Key Performance Metrics Research Articles

Relative Acceleration and Maximum Velocity in Rugby Players According to Age Category and Playing Position.

Zabaloy, S, Freitas, TT, Alcaraz, PE, Gálvez-González, J, Pereira, LA, Comyns, T, Loturco, I, and Healy, R. Relative acceleration and maximum velocity in rugby players according to age category and playing position. J Strength Cond Res XX(X): 000-000, 2024-This study aimed to: (a) assess the intrasession reliability of the acceleration time constant (i.e., τ) and τ-derived measures; (b) analyze the influence of τ and maximum velocity (Vmax) on 40-m sprint performance and to compare various sprint-related outcomes among rugby players from different playing positions and age categories; and (c) explore the associations between τ and several sprint performance metrics. A total of 300 male rugby players volunteered to participate in this study and were divided into age categories (i.e., under-14 [U14]: n = 91, age: 12.6 ± 0.5 years; under-16 [U16]: n = 85, age: 14.8 ± 0.5 years; under-18 [U18]: n = 75, age: 16.6 ± 0.5 years; and Seniors: n = 49, age: 24.2 ± 4.1 years). The results demonstrated good to excellent reliability for all measured parameters (intraclass correlation coefficient >0.75 and coefficient of variation <9.0%). Younger players (i.e., U14 and U16) displayed lower τ values (effect size: moderate to large; p < 0.02) compared with their older peers (i.e., U18 and Seniors), regardless of their playing position. Moreover, τ was associated with sprint performance metrics at varying levels of correlations (Rho: small to almost perfect; p < 0.001). In conclusion, younger players exhibited lower τ values than their older counterparts, irrespective of their playing positions. The model employed in this study demonstrated its accuracy in assessing several key sprint performance metrics, offering insights that can enhance sprint training programs for rugby players, which can be based on the associations observed among these different variables.

Implementation and Evaluation of Attention Aggregation Technique for Pear Disease Detection

In this study, a novel approach integrating multimodal data processing and attention aggregation techniques is proposed for pear tree disease detection. The focus of the research is to enhance the accuracy and efficiency of disease detection by fusing data from diverse sources, including images and environmental sensors. The experimental results demonstrate that the proposed method outperforms in key performance metrics such as precision, recall, accuracy, and F1-Score. Specifically, the model was tested on the Kaggle dataset and compared with existing advanced models such as RetinaNet, EfficientDet, Detection Transformer (DETR), and the You Only Look Once (YOLO) series. The experimental outcomes indicate that the proposed model achieves a precision of 0.93, a recall of 0.90, an accuracy of 0.92, and an F1-Score of 0.91, surpassing those of the comparative models. Additionally, detailed ablation experiments were conducted on the multimodal weighting module and the dynamic regression loss function to verify their specific contributions to the model performance. These experiments not only validated the effectiveness of the proposed method but also demonstrate its potential application in pear tree disease detection. Through this research, an effective technological solution is provided for the agricultural disease detection domain, offering substantial practical value and broad application prospects.

Assuring Autonomy of UAVs in Mission-critical Scenarios by Performability Modeling and Analysis

Uncrewed Aerial Vehicles (UAVs) have been used in mission-critical scenarios such as Search and Rescue (SAR) missions. In such a mission-critical scenario, flight autonomy is a key performance metric that quantifies how long the UAV can continue the flight with a given battery charge. In a UAV running multiple software applications, flight autonomy can also be impacted by faulty application processes that excessively consume energy. In this article, we propose Flight Autonomy Assurance as a framework to assure the autonomy of a UAV considering faulty application processes through performability modeling and analysis. The framework employs hierarchically configured stochastic Petri nets, evaluates the performability-related metrics, and guides the design of mitigation strategies to improve autonomy. We consider a SAR mission as a case study and evaluate the feasibility of the framework through extensive numerical experiments. The numerical results quantitatively show how autonomy is enhanced by offloading and restarting faulty application processes.

