Al-Furat Journal of Innovations in Electronics and Computer Engineering

Authorities have interest in the use of demographic data to understand users’ behavior due to its importance in making industries unique. In the analysis of the demographic data regarding books’ preferences this study makes a use of the Principle Component Analysis (PCA) and K-means clustering analysis. First a PCA was used in an attempt to reduce the dimensionality of the given dataset, the goal was to maximize the variance retained in the data while at the same minimizing the raw data complexity to 95%. Last, in an effort to classify the data into different demographic areas by age as well as geographical region, the K-means clustering was applied. The outcomes implied in the study show that PCA, as well as K-means clustering, are efficient in distilling information from extensive and great-detail demographic data. The insight arising from the results is additional information in the area of reader preference, as well as suggestions for future marketing and recommendation approaches. These methods were used on the book dataset that contain user and book data, and the results proved that every demographic had preferences with different books. On top of knowledge derived from analysis of the results, it offers further understanding of the readers’ choice of content and indicates areas where marketing and recommendation strategies may be headed in the future. As a result of clustering customers, businesses can for example, target the marketing campaigns and offer appropriate books to the specific ages and geographical areas

Beamforming technology within smart antenna systems is recognized as a crucial advancement in contemporary wireless communication, playing a substantial role in boosting network efficiency and capacity. Through the targeted steering of signals for transmission and reception to particular users or devices, beamforming diminishes interference while maximizing the utilization of existing bandwidth. This study discovers into the principles and applications of beamforming in smart antenna systems, emphasizing its influence on enhancing signal quality, coverage, and overall network efficiency. Through a comprehensive review of existing literature, it is observed that different researchers have proposed distinct approaches to address this objective, Therefore, it can be deduced that there is no singular approach present in this context. The manuscript investigates the obstacles linked to beamforming, including computational intricacy, hardware limitations, and the necessity for accurate synchronization. By conducting a thorough examination, this research highlights the revolutionary capacity of beamforming technology in enhancing intelligent antenna systems and influencing the trajectory of wireless communications recorded cracking and failure numbers

With the expansion of Internet of Things (IoT) technology, the ability to generate and transfer large volumes of data for users has become more widespread. By connecting to the IoT network, users can access resources and devices distributed across the network. However, as the number of connected devices and user requests grows, several challenges emerge, particularly in efficiently managing and allocating available resources to tasks.An optimal resource allocation algorithm should ensure tasks are executed fairly, efficiently, and in the shortest time possible. Beyond time efficiency, other critical factors must also be considered, such as maximizing the efficiency of available resources, minimizing energy consumption, and ensuring load balancing. These factors are essential when allocating resources in IoT networks.This paper introduces a method for resource allocation in IoT networks using the Kepler Optimization Algorithm (KOA). The proposed approach addresses challenges related to resource utilization, energy consumption, and load balancing by allocating tasks across edge and cloud resources. The algorithm ensures low latency and energy efficiency by leveraging the exploration and exploitation capabilities of KOA, inspired by Kepler's laws of planetary motion.In the proposed system, multiple resources and tasks with varying lengths are considered. The KOA-based algorithm allocates tasks to the most suitable resources based on a structure that draws an analogy between planetary motion parameters (such as mass, orbit, and gravity) and computational resources such as CPU, memory, and bandwidth. The decision-making process for allocating tasks between edge and cloud layers plays a significant role in ensuring optimal resource usage. Tasks requiring minimal latency are processed at the edge, while others are forwarded to the cloud for execution. If neither the edge nor the cloud can meet the required execution time, the task is rejected. This decision-making process is based on real-time evaluations of resource availability and latency constraints, ensuring the best possible outcome for task execution.Simulation results demonstrate that the proposed method outperforms traditional methods like Particle Swarm Optimization (PSO) and Gray Wolf Optimization (GWO), showing superior performance in energy efficiency, response time, and load balancing.

The paper studies the critical issue of frequency hopping spread spectrum (FHSS) for drone communications, particularly for UAVs in both civilian and military sectors. It reveals the shortcomings of existing FHSS algorithms, which cannot resist jamming, further adaptability, and sensitivity to complex electromagnetic environments where UAVs work. A comprehensive literature review highlighted a decline in different resilience parameters, which demands an adaptive communication strategy with real-time environmental information to support resilient and energy-efficient communications. These challenges are investigated using emerging technologies like machine learning, software-defined radios, and cognitive radio systems. In addition, the paper underlines the necessity of putting well-designed regulations in place to ensure that UAVs are safely integrated within common air spaces. The work also suggests areas where frequency hopping techniques can be improved, especially within swarm drone operations, by proposing adaptive and collaborative communication models. The research is an essential step towards advancing UAV communication technologies and provides fresh information on alleviating interference and jamming threats in the rapidly crowded airspace.

