Journal of Science Engineering Technology and Management Science

The Funds Flow Statement is an important financial management tool used to analyze the movement of funds between two accounting periods. It helps identify the various sources from which funds have been generated and the areas where these funds have been utilized. Unlike the cash flow statement, which focuses only on cash transactions, the funds flow statement provides a broader view of changes in the financial position by examining variations in working capital. It enables management, investors, creditors, and other stakeholders to evaluate the financial stability, operational efficiency, and long-term solvency of an organization. A detailed funds flow analysis assists in understanding the effectiveness of financial planning, capital investment decisions, and the overall utilization of financial resources.This study focuses on the Funds Flow Statement Analysis at Bajaj Allianz Life Insurance Company Ltd. The primary objective is to examine the company's sources and applications of funds over the study period and to evaluate its financial performance and fund management practices. The analysis considers key financial components such as shareholders' funds, long-term borrowings, investments, fixed assets, current assets, current liabilities, reserves and surplus, and changes in working capital. By comparing financial statements over multiple years, the study identifies trends in fund generation, investment activities, financing decisions, and resource allocation.The research is based on secondary data collected from the company's published annual reports, financial statements, industry reports, and other reliable financial sources. Various financial analysis techniques, including comparative balance sheet analysis, schedule of changes in working capital, preparation of funds flow statements, and interpretation of financial ratios, are employed to assess the company's financial position. These analytical tools provide valuable insights into the organization's ability to generate funds from operations, maintain adequate working capital, finance long-term investments, and meet its financial obligations efficiently.The findings of the study indicate that effective fund management plays a significant role in ensuring the financial strength and operational sustainability of the company. The analysis highlights the relationship between operating activities, investment decisions, and financing strategies in influencing the overall financial health of the organization. It also demonstrates how proper allocation of funds contributes to business expansion, customer service enhancement, technological development, and longterm profitability in the highly competitive insurance sector.

Keywords :

Author : Ms. BORRA AKHILA. P, V. DEEPA

Title : “FUNDS FLOW STATEMENT ANALYSIS”AT BAJAJ ALLIANZ LIFE INSURANCE COMPANY LTD

Volume/Issue : 2026;03(07)

Page No : 246-253

The research article deals with the employee absenteeism in Hetero Drugs Limited, and its causes, consequences and mitigation measures. Absenteeism poses a fundamental problem in organizations in terms of productivity, operational effectiveness, the morale of employees and organizational success. With regards to absenteeism, the study aims to have an in depth comprehension of the process through a critical analysis of the issue through other lenses. Based on the observations made by workers, workers unions and management officials, the study investigates several elements of absenteeism. It also includes key factors causing employee absenteeism (personal, organizational, social, and workplace). The study then looks at absenteeism rates for the company at their existing level and identifies what can be done to reduce absenteeism rates and enhance attendance. Based on the results of this study, both short-term measures and long-term measures are recommended to combat absenteeism and increase employee commitment. The recommendations are on enhancing working conditions, employee well-being, communication, motivation, and the utilization of engagement practices overall. Additionally, such strategies have been highlighted in this study for enhancing employee morale, developing better organizational relationships, and building a favorable work environment. Hetero Drugs Limited, on the whole will have the results of the abovementioned work supported by absenteeism data reduction rates, greater productivity and a more-dedicated, pleased and happy workforce.

Keywords :

Author : Ms. Kandada Mahita Reddy, Dr. K. Gyaneshwari

Title : Absenteeism Of Employees At Hetero Drugs Limited

Volume/Issue : 2026;03(07)

Page No : 254-261

Insurance has evolved from being a financial protection mechanism to becoming an effective long-term investment tool that supports wealth creation, financial security, and future planning. This study, titled "Analysis of Insurance as a Long-Term Investment Tool with Reference to HDFC Standard Life Insurance," aims to evaluate the role of life insurance products in meeting the long-term financial objectives of policyholders. The research focuses on understanding customer preferences, awareness, satisfaction levels, and the investment benefits associated with HDFC Standard Life Insurance plans. It also examines the factors that influence customers' decisions while selecting insurance products, such as returns, risk coverage, tax benefits, premium affordability, and policy features. The study is based on both primary and secondary data. Primary data were collected through structured questionnaires administered to policyholders, while secondary data were obtained from company reports, journals, books, and published research articles. Descriptive statistical techniques, including percentage analysis, charts, and graphs, were used to interpret the collected data and identify key trends. The findings indicate that life insurance is increasingly perceived as a reliable long-term investment option due to its dual benefits of financial protection and disciplined savings. HDFC Standard Life Insurance has gained customer confidence through its diversified product portfolio, flexible premium options, customer-centric services, and digital support. However, the study also identifies areas for improvement, such as enhancing customer awareness regarding policy features, simplifying claim procedures, and providing personalized financial guidance. Overall, the research concludes that HDFC Standard Life Insurance plays a significant role in helping individuals achieve long-term financial stability and investment growth while ensuring comprehensive life protection.