Comparative Analysis of Neural Network Architectures for Predicting Chronic Disease Indicators Using CDC’s Chronic Disease Indicators Dataset

This research evaluates the performance of three machine learning models—Neural Network (NN), Convolutional Neural Network (CNN), and Recurrent Neural Network (RNN) using Long Short-Term Memory (LSTM) units—in predicting chronic disease indicators using the CDC's Chronic Disease Indicators (CDI) dataset. The study employs a comprehensive preprocessing pipeline and 5-fold cross-validation to ensure robustness and generalizability of the results. The CNN model outperformed both the NN and RNN models across all key performance metrics, achieving an accuracy of 0.6303, precision of 0.6445, recall of 0.6303, and F1 score of 0.5950. The superior performance of the CNN is attributed to its ability to capture spatial hierarchies and interactions within the structured dataset. The findings underscore the importance of selecting appropriate machine learning architectures based on the data characteristics. This research provides valuable insights for public health officials and policymakers to enhance chronic disease monitoring, early detection, and intervention strategies. Future work will explore hybrid models and advanced techniques to further improve predictive performance. This study highlights the potential of CNNs in public health informatics and sets a foundation for further research in this domain

Optimizing energy‐efficient data replication for IoT applications in fog computing

SummaryThe rise of the Internet of Things (IoT) has given rise to an era marked by interconnected devices and substantial data generation. This has led to an increased reliance on cloud computing for data processing and storage, primarily due to its cost‐effective pay‐for‐use model. However, this dependence has prompted critical inquiries into the optimal replication of data: what data to replicate, when to replicate it, and where to place new replicas strategically. Conventional cloud data replication often results in resource overutilization, performance bottlenecks, increased workloads, energy consumption, prolonged user wait times, and suboptimal response times. In response to these challenges, this paper introduces a novel approach named Multiobjective Optimization Harris Hawks Optimization with Salp Swarm Algorithm (MOHHOSSA). This approach employs multiobjective optimization (MOO) alongside Harris Hawks Optimization (HHO) and IoT‐based Salp Swarm Algorithm (SSA) for cloud computing environments. MOHHOSSA efficiently identifies data replication opportunities and strategically allocates them across nodes in cloud computing infrastructures. The algorithm aims to enhance key performance metrics, including energy consumption, carbon dioxide emission rate, and mean service time. Extensive experimental validation demonstrates MOHHOSSA's superior performance compared to alternative algorithms. It excels in optimizing energy efficiency, load distribution, mean service time, and the establishment of cost‐effective communication paths between nodes. This research represents a significant advancement in addressing challenges related to IoT data replication in cloud computing, ultimately promoting more sustainable, efficient, and responsive cloud‐based services.

Multi-objective optimization of morphology for high-rise residential cluster with the regards to energy use and microclimate

Urban morphology significantly influences building energy consumption, solar energy potential, and outdoor thermal microclimate. This study seeks to optimize the urban morphology of high-rise residential clusters, using a framework that emphasizes energy use, outdoor thermal microclimate and incremental investment cost at a preliminary stage of design. The proposed framework is based on performance oriented parametric simulation and implements multi-objective optimization using the Grasshopper platform to assess residential cluster morphology. The study analyzed the five morphological parameters (floor area ratio (FAR), building density (BD), average floor (AF), average orientation (AO), and average aspect ratio (AAR)) to achieve the minimize of the Net Energy Intensity (NEI), Universal Thermal Climate Index (UTCI), and Incremental Investment Cost (IIC) of residential clusters. This approach aims to enhance energy efficiency and improve summer microclimate while reducing investment costs. Additionally, analyzed the correlation between morphological parameters and three key performance metrics: Energy Use Intensity (EUI) (encompassing heating, cooling, and lighting requirements), Photovoltaic Energy Generation (PVEG), and UTCI. The findings reveal that the optimal morphology of residential clusters varies significantly depending on the desired objective. When prioritizing PVEG, a morphology characterized by low height, high density, and a small aspect ratio is recommended. It is noteworthy that in this morphology, the cluster also demonstrates optimal UTCI during the summer. Conversely, if EUI is the primary objective, a configuration with higher height and aspect ratio, along with lower density, is suggested. On the other hand, balancing the requirements of these three objectives may require a moderately-spaced layout with low height, large aspect ratio, and compact front-to-back building spacing. Under these morphologies, particular attention should be given to the layout in the north–south directions. Furthermore, southward orientation is advisable. Additionally, based on analysis of Pareto solutions, a FAR of approximately 2.6 to 2.7 is recommended.