Increased intraocular pressure and optic nerve damage, which may cause irreversible blindness, are the hallmarks of glaucoma. If this disease is identified early on, its severe effects can be prevented. However, among the older population, the illness is often identified at a later stage. Consequently, individuals may be spared irreversible visual loss by early identification. Ophthalmologists use a variety of expensive, time-consuming, skill-oriented techniques when manually assessing glaucoma. A definitive diagnostic method for early-stageglaucoma detection is still elusive, while a number of approaches are in the experimental stages of development. We offer an autonomous deep learning-based technique that has very high accuracy in detecting early-stage glaucoma. The detection method entails identifying patterns in the retinal pictures that physicians frequently miss.A test accuracy of 99.26% was attained in this study using the Resnet-50 network and data from the G1020 database that had been processed and transformed from RGB to RGBA

With the continued spread of integrated systems such as medical systems, Internet of Things systems and car control systems, securing these systems has become of electronic threats of utmost importance. the paper aims to provide recommendations for developers, researchers, and practitioners in the field of embedded systems security to address the increasing challenges of cyber security. Embedded systems are vulnerable to threats and hacks that could compromise their security. Overloading a power product can lead to power consumption by overusing peripherals or sensors. Embedded systems are also vulnerable to direct attacks: if a hacker gains access to the hardware, they can perform intrusion attacks on the system bus, tamper with the integrity of the system, and potentially cause peripheral damage.

In this paper, we discuss the unique characteristics of embedded systems addresses their vulnerability to attacks, exploring challenges and techniques in protecting embedded systems from cyber threats. In addition to providing an overview of common types of attacks targeting these systems, we also delve into the best practices and various security measures that can be used to mitigate the risks associated with embedded systems. These include access control methods, intrusion detection, security methods, encryption, and secure software development. In addition, we highlight the importance of continuous monitoring and updating of embedded systems to ensure their security and ability to withstand advanced cyber threats for long periods. Finally, The study focuses on reducing the uses of traditional software to include a variety of methods and techniques to identify and evaluate to produce radical ways to deal with security problems. The attack framework and types of partial analysis are reached as a business model and implemented to further implement and analyze various security methods as a means to address security problems.

The COVID-19 virus has highlighted the critical need for efficient and rapid communication between patients in distress and emergency medical services, especially ambulance dispatch systems. The following research paper presents a adapted algorithm intended to adjust the Kruskal method for shortening pathways in communication networks linking patients and ambulances through critical situations, confirming timely reply and effective resource distribution. The suggested method takes into reflection the unique challenges posed by COVID-19, as well as the essential to minimize patient-ambulance interaction to decrease the risk of viral transmission. This article shows a new technique, which effects real-time data on COVID-19 contagion rates, indications of patients, ambulance obtainability, and geographical info. In this case, we clarify how by adding these features to the Kruskal algorithm, we reach the finest paths for the best dispatch of ambulances with a perspective of minimizing the spread of the virus. The revised algorithm is designed to focus on routes with the fewest stops and contact points, enabling faster response times and reducing opportunities for disease spread. Furthermore, we present a case study demonstrating the effectiveness of our adapted algorithm in a simulated emergency reply scenario during the COVID-19 pandemic. Comparative analysis with traditional path-shortening algorithms showcases the superior concert of our approach in terms of reply time and safety. This shows delivers a valued effect to the field of emergency medical services, offering a practical solution to address the tests posed by COVID-19 while improving overall response efficiency. The modified algorithm can be seamlessly integrated into existing ambulance dispatch systems, helping healthcare providers and emergency responders make informed decisions that prioritize both patient well-being and public health safety during these unprecedented times.