Keywords :

Author : Ms. M. Swetha, V. Deepa

Title : Analysis Of Insurance As A Long Term Investment Tool W.R.T. Hdfc Standard Life Insurance

Volume/Issue : 2026;03(07)

Page No : 262-268

Foreign Direct Investment (FDI) has emerged as a significant driver of economic growth, technological advancement, employment generation, and business expansion in developing economies. In India, the liberalization of FDI policies by the Government of India has encouraged multinational corporations to establish and expand their operations across various sectors. Among these organizations, Amazon India has become one of the most prominent beneficiaries of foreign capital inflows. According to the Department for Promotion of Industry and Internal Trade (DPIIT, 2025), increased FDI inflows have strengthened the country's retail, logistics, warehousing, and digital commerce infrastructure. The present study examines the impact of Foreign Direct Investment on the growth of Amazon India and evaluates how foreign capital has contributed to business expansion, operational efficiency, market penetration, and employment opportunities.The study is based on secondary data collected from Amazon India reports, DPIIT publications, Reserve Bank of India reports, industry analyses, and e-commerce market studies. Amazon India's expansion strategy has been significantly supported by foreign investments, which enabled the company to establish fulfillment centers, strengthen supply chain networks, enhance technological capabilities, and improve customer service quality. As reported by the Reserve Bank of India (2025), FDI inflows into the e-commerce and retail sectors have accelerated digital transformation and increased market competitiveness. The findings indicate that foreign direct investment has positively influenced Amazon India's revenue growth, infrastructure development, employment generation, and customer reach. Furthermore, FDI-supported investments have contributed to innovation in logistics management, artificial intelligence applications, cloud computing services, and digital payment systems. Industry reports published by the India Brand Equity Foundation (IBEF, 2025) suggest that increased foreign investment has strengthened India's position as one of the world's fastest-growing e-commerce markets. The study concludes that Foreign Direct Investment has played a crucial role in the growth and development of Amazon India by facilitating capital availability, technological advancement, operational expansion, and market competitiveness.

Keywords :

Author : Mr. ANANTH KUMAR. P, T. RAKESH

Title : IMPACT OF FOREIGN DIRECT INVESTMENT ON THE GROWTH OF AMAZON INDIA

Volume/Issue : 2026;03(07)

Page No : 269-279

The total cost of bearing a particular level of yield is the cost of all the determinants of recommendation secondhand. Conventionally statistician use models accompanying two inputs capital, K. and labor, L. Capital is pretended expected the established recommendation message that the amount of capital secondhand does not change accompanying the level of result. The rent price for one of capital is meant r. Thus the total established costs equal Kr. Labor is the changing recommendation aim that the amount of labor secondhand changes accompanying the level of yield. In fact in the short run the only habit to change profit is by variable the amount of the changeable recommendation. Labor is meant L and for one cost or undertake rate is designated w so the total changeable costs is Low. The declaration places itself at the aid of the country with its own government, management, manufacturing, and the association to accomplish the aims of a social democracy developing in the affluence and the well-being of allure family- An experience progressively fulfilled accompanying the reveal of the country's saving and change in the financial synopsis of the realm. In contemporary's globe, the declaration of unoriginal bookkeeping and analyzing has captured a less in rank and accountants progressively donate towards the administration of sparse possessions like capital, land and request clever resolutions. This has unlocked up advances manage and overwhelming space Cost and Works accountants to jostle trustworthiness as Cost and Management Accountants similarly new ranges and dream attending in India and overseas. Members concerning this declaration will be the hidden motive in the crew of administration while in enrollment and a key advisor, an productive Cost and Management Auditor and unfit guide working. This is reason Cost Accountants in India are named Management Accountants everywhere the planet. It’s our added name. We persuade you to peruse through our site. Complete Information on our active, record and professional authorization are all possible.

Keywords :

Author : MACHAGONI PRIYANKA, V. DEEPA

Title : COST CONTROL ANALYSIS AT HERO MOTOCORP LIMITED

Volume/Issue : 2026;03(07)

Page No : 280-285

The project aims to comprehend by virtue of what within &extrinsic determinants influence the future price of the guest. It too involves portion the financiers to set either to purchase a party share a suggestion of correction established fundamental and mechanics reasoning. Fundamental study is a stock appraisal plan that uses fiscal reasoning namely an study of a party s fiscal dossier to conclude the change of that party s stock price Technical study refers to the study of the price operation instability retail generally, but not particularly through charts so that forecast future prices. The purpose still serves the financiers to select either to purchase the party shares a suggestion of correction or likewise to learn fundamental reasoning of impartiality shares and the determinants that influence the guest s conduct.The dossier secondhand for the study is subordinate dossier. Such as News documents, Internet, Magazines and Books.The financier can see the risk and return of the shares utilizing this reasoning and likewise valuable for financier to elect about moment of truth skyline of expenditure. The financier can estimate the future EPS and DPS by way of the businessrelated signs. The financier bear resolve the action of stock exchange all at once also the practice of the campaign of the shares at which point the financier is inclined install. The study confirmed that the accomplishment of SBI is better than AXIS bank cause the range of vacillations is reduced accompanying SBI. Even though skilled vacillations, overall act was powerful. Due to reduced excitability and powerful character we can reply that the conduct of Andhra carbohydrate enterprises was better than Bajaj Hindustan carbohydrate labors.

