Journal of Data Science and Information Technology

You are nothing witout your set eyes care set injury magna consectr elit, do eiusmod tempor incididunt or ut labore areas disease eyecare dolore aliqua. Ut enim adet minim veniam, and quis nostrud exercitation produrYou are nothing witout your set eyes care set injury magna consectr.

You are nothing witout your set eyes care set injury magna consectr elit, do eiusmod tempor incididunt or ut labore areas disease eyecare dolore aliqua. Ut enim adet minim veniam, and quis nostrud exercitation produrYou are nothing witout your set eyes care set injury magna consectr elit, do eiusmod tempor incididunt or utlabore areas disecare dolore.aliqua. Ut enim ad et minim veniam, and quis nostrud exercitation produrconducted right in our clinic.Ut enim ad et minim veniam, and quis nostrud exercitation produrconducted right in our clinic.

Adaptive Self-Healing Software Systems Using Large Language Models:Bridging Configuration Validation, Vulnerability Detection, and Specification Learning

Somasekhar Gubbala

Software reliability is a persistent challenge due to dynamic misconfigurations, hidden vulnerabilities, and evolving system specifications. Although recent advances in Large Language Models (LLMs) have shown great potential in various software engineering tasks—such as configuration validation, vulnerability detection, and specification generation—each of these works tends to focus on isolated aspects of reliability. In this paper, we present AutoHeal, a novel LLM-driven framework for adaptive self-healing software systems that unifies these capabilities. AutoHeal employs multi-phase reasoning: (1) validating configurations using prompt-conditioned analysis, (2) detecting vulnerabilities through contextual code exploration, and (3) reconstructing specifications to maintain system consistency. We introduce an LLM-ensemble learning approach that adaptively tunes prompts and responses based on system feedback and historical corrective actions. Experimental results on ten open-source projects demonstrate that AutoHeal achieves an average precision improvement of 18% over state-of-the-art single-task baselines in identifying and automatically remediating misconfigurations and vulnerabilities. This work opens a new direction in building resilient and intelligent self-managed software systems powered by large-scale language models.

TriboFusion: A Multi-Parameter SurfacePerformance Index for Comparative Evaluation of Heat-Treated, Nitrided, Chromized and Boronized Steel Surfaces under Sliding Wear

Ramamurthy Narasimhan

Heat treatment, nitriding, chromizing, and boronizing are the most common surface engineering techniques to improve the tribological performance of steel components operating under severe sliding conditions. Although the surface hardness, wear resistance and frictional behavior are improved by these treatments, their effectiveness depends on the working conditions, the characteristics of the diffusion layer, the surface roughness and the resulting microstructure. The present study presents an indepth comparison of the tribological behavior of heat-treated, nitrided, chromized and boronized steel surfaces, which are obtained conventionally from the same starting material. The treated specimens were characterized by microhardness testing, surface roughness analysis, optical microscopy, scanning electron microscopy and elemental characterization techniques. The tribological performance is evaluated by calculating the coefficient of friction, wear rate, material loss, wear-track depth and the dominant wear mechanisms (adhesive wear, abrasive wear, oxidation, delamination and microcracking) under comparable testing conditions. We propose a Multi-Parameter Surface Performance Index (MSPI) which combines multiple mechanical, microstructural, geometrical and tribological properties into one quantitative performance index. This framework, called TriboFusion, aims to enable objective comparison of different surface-treatment techniques. The proposed framework normalizes heterogeneous experimental measurements and applies a weighted aggregation strategy to rank the overall performance of each surface treatment. Conventional methods evaluate tribological properties based on individual parameters (hardness, wear rate). TriboFusion takes into account a set of interacting tribological properties at once, thus providing a more holistic evaluation. The proposed methodology provides a systematic decision-support tool for the selection of the most suitable surface-treatment process for engineering components such as bearings, pumps, valves, sleeves, rods and couplings used in the automotive, manufacturing, mining, and oil and gas industries. The framework is computationally efficient, generic and easily adaptable to other surface engineering technologies.

AI-Driven Predictive Maintenance Optimization Framework (AIPMOF) for Intelligent Network Fault Detection and Infrastructure Reliability Enhancement