The degradation of signal quality in optical fiber communication (OFC) systems due to nonlinear phase noise (NPN) and the need for effective multi-dimensional modulation techniques to mitigate this issue is presented in this article. Optical communication technologies have seen significant advancements in recent decades, meeting the escalating demands for bandwidth, Nevertheless, the efficiency of these systems is compromised by fiber nonlinearity employing multiple dimensions’ techniques a crucial role in (OFC) systems to address the degradation of signals, also overcoming the effects the nonlinear phase noise (NPN) that produce from send signal to far distance. This article explores the concept of Nonlinear impairment, including its Kerr effects, Polarization mode dispersion (PMD), Amplification spontaneous by noise emission, and Attenuation. It also highlights the importance of multi-dimensional modulation techniques to protect the signal sent in optical fiber. This paper explored the impact of different categories of M-dimensions techniques on the signal that is sent via optical fiber and Detect the effectiveness of nonlinear phase noise (NPN) like Digital backpropagation (DBP), mid-link optical phase conjugation (ML-OPC) and other techniques, also there is A different effective strategy recognized as phase conjugated twin waves (PCTWs) Which contribute significantly to nullify NPN. The paper concludes by providing an overview of the discussed topics and their significance in the field of optical fiber communication(OFC)

Artificial intelligence and deep learning in particular are now considered as promising methods in numerous scientific fields including medical science because the former can handle large amounts of data with non-linear relationships. Urinary bladder cancer is another frequent neoplasm that has variable histological variants and requires correct classification for the appropriate treatment tactics and prediction. This study proposed a Convolutional Neural Network (CNN) model that is accurate and simple to classifying bladder cancer, where, comparing its performance against three transfer learning architectures: These models include VGG16, InceptionV3, and MobileNetV2 for the two datasets that were used. It is seen from the experimental results that the proposed deep CNN model achieves a higher overall accuracy than the established transfer learning models which is 99. 5% in the final prediction and this makes the system suitable as a diagnostic tool for diagnosing bladder cancer.

Data sharing is a critical thing of current digital ecosystems, facilitating seamless communique, collaboration, and innovation throughout numerous sectors, consisting of healthcare, finance, and supply chains. However, safety demanding situations including facts breaches, unauthorized get admission to, and privateness violations pose enormous risks, limiting the consider and willingness of agencies to proportion facts correctly. Traditional safety mechanisms frequently fall short in addressing these concerns, necessitating the adoption of superior answers.Blockchain era emerges as a transformative option to beautify records safety, integrity, and transparency in facts-sharing ecosystems. By leveraging decentralized ledgers, cryptographic hashing, and clever contracts, blockchain guarantees tamper-evidence statistics exchange at the same time as preserving privateness and get right of entry to control. This paper reviews the potential of blockchain as a steady data-sharing framework, studying its benefits, obstacles, and real-international applications. Furthermore, the have a look at explores how blockchain mitigates safety vulnerabilities, promotes trust, and fosters regulatory compliance in information-sharing environments. The evaluate concludes that at the same time as blockchain offers a promising approach to stable facts sharing, demanding situations together with scalability, regulatory alignment, and integration with present systems must be addressed to maximise its adoption. Future studies ought to attention on overcoming these boundaries and enhancing blockchain frameworks to make certain broader implementation across industries.

Electric energy theft causes technical and non-technical losses in addition to serious destruction to energy suppliers and the power grid. Power quality and overall profitability are negatively impacted by energy theft. By combining data and energy flow, smart grids could potentially solve the issue of power theft. Power theft can be detected with the use of smart grid data analysis. However, there was room for improvement in the previous approaches' ability to detect energy theft. In this study, we introduced a machine-learning model for energy theft detection and smart grid classification based on active learning.
For the utilities, electricity theft is a serious worry. The introduction of smart meters has increased the frequency of gathering data on residential energy usage, opening it up for sophisticated data analysis that was previously unattainable. In fact, the sustainability, efficiency, and dependability of the conventional energy infrastructure may be significantly increased by employing Smart Grid (SG) networks, which are essentially enhanced networks of linked things. The amount of data generated by the SG infrastructure is enormous and includes user power usage. By employing machine learning and deep learning algorithms on this data, it is possible to precisely identify individuals who steal electricity. electricity consumption dataset released by State Grid Corporation of China is used to train and test the models. The Dataset released by State Grid Corporation of China is used since It was the sole dataset accessible online. The total number of users is 42372. The Number of normal users is 38757. The Number of aberrant user or electricity thieves 3615. A set of six algorithms used in the research. the most accurate algorithm is Support Vector Machine SVM. The use of this technology in this field may improve the precision of energy theft detection as well as the issues and outcomes associated with power.
More specifically, the Deep Conventional Neural Network CNN model effectively completes two tasks: it distinguishes between non-periodic energy and, at the same time, preserves the general features of the power consumption data. The results of the testing show that the deep CNN model has the highest level of accuracy and performs better than previous models for energy theft detection.in this thesis a set of six which is algorithms (Random Forrst,Logistic Regression,Support Vector Machine,K Nearst Nighbour and NN Deep Learning) used, the best algorithm chosen.the work provided that the most accuarate algorithm is the SVM with accuracy of 91%.