Keywords :

Author : Mr. RAOULAKOLA VISHAL, V. DEEPA

Title : FUNDAMENTAL AND TECHNICAL ANALYSIS IN RELIGARE SECURITIES

Volume/Issue : 2026;03(07)

Page No : 286-292

Investor awareness regarding the depository system is crucial for the effective functioning of capital markets and the protection of investor interests. This study examines the level of investor awareness on the depository system with specific reference to IL & FS Investmart Ltd. The research explores investors' understanding of key depository concepts including dematerialization, demat accounts, trading accounts, beneficial ownership, and pledge mechanisms. The study adopts a descriptive research design using primary data collected through structured questionnaires distributed among investors associated with IL & FS Investmart Ltd. The findings reveal that while investors have a high level of awareness regarding basic depository concepts such as demat accounts (92%), awareness levels decline significantly for advanced concepts such as rematerialization (58%) and pledge processes (52%). The study highlights the need for targeted investor education programs to enhance depository system awareness and promote informed investment decisions.

Keywords :

Author : WAJITHA FATIMA, A. BALA KRISHNA

Title : INVESTOR AWARENESS ON DEPOSITORY SYSTEM AT IL & FS INVESTMART LTD

Volume/Issue : 2026;03(07)

Page No : 293-300

Technical analysis is a widely used methodology for forecasting stock price movements by analyzing historical price patterns, trading volumes, and other market data. This study presents a comprehensive technical analysis of select banking stocks at Alice Blue Securities. The research examines the price trends, moving averages, relative strength index (RSI), trading volumes, and support-resistance levels of major banking stocks including HDFC Bank, ICICI Bank, State Bank of India, and Axis Bank. The study employs various technical analysis tools and charting techniques to identify trading opportunities and predict future price movements. The findings reveal that moving average crossovers and RSI divergence provide reliable entry and exit signals for banking stocks. The study concludes that technical analysis, when combined with proper risk management, can significantly enhance trading profitability for investors at Alice Blue Securities.

Keywords :

Author : NAMPALLY LAHARYA, V. DEEPA

Title : A STUDY ON TECHNICAL ANALYSIS OF BANKING STOCKS AT ALICE BLUE SECURITIES

Volume/Issue : 2026;03(07)

Page No : 301-308

Portfolio management is a critical aspect of investment planning that involves the systematic selection and management of investment assets to achieve optimal risk-return outcomes. This study examines the portfolio management practices at ICICI Direct, one of India's leading investment service platforms. The research analyzes the asset allocation strategies, investment performance, and risk management techniques employed in constructing and managing investment portfolios. The study evaluates the performance of a diversified portfolio comprising equity stocks, mutual funds, fixed deposits, bonds, and cash equivalents over a five-year period. Various portfolio performance metrics including alpha, beta, Sharpe ratio, and standard deviation are calculated and analyzed. The findings reveal that the diversified portfolio at ICICI Direct has consistently outperformed the Nifty 50 benchmark, delivering superior risk-adjusted returns. The study concludes that systematic portfolio management, combined with proper asset allocation, is essential for achieving long-term investment objectives.

Keywords :

Author : E. SAI PRASAD, T. RAKESH

Title : PORTFOLIO MANAGEMENT AT ICICI DIRECT

Volume/Issue : 2026;03(07)

Page No : 309-316

As EVs become more mainstream, battery swapping stations must implement battery management in a way that is effective and fair, and that can be affected by the pricing and inefficiency of various battery health and degradation levels. To tackle this challenge, a real-time RUL estimation framework is developed based on the Battery RUL Dataset available from Kaggle . Parameters such as cycle index, discharge time, charging time, voltage characteristic, time constant, etc., describing the battery degradation behavior are included in the dataset. Based on the operational and electrical characteristics, the RUL estimation of EV batteries is performed using regression techniques such as the RF, Lasso, GB, Kernel Ridge, DT and XGBoost regression. In particular, XGBoost achieves the best test RMSE of 3.50 and is the most accurate among the models, which makes it a promising model for making accurate RUL estimates and for making fair dynamic pricing for battery swapping stations. To enhance the prediction performance and the interpretability we propose the use of the Stacking and Voting Regressors, providing an RMSE of 3.039 and 3.329, respectively. Moreover, LIME and SHAP are utilized to understand the model outputs and to detect influential factors. The flask-based interface offers a realtime input and prediction, which brings transparency, data-driven and fair pricing methods to EV battery swapping systems.