Gaurav Saxena

Modern network infrastructures support mission-critical services across cloud computing, telecommunications, industrial automation, and enterprise information systems. As these infrastructures become increasingly complex, conventional reactive and preventive maintenance strategies struggle to identify hidden performance degradation before service disruptions occur. Artificial Intelligence (AI)-driven predictive maintenance has emerged as an effective solution for forecasting network failures, optimizing maintenance schedules, and improving infrastructure reliability through continuous analysis of operational data. This paper proposes the AI-Driven Predictive Maintenance Optimization Framework (AIPMOF), an intelligent framework that integrates data acquisition, preprocessing, feature engineering, machine learning-based fault prediction, reliability assessment, and maintenance decision support into a unified predictive maintenance architecture. The framework employs Support Vector Regression (SVR) and AdaBoost Regression to predict network reliability scores using key operational indicators, including CPU utilization, memory utilization, and network latency. Experimental evaluation was conducted using a dataset containing 200 network performance records. Performance was assessed using multiple regression evaluation metrics, including the coefficient of determination (R²), Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Explained Variance Score (EVS), Mean Squared Logarithmic Error (MSLE), and Median Absolute Error (MedAE). The proposed framework demonstrates strong predictive capability, with SVR achieving an R² value of 0.9444 on the testing dataset, outperforming AdaBoost Regression, which achieved an R² value of 0.9195. The results indicate that AI-based predictive maintenance can accurately estimate infrastructure reliability and provide early warnings of potential failures, thereby reducing downtime, maintenance costs, and operational risks. The proposed AIPMOF framework contributes a scalable and intelligent decision-support mechanism suitable for cloud infrastructures, software-defined networks, enterprise systems, and Industrial Internet of Things (IIoT) environments. The framework provides a foundation for future autonomous, self-healing network management systems capable of continuously learning from operational data and adapting maintenance strategies in real time.

HYPERION-Q: A Graph-Guided Self-Validating and Hardware-Aware Framework for High-Performance Query Processing

Ramachandra Reddy Vangala

Modern data management systems must simultaneously address three critical challenges: efficient query optimization for large queries, reliable detection of logical errors in database engines, and high-performance processing across heterogeneous hardware architectures. Traditional query optimizers rely on dynamic programming strategies that exhibit exponential complexity when evaluating join orders. At the same time, ensuring correctness of query execution engines remains difficult due to the absence of reliable ground truth for validating complex queries, particularly in spatial and analytical workloads. Moreover, the increasing availability of high-performance hardware such as GPUs and NVMe storage arrays demands new system architectures capable of exploiting these resources effectively. In this paper, we propose HYPERION-Q, a novel framework that integrates graph-guided query optimization, self-validating query testing, and hardwareaware execution planning. The framework combines three complementary ideas: (i) a graph-based join enumeration strategy that extends subset convolution techniques for accelerated optimization, (ii) a transformation-invariant validation mechanism inspired by affine-equivalent query generation to detect logical inconsistencies, and (iii) a hardware-aware execution planner that dynamically maps operators to GPU and NVMe storage paths. The proposed framework significantly improves query optimization efficiency while ensuring correctness and high throughput. Experimental results demonstrate that HYPERION-Q improves query planning speed by up to 35× and increases processing throughput by 2.8× compared to baseline systems.

Data Science Applications in Bioinformatics for Genetic Sequencing of COVID Mutations

Krishna Moorthy Selvaraj, Satya Sukumar Makkapati, Kishor Kumar Amuda, Surya Rao Rayarao and Dr. Suryakiran Navath, Ph.D.

This manuscript explores the integration of data science methodologies into bioinformatics for the comprehensive analysis of genetic sequencing data related to COVID-19. Leveraging advanced computational approaches, we showcase the diverse applications of data science in unraveling the complexities of SARS-CoV-2 mutations. The presented methods and results underscore the significance of a multidisciplinary approach in understanding the genomic landscape of the virus.

Genomic sequences of SARS-CoV-2 were obtained from diverse sources, creating a rich and extensive dataset. Data preprocessing involved quality control and feature engineering to prepare the data for subsequent analyses. Unsupervised clustering techniques and machine learning models, including Random Forest and Gradient Boosting, were applied to discern mutation patterns and predict the functional impact of mutations. The integration of network analysis further extended the exploration into protein-protein interactions and epidemiological dynamics associated with genetic mutations.

Computational Molecular Biology in Data Science Applications on Bioinformatics in Genetic Sequencing of COVID Mutations 

Krishna Moorthy Selvaraj, Satya Sukumar Makkapati, Kishor Kumar Amuda , Surya Rao Rayarao, Dr. Suryakiran Navath, Ph.D

Analyzing The Impact of Virtual Private Networks (VPNS) On Online Security Using The DEMATEL Method

Tejasvi Gorre

A Virtual Private Network (VPN) is a technology that enhances online privacy and security by establishing a secure, encrypted connection between a user's device and a remote server. Acting as a protective tunnel, a VPN routes the user's internet traffic through this encrypted connection, shielding their data from potential cyber threats, surveillance, and unauthorized access. VPNs serve as powerful tools for safeguarding sensitive information, especially when using public Wi-Fi networks, as they prevent hackers or malicious entities from intercepting data transmissions. Additionally, VPNs allow users to mask their true IP address with that of the remote server, effectively anonymizing their online activities and bypassing geographical restrictions. Beyond security and anonymity, VPNs offer other practical benefits. They enable users to access region-restricted content, granting access to websites, services, and streaming platforms that might otherwise be unavailable in their location. Whether for personal use or business needs, VPNs have become integral in today's digital landscape, providing a reliable means of maintaining privacy, evading censorship, and fortifying online experiences. the significance of researching Virtual Private Networks (VPNs) lies in their pivotal role in modern cybersecurity and digital privacy.