Users share their opinions on various products through online reviews on e-commerce sites and linked microblogs. Reviews from users are a terrific way to learn more about what kinds of things interest them. Some recent efforts have turned to reviewing texts and the abundance of information they provide to improve overall score collaborative filtering recommender systems. This paper includes review terms, review topics, and review attitudes. The works in question utilize review texts to infer user preferences. In this study, we comprehensively analyze current attempts that use review texts. We investigate how these texts are used to overcome some of the most pressing issues plaguing conventional forms of collaborative filtering.

The "infinite impulse response" (IIR) digital filter was developed using the hybrid optimization artificial intelligence (AI) algorithm. At AI algorithm D-PSO, which stands for the "particle swarm optimization" dynamic topology, we make use of an approach that is both efficient and simple to memorize. The researchers investigated strategies to maximize the permissible ripples in a passband, the stopband, and the transition band while minimizing the nonlinear mean square error (MSE) between an initial filter response and the required filter response in those bands. Using the approach resulted in a considerable reduction in the square error rates of both the passband and the stopband, according to the findings of an experiment. The IIR digital filter square error values with the D-PSO are superior to those of digital filters using evolutionary AI algorithms such as the dynamic inertia PSO (DI-PSO) or the modified dynamic inertia PSO (MDI-PSO); this allows the IIR digital filter to achieve better results because the square error values depend on the sequence in which the filters are applied. Therefore, compared to digital filters and coefficients created by evolutionary ways, the ones produced by the suggested method are more precise and stable than those produced by evolutionary AI approaches.

Integrating unmanned aerial vehicles (UAVs) into a relay-based free space optical (FSO) communication system has several blessings that incorporate dealing with turbulence-induced atmospheric scintillation due to their flexible mobility. This study extensively assesses a UAV-FSO system that is based on a decode-and-forward dual-hop strategy with multiple transmission sources. Through the incorporation of the Gamma-Gamma (GG) distribution to measure factors such as atmospheric losses, atmospheric turbulence, angle-of-arrival fluctuations, and pointing errors, a faithful formula for the probability density function (PDF) of the total channel gain is derived. A mathematical representation for the average bit error rate (BER) of the system is also derived and later on, validated through extensive Monte Carlo simulations. The simulation outcomes spotlight model robustness across a range of operational conditions. These results underline the enhanced efficiency and versatility of the UAV-assisted FSO systems that can manage various data sources, and consequently, they can be quite applicable in the case of surveillance and mobile network communications.

The integration of Wireless Sensor Networks (WSNs) in agriculture has transformed precision farming, enabling monitoring and management of crops. However, traditional WSNs face challenges related to coverage, scalability, and adaptability to varying conditions. This study introduces a WSN architecture that combines terrestrial and aerial (drone-based) sensor nodes to enhance the efficiency of smart agriculture. While terrestrial nodes collect ground-level data, aerial nodes offer a perspective that can swiftly respond to changing environmental conditions. This combined approach optimizes resource allocation, enhances data accuracy, and ensures coverage. By conducting simulations and field tests, we assess the performance of the WSN in terms of coverage, energy efficiency, and throughput. The results indicate that hybrid WSNs significantly improve precision agriculture capabilities by providing a solution for real-time monitoring, efficient resource utilization, and timely decision-making. This study sets the stage for advancing cutting-edge farming technologies to meet the increasing need for productive agricultural practices.