Keywords : Battery swapping station, electric vehicle, machine learning, remaining useful life, XGBoost”.

Author : JASTI KUMARI ¹ MULLA MUNWAR²

Title : A Machine Learning-Based Real-Time Remaining Useful Life Estimation and Fair Pricing Strategy for Electric Vehicle Battery Swapping Stations

Volume/Issue : 2026;03(07)

Page No : 317-328

An Advanced Medical and Hospital Management System is a comprehensive digital platform designed to improve the efficiency, accuracy, and quality of healthcare services by integrating clinical, administrative, and financial operations into a single system. Traditional hospital management methods often rely on manual processes and disconnected applications, leading to delays, data redundancy, medical errors, and inefficient resource utilization. The proposed system addresses these challenges by providing a centralized solution for managing patient records, appointment scheduling, doctor consultations, laboratory reports, pharmacy inventory, billing, staff management, and hospital administration. The system incorporates modern technologies such as cloud computing, electronic health records (EHR), secure databases, and role-based access control to ensure data integrity, accessibility, and patient privacy. It enables real-time information sharing among healthcare professionals, facilitating faster diagnosis, improved clinical decision-making, and better coordination of patient care. Automated workflows reduce administrative workload, minimize human errors, and enhance overall operational efficiency. Additionally, the system provides analytical dashboards and reporting tools that assist hospital administrators in monitoring performance, managing resources, and making data-driven decisions. Features such as online appointment booking, digital prescriptions, inventory tracking, and automated billing improve patient experience while optimizing hospital operations. Overall, the Advanced Medical and Hospital Management System offers a scalable, secure, and user-friendly solution that enhances healthcare delivery, streamlines hospital workflows, reduces operational costs, and supports high-quality patient care. It serves as an effective platform for modern healthcare institutions seeking digital transformation and efficient clinical operations.

Keywords : In today’s fast-paced world, efficient management of healthcare facilities is crucial to provide quality medical services and ensure patient satisfaction. Traditional manual methods of handling hospital operations, such as maintaining patient records, scheduling appointments, and managing doctor availability, are often timeconsuming, prone to errors, and lack realtime accessibility.

Author : Mrs. JASTI KUMARI1 , PATHIPATI SEKHAR

Title : Advanced medical and hospital management system for efficient clinical operations

Volume/Issue : 2026;03(07)

Page No : 329-339

Vulnerability Assessment and Penetration Testing (VAPT) of web applications is an essential security practice aimed at identifying and mitigating security vulnerabilities within web-based systems. This process involves systematic evaluation of a web application’s security posture through various techniques, including scanning for known vulnerabilities, mis configurations, and coding flaws, followed by exploiting these weaknesses in a controlled environment to determine the level of risk they pose. VAPT typically includes both automated and manual testing methods, which help to detect potential threats such as SQL injection, cross-site scripting (XSS), cross-site request forgery (CSRF), and improper authentication mechanisms. By simulating the tactics and techniques used by real-world attackers, VAPT ensures that vulnerabilities are identified before malicious actors can exploit them. This process also helps organizations comply with regulatory frameworks and standards, ensuring that sensitive data remains protected from unauthorized access. The findings from a penetration test are analyzed, and remediation strategies are provided to mitigate risks, strengthen security, and enhance the overall defense mechanisms of the web application. Through VAPT, businesses can achieve a proactive security posture, ensuring the integrity, confidentiality, and availability of their web applications, and reducing the likelihood of data breaches or cyber attacks.

Keywords : Vulnerability Assessment and Penetration Testing (VAPT) are critical components of a comprehensive cyber security strategy, particularly in the context of web applications.

Author : SK. Anjaneyulu Babu 1 , R.Mamatha 2

Title : VULNERABILITY ASSESSMENT AND PENETRATION TESTING OF WEB APPLICATION

Volume/Issue : 2026;03(07)

Page No : 340-351

Demand forecasting is a critical component in supply chain management and business planning, aiming to accurately predict future customer demand for products or services. Traditional forecasting methods, such as moving averages and ARIMA models, often fall short when dealing with large-scale, non-linear, and multi-factor datasets. In recent years, machine learning (ML) has emerged as a powerful approach to enhance the accuracy and adaptability of demand forecasting models. This study explores the application of machine learning techniques—ranging from classical algorithms like linear regression and decision trees to advanced methods such as ensemble models (e.g., Random Forest, XGBoost) and deep learning architectures (e.g., LSTM networks)—to forecast demand using historical sales data, seasonal trends, promotional effects, and external variables such as weather and holidays. By engineering relevant features like time lags, rolling statistics, and categorical encodings, the models are trained and evaluated using appropriate time-series validation strategies. Performance is measured using metrics such as MAE, RMSE, and MAPE to ensure robust comparisons. The results demonstrate that ML models significantly outperform traditional forecasting methods in handling complex patterns and adapting to dynamic market behavior. The study also emphasizes the importance of feature selection, data preprocessing, and model retraining pipelines in achieving scalable and accurate demand forecasting systems. Overall, this work provides a comprehensive framework for deploying machine learning models in real-world forecasting applications, contributing to improved inventory planning, reduced waste, and better customer satisfaction.