As online threats and data breaches continue to escalate, understanding the intricacies of VPN technology is crucial for developing advanced encryption techniques, improving network security protocols, and countering emerging cyber risks. Furthermore, VPN research contributes to enhancing user awareness about the importance of safeguarding personal information, aiding in the design of more effective privacy solutions for individuals, businesses, and organizations. By delving into VPNs, researchers can devise strategies to mitigate cyber threats and ensure a safer online environment for users worldwide. the DEMATEL (Decision-Making Trial and Evaluation Laboratory) method is a systematic approach used for analyzing complex interrelationships among various factors in a decision-making process. By visually mapping cause-and-effect relationships, DEMATEL helps to identify key drivers and dependencies within a system. It quantifies the strength and direction of these relationships, enabling decision-makers to prioritize factors based on their impact. This method finds applications in diverse fields such as business, engineering, healthcare, and environmental management, aiding in understanding intricate systems, formulating effective strategies, and making informed decisions in complex environments. Express VPN, NordVPN, CyberGhost VPN, Private Internet Access, Surfshark. Express VPN, NordVPN, CyberGhost VPN, Private Internet Access, Surfshark. calculate the average of the matrix and its threshold value (alpha) Alpha 0.873339618 If the T matrix value is greater than threshold value then bolds it.

Power Electronics in Energy Systems: Enhancing Efficiency and Quality in Electrical Energy Conversion and Distribution

Mahesh Kumar Mishra

Focus is placed on all aspects of electrical energy as well as innovation in energy generation and delivery, three different approaches, and efficient technologies in energy and energy systems research. Research projects focus on systems and equipment for converting, supplying, and using energy as a form of electricity. To increase effectiveness and quality while fostering the gradual materialization of intelligent, efficient energy, power electronics are increasingly a more fundamental component of power systems. Power systems use a wide variety of power electronics. Power systems are the physical study of converting electrical energy from one medium to another. More than 80% of the total electricity produced at a global average rate of 3.4 billion kilowatts per hour per year is reprocessed or recovered in industries like electronics.

Electrical energy is processed or converted using power electronics converters, often known as power converters or switching converters. There are two types of electricity: AC power and DC power. Depending on the kind of power it uses, the distribution system is split into AC distribution systems and DC distribution systems. Once electricity is produced, it needs to be transported from power plants to regional distribution networks over considerable distances. This is accomplished through high-voltage transmission cables, often known as the power grid. High voltages are used on these transmission lines to convey the electricity in order to reduce energy loss during long-distance movement.

Cloud-Driven Big Data Adaptation Leveraging Distributed Systems

Prabhakar Vagvala

Cloud Computing Environment Optimization: A Comprehensive COPRAS Methodology Approach

Janaki Ram Kiran Gummaluri

Cloud computing has emerged as a transformative technology, offering diverse service models to meet varying organizational needs. This study employs the Complex Proportional Assessment (COPRAS) method to comprehensively evaluate and analyze different cloud environments, providing a nuanced approach to cloud service selection. The research investigates five distinct cloud environment types: general-purpose, service-centric, zone-centric, distance-centric, and cost-centric, examining their performance across critical parameters including quality of service, number of available services, availability zones, consumer distance, and hourly cost. The multi-criteria analysis reveals significant variations in cloud environment effectiveness. Zone-centric environments emerged as the top performer, achieving a remarkable quality index of 0.291 and a 100% usability degree. Service-centric environments followed closely, demonstrating a 92.03% usability degree and highlighting the importance of service availability. General-purpose environments showed moderate performance with a 63.97% usability degree, indicating their versatility. Conversely, distance-centric and cost-centric environments exhibited the lowest performance, suggesting limitations in meeting comprehensive organizational requirements. Key findings underscore that cloud computing is not a one-size-fits-all solution but a complex ecosystem requiring strategic selection. The research emphasizes that while cost is important, it should not be the sole determining factor in cloud environment selection. The study provides a robust framework for decision-makers, enabling them to align cloud infrastructure choices with specific organizational objectives. The methodology offers critical insights into the evolving cloud computing landscape, addressing the growing complexity of data management and the increasing demand for scalable, secure computing solutions. By presenting a comprehensive evaluation approach, the research contributes to a more sophisticated understanding of cloud environment selection, encouraging organizations to adopt a strategic, multi-dimensional approach to cloud infrastructure deployment.