This work presents a general and introductory review of Visible light communication (VLC) systems represent an effective alternative to conventional wireless communications, providing a fast means of transmitting data in indoor environments. However, the dynamic nature of wireless optical channels poses several constraints that must be taken into account during design, especially at the receiver side. Among the most prominent of these challenges are those related to receiver movement and orientation, which may cause issues related to channel gain and signal to noise ratio (SNR).Since the channel changes continuously over time due to several reasons, including user movement and environmental factors such as dimming during use, accompanied by interference from other ambient lights, researchers are seeking to find accurate and continuous methods for estimation. In addition to the problems that come with relying on line-of-sight (LOS), it imposes limitations and challenges related to signal degradation due to unavoidable obstacles, and thus more efficient nonlinear techniques such as non-line-of-sight (NLOS). Advanced models have been proposed to solve receiver problems, including advanced receiver motion models, such as those for user device orientation based on experimental measurements. Device orientation statistics are presented for both sitting and walking activities, and other random path models based on light direction are considered with the importance of taking into account receiver orientation and motion patterns to improve performance. Also, deep learning methods are effective in improving resource allocation and signal detection to enhance flexibility especially in complex indoor environments. In this paper, the latest developments related to the problems and innovative solutions to ensure reliable communication in visible light communication (VLC) networks are discussed.

Sustainability refers to the ability to maintain balance and continuity over the long term, whether in the environment, in the economy, or society, so one of the highest-paid professions in the world is data science because this profession is concerned with providing companies with tools and systems with a machine learning system, such as the grade estimation system for universities and the system for extracting thousands of pieces of data to make decisions. Data science salaries vary across different fields and depend on factors such as skills, programming experience, and certifications held. In recent years, experts have considered the job of data scientists to be the most attractive. However, people with data science experience seem to be rare. This study aims to highlight data science salary trends for the years 2021–2023 for Sustainability. Focusing on various aspects of employment, including work experience, job titles, and company locations, this data set provides valuable insights into salary distributions within the industry. The research is based on a dataset taken from the open-source ‘Kaggle’ and an online survey of various sites. This study showed that the level of salaries for data analysts has increased significantly in 2023. People with the highest salaries are experienced professionals who make the most money. The study also showed that salaries in US dollars are the highest, with experienced contractors earning 416,000.

Facial expression identification has garnered considerable attention in recent years owing to its extensive applicability across various domains, including human-computer interaction, market research, and healthcare. The primary objective of Facial Emotion Recognition (FER) is to correlate various facial expressions with their corresponding emotional states. Advancements in deep learning have significantly enhanced the recognition accuracy of FER technology relative to conventional approaches. This study seeks to improve the accuracy for facial emotion identification by introducing a Deep Learning Cascaded Network (DLFER) founded on the EF-FER1 and EF-FER2 architectures. The hyperparameters of the EfficientNet-B3 network were fine-tuned to improve facial expression representation and classification. The trials utilized the widely recognized Facial Expression Recognition 2013 (FER2013) dataset, comprising 35,887 greyscale photos of faces, each linked to one of seven specific emotions. The model's performance was assessed using accuracy, precision, recall, and F1 score. A comparative analysis was also performed with similar modern studies. The trials demonstrated that the Cascaded Network (DLFER) attained a classification accuracy of 82.09%, surpassing that of state-of-the-art models.

This research aims to classify water bodies in Iraq using Sentinel-2A satellite images and artificial neural networks (ANNs) techniques. This satellite provides high-resolution multispectral imaging data, which helps neural networks to distinguish water from other features such as lakes, rivers, and reservoirs. An ANN model was trained using pre-labelled datasets to recognize the distinctive patterns of water. In this research, a new index called Water Body Index (WBI) is introduced to extract water bodies, which is based on the difference between six spectral bands of Sentinel-2A: blue (B), red (R), green (G), near infrared (NIR), short infrared 1 (SWIR 1), and short infrared 2 (SWIR 2). Using the neural net library in R I obtained a new linear equation that serves as the index. The new index concept had two distinct proposed versions. WBI-C (complete version). WBI-R (reduced version). The distributions of these new indices were compared with four other previously used indices: NDWI, MNDWI, MUWI-C, and MUWI-R. The results showed that WBI-C and WBI-R were more efficient in classifying water compared to vegetation, buildings, and other elements. The total average accuracy rates were: WBI-R: 99.6%, WBI-C: 99.8%, NDWI: 99.6%, MNDWI: 98.7%, MUWI-C: 98.9%, MUWI-R: 99%. As for the average Kappa Coefficient: WBI-R: 95.4%, WBI-C: 97.7%, NDWI: 85%, MNDWI: 87%, MUWI-C: 87% , MUWI-R: 89%. As for the average F-score: WBI-R: 97.7%, WBI-C: 98.9%, NDWI: 97%, MNDWI: 93.7%, MUWI-C: 93%, MUWI-R: 94%. These results show that WBI-C and WBI-R outperformed other indices in classifying water bodies with high accuracy.