Keywords : In today’s competitive business landscape, accurate demand forecasting plays a pivotal role in ensuring operational efficiency, cost optimization, and customer satisfaction.

Author : SK. Anjaneyulu Babu 1 , V. Pavani 2

Title : DEMAND FORECASTING USING ML

Volume/Issue : 2026;03(07)

Page No : 352-363

The rapid proliferation of Internet of Things (IoT) devices across various domains such as smart homes, healthcare, industrial automation, and smart cities has introduced unprecedented convenience but also exposed critical vulnerabilities to cyber threats. Among these threats, botnet attacks have emerged as one of the most severe and persistent challenges, leveraging large networks of compromised IoT devices to execute Distributed Denial of Service (DDoS), data theft, and other malicious activities. Due to the resource-constrained nature of many IoT devices, traditional security mechanisms are often insufficient or impractical for effective botnet detection. This project proposes a hybrid machine learning-based approach aimed at enhancing the detection accuracy and efficiency of botnet attacks in IoT environments. The hybrid model synergistically combines unsupervised learning techniques—which identify anomalies in network traffic without prior labeling—with supervised learning algorithms that classify traffic patterns into benign or malicious categories based on historical data. By leveraging the strengths of multiple algorithms, including Decision Trees, Random Forests, and Support Vector Machines, and integrating them through ensemble methods like stacking or voting, the model achieves robust detection capabilities against both known and novel botnet variants. The system architecture involves an initial data preprocessing stage that handles feature extraction, normalization, and selection from IoT network traffic datasets such as Bot-IoT and UNSW-NB15. The unsupervised component flags suspicious activities by clustering or anomaly scoring, while the supervised component refines detection by learning from labeled examples. This layered detection approach reduces false positives and enhances detection speed, which are critical for real-time IoT security applications. Experimental results demonstrate that the hybrid model significantly outperforms individual machine learning classifiers in terms of accuracy, precision, recall, and F1- score. Furthermore, the model maintains low detection latency, making it suitable for deployment in real-world IoT environments where timely responses to attacks are essential.

Keywords : The Internet of Things (IoT) has revolutionized the way devices communicate and interact, enabling seamless connectivity across a wide range of applications such as smart homes, healthcare monitoring, industrial automation, and smart cities.

Author : SK ANJANEYULU BABU1 , D AISWARYA2

Title : EFFICIENT BOTNET ATTACK DETECTION IN IOT USING HYBRID MACHINE LEARNING MODEL

Volume/Issue : 2026;03(07)

Page No : 364-374

Water management is a critical challenge worldwide due to increasing population, climate change, and inefficient usage of water resources. Traditional water management systems often suffer from issues such as lack of transparency, data manipulation, poor resource allocation, and inadequate monitoring, which hinder sustainable water usage and equitable distribution. To address these challenges, this project proposes a Blockchain-Based Water Management System that leverages the decentralized, transparent, and tamperproof nature of blockchain technology to revolutionize how water resources are managed, tracked, and allocated. The proposed system uses blockchain to create a secure and immutable ledger that records every transaction related to water usage, distribution, and supply. This decentralized ledger is accessible to all stakeholders including water authorities, consumers, and service providers, ensuring transparency and trust in the data. Smart contracts are integrated within the blockchain to automate and enforce water usage policies, billing, and penalties without the need for intermediaries, thus reducing corruption and administrative overhead. Moreover, Internet of Things (IoT) devices such as smart meters and sensors are incorporated to collect real-time data on water consumption and quality, feeding accurate information into the blockchain network. By combining blockchain with IoT, the system enables efficient monitoring and management of water resources, early detection of leaks or wastage, and fair billing based on actual consumption. The traceability feature of blockchain helps in auditing water use, preventing illegal extraction, and promoting responsible consumption. Additionally, the system supports data privacy and security, protecting user information while maintaining openness of water usage data for regulatory compliance. Overall, this blockchain-based water management solution aims to enhance the sustainability, transparency, and efficiency of water resource management. It empowers stakeholders with reliable data, automates administrative processes, and promotes accountability. As water scarcity becomes an increasing concern globally, such innovative technological approaches are essential to safeguard this vital resource for future generations.

Keywords : Water is an indispensable resource essential for life, agriculture, industry, and ecosystem balance.