Leveraging Machine Learning for Telecom Banking Card Fraud Detection: A Comparative Analysis of Logistic Regression, Random Forest, and XGBoost Models

In recent years, telecommunication bank card fraud has become a major threat to financial security, so it is necessary to develop robust detection mechanisms for telecommunication bank card fraud. This study examines the application of machine learning techniques (specifically logistic regression, random forests, and XGBoost) in identifying fraudulent telecom bank transactions. Using a dataset consisting of one million transaction records from the 2024 National Student Data Statistics and Analytics Competition, we implemented and evaluated these models based on key performance metrics such as accuracy, precision, recall, F1 score and ROC-AUC. The results show that XGBoost outperforms the other models, achieving superior accuracy and robustness in fraud detection, while Random Forest also performs well, achieving almost perfect classification accuracy. Logistic regression, while effective, lagged behind in terms of handling the complexity of the data. The analyses in this paper further highlight the critical role of features such as transaction amount ratios and online transaction status in predicting fraud. These findings suggest that advanced machine learning models, especially ensemble methods such as XGBoost, are highly effective in combating telecom banking fraud and should be integrated into existing detection systems to enhance their predictive capabilities.

Assessing the impact of colostrum feeding delay on serum immunoglobulin G and total protein in dairy goat kids

This experiment was motivated by the need to understand the impacts of delaying the first colostrum feeding on the prevalence of failed transfer of passive immunity (FTPI). A cohort of 216 kids was stratified into groups based on the colostrum feeding delay postbirth: 0–4 h, 4–8 h, 8–12 h, and 12–16 h. All kids received a single colostrum meal of 300 mL, and blood samples were collected approximately 36 h after feeding. Serum immunoglobulin G (SIgG) was measured using ELISA, and serum total protein (STP) was assessed using the Bradford method and refractometry (STPb and STPr). Statistical methods like Pearson correlations, Bland-Altman plots, and Lin’s concordance coefficient were employed to assess associations and agreements between SIgG, STPb and STPr. Receiver operator characteristic analysis was employed to determine optimal STPb and STPr thresholds for predicting FTPI (SIgG < 12 g/L). Subsequently, areas under the curve, sensitivity, and specificity were examined to assess the accuracy of these thresholds. Our results showed that for each hour’s delay from birth to colostrum intake (up to 16 h), IgG apparent efficiency of absorption (AEA) decreases at an approximate rate of 2.0% per hour, and SIgG decreases at an approximate rate of 1.0 g/L per hour. However, this decline is not constant over time but intensifies progressively with increased feeding delay. Specifically, reductions in IgG AEA were 1.3, 2.9, and 5.9% per hour, and decreases in SIgG were 0.2, 0.3, and 0.7 g per hour for SIgG across the time intervals of 0–4 to 4–8 h, 4–8 to 8–12 h, and 8–12 to 12–16 h, respectively. Additionally, there was an increase in SIgG of 1.2 g/dL but a decrease in IgG AEA of 1.9% for each gram per kg of BW increase in IgG intake. The correlations between SIgG and STPr and STPb were 0.62, and 0.36, respectively. Optimal STPr and STPb thresholds predicting FTPI were determined to be 4.6 and 6.2 g/dL. The prevalence of FTPI, according to SIgG, STPr, and STPb thresholds were 63, 62, and 45%. Overall, STPr showed higher values for key performance metrics (i.e., sensitivity, likelihood ratio of positive tests, overall accuracy, and Youden’s index), indicating better prediction ability than STPb. Our findings corroborate the critical importance of swift colostrum administration, ideally occurring no later than 12 h postbirth. Moreover, our research validates the effectiveness of Brix refractometry as a practical, on-farm method for assessing FTPI in goat kids.

Enhancement of Ion-Sensitive Field-Effect Transistors through Sol-Gel Processed Lead Zirconate Titanate Ferroelectric Film Integration and Coplanar Gate Sensing Paradigm

To facilitate the utility of field effect transistor (FET)-type sensors, achieving sensitivity enhancement beyond the Nernst limit is crucial. Thus, this study proposed a novel approach for the development of ferroelectric FETs (FeFETs) using lead zirconate titanate (PZT) ferroelectric films integrated with indium–tungsten oxide (IWO) channels synthesized via a cost-effective sol-gel process. The electrical properties of PZT-IWO FeFET devices were significantly enhanced through the strategic implementation of PZT film treatment by employing intentional annealing procedures. Consequently, key performance metrics, including the transfer curve on/off ratio and subthreshold swings, were improved. Moreover, unprecedented electrical stability was realized by eliminating the hysteresis effect during double sweeps. By leveraging a single-gate configuration as an FeFET transformation element, extended-gate (EG) detection methodologies for pH sensing were explored, thereby introducing a pioneering dimension to sensor architecture. A measurement paradigm inspired by plane gate work was adopted, and the proposed device exhibited significant resistive coupling, consequently surpassing the sensitivity thresholds of conventional ion-sensitive field-effect transistors. This achievement represents a substantial paradigm shift in the landscape of ion-sensing methodologies, surpassing the established Nernst limit (59.14 mV/pH). Furthermore, this study advances FeFET technology and paves the way for the realization of highly sensitive and reliable ion sensing modalities.

