicity.ResultsCompared to statewide hypertension prevalence of 34.5% in the BRFSS, an EHR-based phenotype estimated an overall prevalence of 24.1%. Estimates were not equivalent overall or across most subpopulations. Like BRFSS, we observed higher prevalence among Black men and women as well as increasing prevalence with age.ConclusionWith caveats, this study demonstrates that EHR-derived prevalence estimates may serve as a complement for population-based survey estimates. Utilizing available EHR data should increase timeliness of surveillance as well as enhance the ability of states and local health agencies to more readily address the burden of chronic disease in their respective jurisdictions.

Intelligent Fraud Detection in IoT-Driven Transactions Using Multi-Layer Neural Classification

When individuals conduct financial fraud in an Internet of Things (IoT) environment, it is because they have stolen the identity of another person or their credit card information and then utilised it to make fraudulent mobile transactions. Within the context of the IoT, financial fraud is a problem that is rapidly developing as a result of the growth of smartphones and internet transition services. Because financial fraud leads to monetary loss, it is necessary to have a system that is accurate for identifying financial fraud in an IoT environment. This is because financial fraud occurs in the real world. In the context of the IoT, there is an urgent requirement for a trustworthy system that can identify instances of financial fraud. This is because the use of smartphones and online transactions has become increasingly widespread. Our proposed method, which makes use of deep multi-layer classification, is comprised of two essential steps: first, we need to identify the presence of an intrusion; second, we need to identify the sort of intrusion that has occurred. In order to efficiently extract features, we make use of a technique known as Synthetic Minority Oversampling Technique (SMOTE), which results in an improvement in the classification accuracy. The foundation of our research is the utilisation of a Multiple-hidden Layer Backpropagation Neural Network (BPNN) for the purpose of distinguishing between routine operations and actions that include intrusion. Considering the multi-pronged approach ensures any potential risks is achieved. By merging these approaches into a robust and accurate fraud detection system, we have made a substantial contribution to the field.

Coexistence in Wireless Networks: Challenges and Opportunities

The potential consequences of interference on communication networks are one of the main challenges in the nature and efficiency of wireless communication links. The interruption is seen as additional noise to the device, which can have a major impact on the efficiency of the connection. The rapid expansion of broadband wireless networks and the increasing congestion of the radio frequency spectrum due to shared usage by terrestrial and satellite networks have heightened concerns about potential interference. To optimize spectrum utilization, multiple terrestrial and satellite networks often coexist within the same frequency bands allocated for satellite communications services. Spectrum interference in wireless networks is a topic of much interest in the current scenario as it can present a lot of challenges. This article provides a critical review of the coexistence and spectrum sharing in wireless networks. Along with this, mitigation techniques to avoid interference have also been discussed in detail. The article aims to give a detailed discussion on the challenges and opportunities in this field by reviewing significant recent works in this field.

Teaching learning based optimization algorithm for effective analysis of power quality using dynamic voltage restorer

In this study, the load voltage is dynamically restored utilising the dynamic voltage restorer (DVR) using the voltage injection approach. The injected voltage is generated using a voltage-source inverter (VSI), which is necessary to correct for the utility network's sag and swell characteristics voltage. The restoration process is dependent on the condition and quality of the utility system, i.e., it injects energy into the external system for the duration of voltage sag, and during voltage swell, energy is absorbed by the compensator from the external system, causing an rise in dc link voltage, which is connected across the VSI. In this study two different controllers are employed based on a learning based optimized algorithm. The simulation results are shown using two different controllers and the performance of the proposed controller is found to be a better one.

Planning a robust echelon utilization network for used electric vehicle batteries based on two decision-making criteria

Planning a robust echelon utilization network for used electric vehicle batteries based on two decision-making criteria

국가교육위원회 설치와 연구·개발형 국가교육과정 개발에 대한 재고

Purpose: This study aims to reconsider the existing research &amp; development curriculum development system according to the establishment and operation of the National Board of Education. Method: Literature analysis mainly focused on legal systems and notices for the establishment of the National Board of Education and the operation of sub-organizations. Results: The research results were divided into social consensus, establishment and change planning and notification stages, operation and feedback stages such as investigation, analysis, and inspection, network utilization, and establishment and operation of a consultative body as a voluntary organization to reconsider the research and development curriculum. Conclusion: Through discussions for the use of various organizations within the institutional framework set out in the National Education Commission Establishment and Operation Act and the Enforcement Decree of the Act, it is necessary to prepare a method and model for participation and consensus of the subjects related to the national curriculum.