Author : 1 K.UDAY KIRAN #2 K.SRAVANA KAVYA

Title : BLOCKCHAIN-BASED WATER MANAGEMENT SYSTEMS

Volume/Issue : 2026;03(07)

Page No : 375-385

In today’s increasingly complex and distributed IT environments, traditional perimeter-based security models are no longer sufficient to protect against sophisticated cyber threats. Zero Trust Network Access (ZTNA) addresses these challenges by eliminating implicit trust and enforcing continuous verification of every user and device attempting to access network resources. However, conventional ZTNA implementations often depend on centralized authentication and policy management servers, which introduce vulnerabilities such as single points of failure, limited transparency, and susceptibility to tampering. This project proposes a novel blockchain-based ZTNA system that leverages the decentralized, immutable, and transparent nature of blockchain technology to enhance security, trust, and auditability within the ZTNA framework. By employing a permissioned blockchain to record authentication events, access policies, and audit logs, the system distributes trust across multiple nodes, thereby eliminating reliance on centralized authorities. Smart contracts automate the dynamic enforcement of granular access control policies, considering contextual factors like user identity, device posture, location, and time, to ensure adaptive and least-privilege access in real time. The integration of blockchain with continuous device and user verification improves resilience against attacks, reduces administrative overhead, and strengthens compliance with security standards. Additionally, the transparent and tamperproof nature of blockchain logs facilitates comprehensive auditing and forensic analysis. This innovative approach provides a scalable, secure, and trustworthy access control solution tailored for modern enterprise networks, effectively addressing the shortcomings of existing ZTNA systems and paving the way for more resilient cybersecurity architectures.

Keywords : With the rapid expansion of cloud computing, remote work, and mobile device usage, traditional network security models that rely on a strong perimeter have become increasingly inadequate.

Author : 1 SK.HIMAM BASHA, 2 N.V.ANITHA

Title : SECURE AND AUDITABLE ACCESS CONTROL VIA BLOCKCHAIN-BASED ZERO TRUST NETWORKS

Volume/Issue : 2026;03(07)

Page No : 386-396

Alzheimer’s disease (AD) is a progressive neurodegenerative disorder that significantly impairs cognitive functions and quality of life, making early diagnosis critical for effective intervention and management. Traditional diagnostic methods often rely on clinical evaluations and neuroimaging techniques, which can be expensive, timeconsuming, and not readily accessible in many settings. This study proposes a novel machine learning framework that utilizes cognitive features derived from neuropsychological assessments to facilitate the early detection of Alzheimer’s disease. By leveraging a voting-based ensemble learning approach, which combines the predictive strengths of multiple classifiers— including logistic regression, random forests, gradient boosting, and support vector machines—the model aims to improve classification accuracy, robustness, and generalizability across different patient populations. The dataset comprises various cognitive test scores representative of memory, attention, executive function, and language abilities, along with corresponding diagnostic labels categorized into normal control, mild cognitive impairment, and Alzheimer’s disease groups. Comprehensive preprocessing steps such as imputation of missing data, feature scaling, and selection are performed to enhance model performance. The ensemble model is trained and validated using stratified crossvalidation techniques to mitigate overfitting, and its predictive capability is assessed through standard metrics such as accuracy, precision, recall, F1-score, and area under the ROC curve. Results demonstrate that the voting-based ensemble outperforms individual classifiers, highlighting the advantage of aggregating diverse decision boundaries to capture the complex patterns inherent in cognitive decline. This approach not only provides a cost-effective and accessible diagnostic tool but also offers insights into the most significant cognitive indicators linked to Alzheimer’s progression, potentially aiding clinicians in early intervention strategies and personalized patient care. Overall, this study underscores the potential of machine learning ensemble methods as a powerful adjunct in the early detection and monitoring of Alzheimer’s disease, contributing to improved patient outcomes and advancing the field of neurodegenerative disease diagnostics.

Keywords : Alzheimer’s disease (AD) is the most common form of dementia, characterized by a gradual decline in cognitive functions such as memory, reasoning, language, and behavior.

Author : #1 K.UDAY KIRAN , #2 S. SUMALATHA

Title : EARLY DETECTION OF ALZHEIMER'S DISEASE USING COGNITIVE FEATURES A VOTING-BASED ENSEMBLE MACHINE LEARNING APPROACH

Volume/Issue : 2026;03(07)

Page No : 397-410

In today’s digital age, the rapid growth of online educational platforms has created an overwhelming abundance of courses across diverse domains. However, the lack of personalized guidance often leaves learners confused and struggling to choose the right courses that align with their individual goals, interests, and skill levels. To address this challenge, this project proposes the development of a Personalized E-Learning Course Recommendation System that leverages artificial intelligence and machine learning techniques to provide tailored course suggestions to users. The system collects user-specific data such as educational background, learning preferences, previously completed courses, user ratings, and feedback, and utilizes this information to generate accurate and relevant course recommendations. It employs a hybrid recommendation engine combining content-based filtering, which matches courses based on user preferences and course metadata, and collaborative filtering, which identifies patterns in user behavior and suggests courses liked by similar users. This ensures a highly customized learning experience that evolves over time with continuous feedback and usage. The platform also integrates a userfriendly interface, a smart search feature, progress tracking, and an optional admin panel for managing course content. By intelligently matching learners with suitable courses, the system not only enhances user engagement and satisfaction but also significantly improves the effectiveness of the learning process, making education more accessible, efficient, and impactful.