It’s about time: mitigating cancer-related cognitive impairments through findings from computational models of the Wisconsin Card Sorting Task

BackgroundMany cancer survivors experience cancer-related cognitive impairment (CRCI), often with significant negative consequences across various life domains. Emerging evidence suggests that allowing additional time to process information before acting may be a useful strategy for those with CRCI to mitigate some of its impacts. The Wisconsin Card Sorting Task (WCST), a measure of general cognition, has shown that for some cancer survivors, longer task completion time facilitates similar task performance outcomes to control populations concerning perseveration errors; a key performance metric of the WCST. However, assessing if this strategy may be useful, as well as determining for whom it may be useful, with regard to strengths and weaknesses among select cognitive domains, is challenging due to factors such as the problem of task impurity. Accordingly, this study provides an initial computational and experimental assessment of whether additional time to process information before acting is a useful strategy for those with CRCI.MethodsWe simulated individual cognitive differences observed in humans by varying contributions of executive functioning components (updating, shifting, inhibition) to yield 48 distinct computational models of the WCST. Our main manipulation was then to provide these models with more or less time (at three levels of 20, 40 and 60 cycles) before models executed an action to sort a given card. We compared the number of perseveration errors on the WCST produced by the computational models. Additionally, we determined models that simulated the performance of cancer survivors on the WCST by comparing the number of perseveration errors produced by the models to human data.ResultsAdditional processing time resulted in the models producing significantly fewer perseveration errors, supporting our hypothesis. In addition, 8 unique models simulated the performance of cancer survivors on the WCST. Additional time appeared to have a positive influence on performance primarily by mitigating the impacts of severe inhibition impairments. For more severe global executive function impairments, a substantial amount of additional time was required to mitigate the impacts of the impairments. For the most severe impairments, additional time was unable to adequately mitigate the impact on performance.ConclusionAdditional processing time may be a useful strategy to rectify perseveration errors among cancer survivors with CRCI. Our findings have implications for the development of practical strategies, such as workload and deadline management in occupational settings, which may mitigate the negative effects of CRCI.

Analisis Pengaruh Forecasting Demand Terhadap Efisiensi Manajemen Persediaan

This study analyzes the impact of demand forecasting on inventory management efficiency, focusing on the implementation of the ARIMA method in the context of a manufacturing company in Indonesia. Using a quantitative case study approach, the research explores the relationship between forecasting accuracy and key inventory performance metrics. Results indicate that improved forecasting accuracy significantly enhances inventory efficiency, with the ARIMA method outperforming traditional methods. The implementation of ARIMA resulted in a 36.8% increase in Inventory Turnover Ratio and a 53.3% decrease in stockout rate. Time series analysis revealed a long-term improvement trend in inventory efficiency with significant seasonal components. This research provides valuable insights for practitioners and academics on the critical role of demand forecasting in optimizing inventory management and the potential of the ARIMA method in improving companies' operational efficiency.

Designing cancer screening trials for reduction in late-stage cancer incidence

ABSTRACT Before implementing a biomarker test for early cancer detection into routine clinical care, the test must demonstrate clinical utility, that is, the test results should lead to clinical actions that positively affect patient-relevant outcomes. Unlike therapeutical trials for patients diagnosed with cancer, designing a randomized controlled trial (RCT) to demonstrate the clinical utility of an early detection biomarker with mortality and related endpoints poses unique challenges. The hurdles stem from the prolonged natural progression of the disease and the lack of information regarding the time-varying screening effect on the target asymptomatic population. To facilitate the study design of screening trials, we propose using a generic multistate disease history model and derive model-based effect sizes. The model links key performance metrics of the test, such as sensitivity, to primary endpoints like the incidence of late-stage cancer. It also incorporates the practical implementation of the biomarker-testing program in real-world scenarios. Based on the chronological time scale aligned with RCT, our method allows the assessment of study powers based on key features of the new program, including the test sensitivity, the length of follow-up, and the number and frequency of repeated tests. The calculation tool from the proposed method will enable practitioners to perform realistic and quick evaluations when strategizing screening trials for specific diseases. We use numerical examples based on the National Lung Screening Trial to demonstrate the method.