Optimizing Power Losses and Voltage Profiles through Simultaneous Distribution Network Reconfiguration and DG Placement Using a Hybrid CDOA-PSO Algorithm

The optimal utilization of distribution networks through network reconfiguration has become increasingly critical in modern power systems, primarily due to the extensive integration of Distributed Generation (DG) resources. Strategically positioning and scaling distributed generation optimizes the equilibrium of energy provision and consumption, diminishes electrical losses, and elevates the voltage profile. Previous studies have predominantly concentrated on either DG optimization or distribution network reconfiguration, with limited research conducted on their simultaneous application. Therefore, this paper employs three meta-heuristic algorithms: the Collective Decision-Based Optimization Algorithm (CDOA), Particle Swarm Optimization (PSO), and a hybrid optimization algorithm termed CDOA-PSO, to concurrently address network reconfiguration alongside the optimal placement and sizing of DG. The suggested technique is applied to a 33-bus radial distribution network as per IEEE standards, utilizing MATLAB for execution. To assess the efficacy of the technique, six unique scenarios have been utilized. The results clearly demonstrate a substantial enhancement in the voltage profile and a decrease in power losses with the hybrid algorithm (CDOA-PSO) compared to both CDOA and PSO.

Topology and density control of satellite-defined photonic quantum networks

Creating photonic quantum networks by distributing entangled photon pairs through low Earth orbit satellites is a promising technological advance. A recent work has studied a model of such networks and reported the presence of a heavy-tailed degree distribution. This heterogeneous structure is highly undesirable when it comes to the quantum memory utilization efficiency and network robustness under malicious attack. In this work, however, we show that such a topology is not necessarily inherent to satellite-based quantum networks. We theoretically analyze factors that determine the connection probability between two nodes and propose a principled design methodology to control both the topology and density of the resulting network. We present numerical evidence that our method can continuously transform the heterogeneous heavy-tailed network into a more homogeneous Erdős-Rényi-like random network with the prescribed level of density as characterized by the average or maximal degree. Such results are in good agreement with our theoretical analysis, which not only predicts the qualitative structural transition but also provides a quantitative way to estimate important network features during the process. Under our control strategies, the resulting network can achieve various desirable properties, such as a short path length and diameter, high quantum memory utilization efficiency, and enhanced robustness against attack. We believe the design principle proposed in this work represents an important step towards building and controlling functionally efficient satellite-photonic quantum networks in the future. Published by the American Physical Society 2025

Hybrid Metaheuristic Optimization Algorithms for Energy Aware Fine Cluster Head based Routing in Wireless Sensor Networks

Wireless Sensor Networks (WSNs) and their applications reduce energy consumption to extend sensor node lifetime. WSN applications require energy-efficient communication. Resource constraints limit WSN storage, computing, battery power, and communication. Data processing, aggregation, and clustering are energy-intensive, and deployment and discovery are complicated. Selecting Fine Cluster Heads (FCHs) and Cluster Head (CHs) to extend WSN lifetime is still difficult. This study uses bacterial foraging optimization and ant colony optimization to find suitable gateways (FCHs), CH nodes, and routes from sensor nodes (SNs) to base stations (BS). Long-term network utilization requires balancing node energy usage with CHs and FCHs. Ant colony optimization dynamically finds the energy-aware route with lower network overhead. The algorithm assesses node energy consumption, network lifespan, Packet Delivery Ratio (PDR), and throughput. For WSNs like EECABCO, ECEEC, and EECRP-BOACOA, simulation outperformed clustering-based routing. Node energy usage (9.53 mJ), PDR (97.5%), and network lifetime (9920 rounds) are WSN performance outcomes for 300 sensors. The proposed system operates with 94.24% accuracy. The Bacterial Foraging Ant Colony Optimization (BFO-ACO) clustering and routing algorithm outperforms parallel research.

Analyzing coverage area and channel bonding performance in 60 GHz MIMO systems for wireless local area networks

This study investigates the coverage area and channel bonding performance of millimeter-wave (mmWave) Multiple Input-Multiple Output (MIMO) systems, with a specific focus on 60 GHz Wireless Local Area Network (WLAN) communications under both line-of-sight (LOS) and non-line-of-sight (NLOS) conditions. As the demand for high-speed wireless data transmission increases, this research aims to enhance bandwidth efficiency through effective channel bonding techniques. Our analysis covers three frequency bands: 2.4 GHz (IEEE 802.11n), 5 GHz (IEEE 802.11ac), and 60 GHz (IEEE 802.11ay), utilizing a comprehensive path loss model. The results demonstrate that channel bonding capacity in LOS scenarios significantly exceeds that in NLOS conditions. Notably, the 60 GHz 16 × 16 MIMO system achieves a maximum bandwidth of 12.96 GHz, resulting in peak data rates of 118.89 Gbps for LOS and 110.36 Gbps for NLOS. The coverage areas are quantified as 9.75 m for LOS and 4.8 m for NLOS in the 60 GHz band. These findings underscore the critical trade-offs between bandwidth and coverage in mmWave systems, providing valuable insights for optimizing future high-speed wireless communication technologies. This research contributes to the growing body of literature on mmWave communications and addresses the pressing need for efficient bandwidth utilization in modern wireless networks.