Keywords : In recent years, the proliferation of online learning platforms such as Coursera, edX, Udemy, and Khan Academy has revolutionized the educational landscape by providing learners with access to thousands of courses across various disciplines.

Author : # 1 K. Uday Kiran, #2 V.B.G. Sreekalpavalli

Title : PERSONALIZED E-LEARNING COURSE RECOMMENDATION SYSTEM

Volume/Issue : 2026;03(07)

Page No : 411-422

This project introduces an AI-based financial identification system designed to analyze and classify the financial status of individuals or communities using demographic and economic data. With increasing demand for data-driven solutions in finance and policy-making, the proposed system provides a reliable and scalable approach to assess financial conditions across various population segments.The system utilizes key demographic features such as age, gender, education level, occupation, marital status, and geographical location, along with economic indicators like income level, employment status, housing type, and access to banking services. By processing this data using Machine Learning algorithms such as Random Forest, Logistic Regression, and KMeans Clustering, the model can predict financial standing and group individuals into low, medium, or high financial categories.This classification helps governments, financial institutions, and NGOs to target specific groups for financial aid, credit services, or development programs. For example, banks can assess creditworthiness for microloans, while government bodies can identify underprivileged communities for subsidy distribution or social welfare schemes. The project also incorporates data visualization tools to present economic patterns and demographic influences in a clear, insightful manner. Regional heatmaps, statistical graphs, and predictive dashboards help stakeholders make informed decisions backed by real data.Overall, this project demonstrates how Artificial Intelligence can enhance financial inclusion by leveraging publicly available or surveybased data. It promotes transparent, ethical, and intelligent economic planning, ensuring that financial services and benefits reach those who need them most.

Keywords : In today’s data-driven world, understanding the financial behavior and conditions of individuals or communities has become crucial for inclusive economic development.

Author : M.RATNA KUMARI 1 , M.NAGA SUNANDA 2

Title : AI BASED FINANCIAL IDENTIFICATION BASED ON DEMOGRAPHY & ECONOMIC FORMING

Volume/Issue : 2026;03(07)

Page No : 423-434

Signature verification is a crucial biometric technique widely used for personal authentication in banking, legal documentation, and financial transactions. However, the rise of skilled forgeries poses significant challenges to traditional verification methods. This paper proposes a hybrid signature forgery verification system that integrates Convolutional Neural Networks (CNN) with Histogram of Oriented Gradients (HOG) feature extraction. The extracted features are classified using Decision Tree and Support Vector Machine (SVM) algorithms to enhance accuracy and robustness. The proposed system leverages CNN for deep feature learning and HOG for capturing edge-based structural details, providing a comprehensive representation of signatures. Experimental results demonstrate that the hybrid approach significantly improves classification accuracy compared to conventional methods.

Keywords : Biometric authentication has become increasingly important in modern security systems. Among various biometric traits, handwritten signatures remain one of the most socially and legally accepted forms of identity verification.

Author : P.BHARATHI 1 K.KOTESWARARAO 2

Title : SIGNATURE FORGERY VERIFICATION USING CNN AND HOGBASED FEATURES ALONG WITH DECISION TREE AND SVM

Volume/Issue : 2026;03(07)

Page No : 435-441

The emergence of deep learning-based speech synthesis technologies has enabled the generation of highly realistic artificial audio, commonly known as deep fake audio. These synthetic audio signals can imitate human voices with remarkable accuracy, posing significant threats in areas such as identity theft, misinformation, financial fraud, and digital forensics. Traditional detection methods struggle to identify subtle artifacts present in deep fake audio due to the increasing sophistication of generative models like WaveNet, Tacotron, and GAN-based architectures. This paper proposes an advanced deep learning-based framework for detecting deep fake audio using hybrid neural network architectures. The system integrates Convolutional Neural Networks (CNNs) for spatial feature extraction and Long Short-Term Memory (LSTM) networks for temporal sequence modeling. Audio signals are transformed into time-frequency representations such as spectrograms and Mel-Frequency Cepstral Coefficients (MFCCs) to capture discriminative patterns. The model is trained and evaluated on benchmark datasets like ASVspoof, achieving high detection accuracy and robustness across diverse spoofing attacks. Experimental results demonstrate that the proposed approach significantly outperforms traditional machine learning techniques. This research contributes to enhancing audio authentication systems and mitigating risks associated with synthetic media.