Multi-Object Detection and Tracking with Modified Optimization Classification in Video Sequences

The paper presents a novel approach to enhancing multi-object detection and tracking in video sequences using a Modified Ant Swarm Optimization Deep Learning (ASO-DL) algorithm. The ASO-DL algorithm synergistically combines the optimization capabilities of ant swarm optimization with the powerful feature extraction abilities of deep learning models, resulting in a robust framework for realtime video analytics. Extensive simulations and experiments demonstrate significant improvements in key performance metrics, including accuracy, precision, recall, and F1 score, across various iterations. The proposed method consistently outperforms baseline models, achieving a final best fitness value of 0.96, with an accuracy of 0.98, precision of 0.99, and recall of 0.95. Additionally, classification results across different datasets such as CIFAR-10, IMDB, COCO, and ImageNet highlight the algorithm’s versatility and effectiveness. This research contributes to the field by providing a highly optimized solution for complex multi-object tracking tasks, offering substantial advancements in the accuracy and efficiency of real-time object detection systems. The findings hold significant potential for applications in surveillance, autonomous vehicles, and other domains requiring precise and reliable multi-object tracking.

Numerical Analysis of Flow Velocity and Performance Test of Cross-Flow Turbine (500 W)

The purpose of this study is to analyze the flow velocity and assess the performance of a cross-flow turbine through numerical simulations and performance tests. Using computational fluid dynamics (CFD), the flow patterns and velocity distributions around the turbine blades to gain insights into the turbine's hydrodynamic behavior. In the experimental phase, constructed a prototype of the cross-flow turbine and tested it in a water flume, measuring key performance metrics such as power output and efficiency.The test were performed under design flow condition. The numerical results were validated with performance tests. The numerical analysis revealed critical areas of flow separation and turbulence, which were consistent with the observed experimental data.

Enhancing Energy Efficiency in Telehealth IoT through MultiObjective Optimization on a Hybrid Fog/Cloud Computing Platform

In the rapidly evolving field of Telehealth Internet of Things (IoT), the pursuit of energy-efficient solutions that coexist with optimal system performance is a critical concern. This paper introduces a novel approach to address this challenge by integrating multi-objective optimization techniques within a hybrid fog/ cloud computing platform. Building upon established research on a fog-based telehealth model, this study extends its investigation to encompass a broader spectrum of performance metrics, including energy efficiency, response time, throughput, and resource utilization. The study employs well-established multiobjective optimization algorithms, specifically NSGA-II (Non-dominated Sorting Genetic Algorithm II) and SPEA2 (Strength Pareto Evolutionary Algorithm 2), to construct a comprehensive optimization framework. An intricate objective function is meticulously formulated to quantify the trade-offs between energy efficiency and other key performance metrics, facilitating the identification of Pareto-optimal solutions. The resulting Pareto front offers illuminating insights into the nuanced interplay between energy efficiency and performance attributes, providing decision-makers with tailored options that cater to their specific priorities. Rigorous evaluation of these solutions through simulated experiments reveals a harmonious landscape where energy-saving imperatives coalesce harmoniously with response time, throughput, and resource utilization goals. The implications of this multi-objective optimization approach are analyzed in depth, underscoring its potential to reshape optimization paradigms for Telehealth IoT deployments within a fog/cloud hybrid platform. This research represents a pioneering stride towards reconciling energy efficiency and performance in Telehealth IoT systems, offering a nuanced perspective for informed decision-making and a sustainable future for energy-saving initiatives in Telehealth IoT applications

Redesigning Luxury Cosmetics: The BlueMercury Project – Innovating High-Quality Luxury Products at Affordable Prices

Abstract The BlueMercury project aims to revolutionize the luxury cosmetics market by providing high-quality products at more competitive prices. Luxury cosmetics often face challenges in maintaining quality standards while being affordable. This project addresses these challenges by developing a centralized web-based platform tailored specifically for luxury cosmetic products. The website offers a range of features designed to streamline shopping operations and enhance the user experience among customers and administrators. The platform allows administrators to manage product information, inventory, and system settings. Customers can easily browse products, track their orders, and make secure payments. This fosters a high standard of quality, affordability, and efficiency in the luxury cosmetics market. Overall, the BlueMercury project represents a significant step forward in modernizing luxury cosmetics operations and fostering customer satisfaction. By leveraging technology to create a centralized platform tailored to the needs of luxury cosmetics, the website helps drive operational excellence and ensures the long-term success of the brand. The system features robust reporting and analysis capabilities, allowing administrators to track key performance metrics, identify trends, and generate insights into their operations. This empowers users to make informed decisions and optimize their performance for maximum efficiency and success. Keywords – Luxury Cosmetics, High-Quality Products, Competitive Pricing, Operational Excellence, Customer Satisfaction.