Assessment of Land Resource Utilization Efficiency, Spatiotemporal Pattern, and Network Characteristics in Resource-Based Regions: A Case Study of Shanxi Province

Resource-based regions face particular challenges in achieving sustainable land-use transformation due to their entrenched development patterns. Through an integrated approach (super-efficiency SBM, Global Moran’s I, synergistic modeling, and SNA), this study analyzes Shanxi Province’s land-use efficiency dynamics (2015–2021), revealing (1) an N-shaped efficiency trajectory with core-periphery polarization stable high-efficiency clusters (Taiyuan/Yangquan/Luliang, mean &gt; 1.1) versus fragmented northern mining zones and stagnant southern regions; (2) deficient spatial coordination (Moran’s I &lt; 0) and failed capital-city spillovers, with only 2/10 cities achieving positive synergy; and (3) network instability (density = 0.14–0.29) featuring paradoxical power shifts in the emerging mining hub Shuozhou (degree = 100) outperforming traditional cores. Based on these findings, this study proposes policy recommendations from the perspective of regional policymakers, focusing on establishing provincial-level land resource utilization planning, promoting coordination among cities in terms of land resource utilization at the municipal level, and improving land resource utilization efficiency through environmental regulations. This study offers a new perspective on regional coordination for sustainable development in resource-based regions by conducting research at the provincial level, advancing policy suggestions at the meso-policy level for the green transformation of resource-based cities, and providing theoretical support for promoting the intensive and efficient utilization of land across cities in specific regions.

Greater functional connectivity between executive function-related networks predicts word reading fluency: an fMRI study in children

ABSTRACT This study aimed to determine the involvement of neural circuits associated with executive functions (EF) during Hebrew reading in its two forms, deep and shallow, on a word and contextual level in children. Functional MRI data was collected employing 49 8-12-year-old Hebrew-speaking children performing the n-back task. Functional connectivity within and between EF networks (i.e. the cingulo-opercular; CO and fronto-parietal; FP networks) was calculated and included in prediction models for single word as well as contextual reading measures on a deep and shallow orthographic level. Working memory was positively associated with single word reading in Hebrew-speaking children. Functional connectivity between CO-FP networks better predicted deep orthography reading in single word reading compared to shallow orthography. Results highlight the utilisation of EF networks during the deep form of Hebrew in single word reading.

Modeling of the distribution of cargo flows of combined shipments in the hinterland area of the seaport

This study focuses on assessing the potential for optimizing the utilization of the hinterland transport network when organizing the dispatch of combined cargo shipments from a seaport. The complexity of this task stems from the need to implement innovative methods to enlarge bulk shipments to facilitate their inland transportation using containerization. This approach promotes the development of new transportation routes and necessitates the evaluation of the transport characteristics of the shipping process. Modeling the transport network requires a comprehensive evaluation of factors, as well as economic and operational indicators that characterize the movement of cargo between origin points (sea container terminals) and destination points (consignee warehouses). This paper reviews existing models for assessing transport network utilization and provides a brief overview of each. In evaluating ongoing processes, it is emphasized that each specific origin-destination pair (sea container terminal to consignee warehouse) can be represented not only in terms of volume but also as a function of time. The possibility of developing a dynamic model based on various methods of unitizing cargo and evaluating the network's transport capabilities is also highlighted. The study concludes that, when addressing the problem of distributing flows across the transport network, considering different methods of organizing cargo units, and accounting for constraints on route capacity, time, or transportation costs, a projection method can be applied to identify the optimal transportation solution from a range of feasible options.

A Literature Survey On Sentiment Analysis Using Image Processing

Sentiment analysis, the automated process of determining emotions and opinions expressed in content, has evolved to encompass visual media, allowing for a deeper understanding of sentiments conveyed in images. This paper explores the application of image processing techniques, coupled with Python programming, to conduct sentiment analysis by extracting emotional cues from visual data. The study begins with an overview of the significance and challenges of sentiment analysis in images, emphasizing the need for advanced tools to analyze the ever-growing volume of visual content on the internet. Leveraging Python's rich ecosystem of libraries, the paper delves into the technical aspects of sentiment analysis using image data. Key components of this research include the utilization of Convolutional Neural Networks (CNNs) for feature extraction, pre-trained models for sentiment recognition, and the development of custom datasets to train and validate sentiment analysis models. Python libraries like TensorFlow and Keras provide a robust framework for building and deploying deep learning models. The paper discusses the ethical considerations related to image-based sentiment analysis, addressing concerns about privacy, bias, and cultural nuances. It also explores the potential applications of this technology, ranging from brand sentiment analysis in marketing to monitoring public sentiment on social media platforms. Furthermore, the study identifies challenges and opportunities in the field, paving the way for future research endeavors. By bridging the domains of computer vision, natural language processing, and machine learning, sentiment analysis by image processing in Python opens up new avenues for understanding the emotional impact of visual content in an increasingly digital and visually driven world.

Beyond averaging: A transformer approach to decoding event related brain potentials.

Beyond averaging: A transformer approach to decoding event related brain potentials.