Keywords : Deep Fake Audio, Speech Synthesis, CNN, LSTM, MFCC, Audio Forensics, Voice Cloning, ASVspoof

Author : B.KAVITHA 1 B.DHARMA RAJU 2

Title : DEEP FAKE AUDIO DETECTION USING DEEP LEARNING

Volume/Issue : 2026;03(07)

Page No : 442-450

Demand forecasting is a fundamental component in supply chain management, enabling organizations to predict future product demand and optimize inventory, production, and logistics. Traditional statistical approaches often struggle with nonlinear relationships, seasonality, and high-dimensional data. This paper proposes an advanced forecasting framework integrating machine learning and deep learning models—Random Forest (RF), Gradient Boosting (GB), and Long Short-Term Memory (LSTM). The study emphasizes handling temporal dependencies, feature interactions, and uncertainty in demand patterns. A comparative analysis is conducted using real-world-like datasets, evaluating models based on MAE, RMSE, and MAPE. Experimental findings indicate that LSTM captures temporal dependencies effectively, while ensemble methods ensure robustness and interpretability. The hybrid modeling approach significantly improves forecasting accuracy and scalability in dynamic environments.

Keywords : Demand forecasting is essential for decision-making in industries such as retail, healthcare, e-commerce, and manufacturing.

Author : S.SAVITHRI 1 SK.SHABAZ 2

Title : DEMAND FORECASTING USING RANDOM FOREST, GRADIENT BOOSTING, AND LSTM ALGORITHMS

Volume/Issue : 2026;03(07)

Page No : 451-458

With the rapid growth of digital communication, cloud computing, and the Internet of Things (IoT), protecting sensitive information has become increasingly important. Conventional cryptographic algorithms such as AES, RSA, and ECC provide strong security but face challenges related to computational complexity, key management, and adaptability against evolving cyber threats. Recent advances in Artificial Intelligence (AI), particularly Neural Networks (NNs), have opened new opportunities for developing intelligent cryptographic systems capable of learning complex data transformations. This research proposes a Neural Network-Based Encryption and Decryption Algorithm that utilizes deep learning techniques to generate secure encryption mappings while maintaining accurate decryption capabilities. The proposed model employs a multilayer neural network trained on plaintext-ciphertext pairs to learn nonlinear encryption functions. The system incorporates dynamic key generation, neural weight optimization, and secure decoding mechanisms to improve confidentiality and resistance against statistical, brute-force, and differential attacks. The proposed methodology includes data preprocessing, neural network training, encryption using learned weights, and decryption through inverse neural mapping. Performance is evaluated using encryption time, decryption accuracy, entropy, avalanche effect, key sensitivity, and resistance against cryptographic attacks. Experimental results demonstrate that the neural network-based approach provides enhanced security, adaptability, and scalability while maintaining competitive computational efficiency compared to traditional encryption techniques.

Keywords : Neural Networks, Encryption, Decryption, Artificial Intelligence, Deep Learning, Cryptography, Cyber Security.

Author : M.V.N.S.L SUKANYA 1 SK.SHABAZ2

Title : ENCRYPTION AND DECRYPTION ALGORITHM BASED ON NEURAL NETWORK

Volume/Issue : 2026;03(07)

Page No : 459-467

The exponential growth of online transactions has led to a significant rise in credit card fraud, causing substantial financial losses to financial institutions and customers. Detecting fraudulent transactions is a challenging task due to the high volume of transaction data and the evolving nature of fraud patterns. This paper presents a machine learning-based approach for credit card fraud detection using the Random Forest algorithm. The proposed system analyzes historical transaction data and classifies transactions as genuine or fraudulent. Various preprocessing techniques such as data cleaning, normalization, and feature extraction are applied to enhance model performance. The system is evaluated using performance metrics such as accuracy, precision, recall, and F1-score. Experimental results demonstrate that the Random Forest algorithm provides superior performance compared to traditional methods, achieving high accuracy and robustness in fraud detection.

Keywords : The advancement of digital payment systems has transformed financial transactions, making them faster and more convenient.

Author : Y.VINAY KUMAR 1 K.KOTESWARA RAO 2

Title : CREDIT CARD FRAUD DETECTION USING MACHINE LEARNING

Volume/Issue : 2026;03(07)

Page No : 468-475

The rapid spread of infectious diseases poses a significant threat to global public health, necessitating advanced predictive systems for early detection and intervention. This paper presents an AI-driven predictive analytics framework that leverages machine learning techniques—Random Forest, Decision Tree, and Artificial Neural Networks—to forecast disease outbreaks. The system integrates historical epidemiological data, environmental parameters, and demographic information to generate accurate predictions. Comparative analysis demonstrates that ensemble and deep learning approaches significantly outperform traditional statistical models in terms of accuracy, precision, and recall. The proposed system aims to assist healthcare authorities in proactive decision-making and resource allocation, thereby reducing the impact of epidemics.

Keywords : Disease outbreaks such as influenza, dengue, COVID-19, and malaria continue to challenge healthcare systems worldwide.

Author : M.MADHUSUDHAN REDDY 1 SK.SHABAZ 2

Title : AI-DRIVEN PREDICTIVE ANALYTICS FOR DISEASE OUTBREAKS USING RANDOM FOREST, DECISION TREE AND NEURAL NETWORK ALGORITHMS

Volume/Issue : 2026;03(07)

Page No : 476-482