Design and Implementation of an School College Management System: Enhancing Operational Consistency and Growth

Abstract–The School Management System project aims to revolutionize the management, organization, and communication processes performance within educational institutions. Schools often face challenges in maintaining efficient communication channels, tracking student, and managing administrative tasks. This project addresses these challenges by developing a centralized web-based platform tailored specifically for school management. The portal offers a range of features designed to streamline operations and enhance communication among students, teachers, and administrators. The portal provides a centralized platform for administrators to manage student and teacher information, create classes and subjects, and oversee system settings. Teachers can easily track attendance, assess student performance, and provide feedback. Students can access their records, view marks, and track their academic progress. This fosters collaboration, knowledge sharing, and problem-solving among all users, leading to improved operational efficiency and academic performance. Overall, the School Management System project represents a significant step forward in modernizing school operations and fostering collaboration and communication within educational institutions. By leveraging technology to create a centralized platform tailored to the needs of schools, the portal helps drive operational excellence and ensure the long-term success of students and teachers. The system features robust reporting and analysis capabilities, allowing users to track key performance metrics, identify trends, and generate insights into their operations. This empowers users to make informed decisions and optimize their performance for maximum efficiency and success. Keywords – School Management, Class Organization, Student Performance, Operational Excellence, Knowledge Sharing.

Design and Implementation of an School College Management System: Enhancing Operational Consistency and Growth

Abstract–The School Management System project aims to revolutionize the management, organization, and communication processes performance within educational institutions. Schools often face challenges in maintaining efficient communication channels, tracking student, and managing administrative tasks. This project addresses these challenges by developing a centralized web-based platform tailored specifically for school management. The portal offers a range of features designed to streamline operations and enhance communication among students, teachers, and administrators. The portal provides a centralized platform for administrators to manage student and teacher information, create classes and subjects, and oversee system settings. Teachers can easily track attendance, assess student performance, and provide feedback. Students can access their records, view marks, and track their academic progress. This fosters collaboration, knowledge sharing, and problem-solving among all users, leading to improved operational efficiency and academic performance. Overall, the School Management System project represents a significant step forward in modernizing school operations and fostering collaboration and communication within educational institutions. By leveraging technology to create a centralized platform tailored to the needs of schools, the portal helps drive operational excellence and ensure the long-term success of students and teachers. The system features robust reporting and analysis capabilities, allowing users to track key performance metrics, identify trends, and generate insights into their operations. This empowers users to make informed decisions and optimize their performance for maximum efficiency and success. Keywords – School Management, Class Organization, Student Performance, Operational Excellence, Knowledge Sharing.

Comparative Study of Machine Learning Algorithms using the CICIOV2024 Dataset

Leveraging the CICIoV2024 dataset, this study evaluates the performance of different algorithms in accurately identifying and classifying intrusions in vehicular networks, specifically using LightGBM, XGBoost, CatBoost, and LCCDE algorithms. A comparative analysis conducted considered key performance metrics such as accuracy, precision, recall, and F1-score, shedding light on the strengths and limitations of each approach. Through rigorous experimentation and evaluation, the remarkable results demonstrated 100% accuracy, recall, precision, and F1-score across all models. These findings highlight the efficacy of employing advanced machine learning techniques for enhancing intrusion detection capabilities in IoV environments. The insights gained from this study can inform the development of highly accurate and reliable intrusion detection systems tailored to the unique challenges of vehicular networks.Keywords: CatBoost, CICIoV2024, IoV, LCCDE, LightGBM, XGBoost

Performance evaluation of microservices communication with REST, GraphQL, and gRPC

Microservice architecture has become the design paradigm for creating scalable and maintainable software systems. Selecting the proper communication protocol in microservices is critical to achieving optimal system performance. This study compares the performance of three commonly used API protocols: REST, GraphQL, and gRPC, in microservices architecture. In this study, we established three microservices implemented in three containers and each microservice contained a Redis and MySQL database. We evaluated the performance of these API protocols using two key performance metrics: response time and CPU Utilization. This study performs two distinct data retrieval: fetching flat data and fetching nested data, with a number of requests ranging from 100 to 500 requests. The experimental results indicate that gRPC has a faster response time, followed by REST and GraphQL. Moreover, GraphQL shows higher CPU Utilization compared to gRPC and REST. The experimental results provide insight for developers and architects seeking to optimize their microservices communication protocols for specific use cases and workloads.