The detailed inspection surveys the literature surveys the significant influences that robotics has been on many different fields, like healthcare and industry. This study takes a look at the advantages and the challenges of robots in different industries, following their development from simple devices into complex and very intelligent components today. The research demonstrates how robots have been developed from traditional manufacturing to more effective types that are used in healthcare and industry by depending on academic research, technical progress and real data. The use of robots has dramatically increased the efficiency of production in the industrial field, eliminating the error limits which resulted in cost savings as well as maximum quality articles. Many usages that, appear for robots, like those in healthcare for the monitoring and diagnostics of patients, as well as increase the precision of surgical operations. This full change explains the robot’s potential to transform the care of patients as a whole. Also, many studies focused on the robot’s growing importance in the service sector. This article confirms the robot’s potential to transform multiple industries to be under the control of robots to obtain more precision, quality and improved production in various fields.

Data Encryption Standard (DES) is a broadly used symmetric-key algorithm for ciphering digital data. However, there are several vulnerabilities related to this technique, including key distribution, namely, the key must be securely passed between the associated parties, and susceptibility, that is, the DES is defenceless against brute force and cryptanalysis attacks upon the key and the message, respectively. This paper attempts to tackle the first vulnerability by using the Diffie-Hellman protocol, as it enables the parties to interchange unshared secret. In addition, the second vulnerability is alleviated through: (1) performing the Columnar Transposition Cipher on the message before DES, (2) replacing the classical shifting process of the key with a type of shifter called Barrel. These improvements are vital for safeguarding against breaches and sophisticated attacks. The findings of conducted experiments have revealed that the proposed method satisfies the key and plaintext avalanche with a 50% output bit flipped in the ciphertext, and the average time required to crack passwords handled by the enhanced DES is more than that for classical DES. Therefore, the proposed method of this paper has raised the security requirements of DES.

This research paper is interested in studying how to obtain the best response to the (AVR) Automatic Voltage Regulator, which is an essential device because of its clear effect on maintaining the stability of the voltage in various circumstances through researching to find the best values for the parameters of the Proportional Integral Derivative (PID) which are (Kp, Ki, Kd). After several experiments and studies by researchers to improve the AVR response, we discuss here another new study by applying the cheetah Optimization (CO) algorithm and knowing the extent of its ability to find the best solutions by comparing results by time limits, namely delay time (td), rise time (tr), peak time(tp), stalling time(ts), and Overshot (OS) as well as determining fitness function for Integral Squirrel Error (ISE). Where excellent results were obtained when implementing the (CO) algorithm when comparing the values of time limiters and error criteria, it is also worth mentioning that one of the most important properties of this algorithm is the speed of performance, as it is within the limits of seconds, so that it is the fastest algorithm among other algorithms.

Improving the effectiveness of audience targeting in digital advertising campaigns is a key factor for companies’ success in the digital age. With the rapid development of artificial intelligence technology, these campaigns have become more precise and engaging for the target audience. This paper reviews the importance of exploiting artificial intelligence tools to improve the effectiveness of digital advertising campaigns and e-marketing through improving personal targeting, big data analysis, and content personalization. The study includes a review of previous research on this topic and the various artificial intelligence tools used in this field, such as machine learning, big data analysis, and recommendation systems used in recommending products to users online while providing recommendations for improving digital targeting strategies.

While complex network development and dynamic traffic are still developing, there has been great optimization and management of network traffic. This paper will develop a feature-based approach based on intelligent selection and reduction to improve traffic flow management, optimization of resource utilization, and enhancement of network security. While methods of statistical correlation and clustering retain only the relevant features in the system, irrelevant ones are filtered out and operational efficiency is optimized along with the decision-making process. Advanced correlation algorithms are proposed in a cross-selection set, such as Spearman and Kendall, besides dendrogram-based clustering analysis. This makes the solution robust for designing and monitoring modern network environments. It can be seen from the experimental results that the proposed framework can remove redundancy and enhance the feature interpretability, scalability, and adaptability to domain-specific network requirements. Furthermore, the framework proves its efficiency in capturing nonlinear feature relationships, making it robust for real-world network applications.