Journal of Science Engineering Technology and Management Science

This research presents the development of an Internet of Things (IoT)-integrated automation framework designed to optimize operational efficiency and animal welfare in dairy cattle farms. The proposed system utilizes the ESP32 microcontroller as the primary processing and communication gateway to synchronize a network of sensors and actuators. Key hardware components include a Real-Time Clock (RTC) for precise task scheduling, DHT22 sensors for microclimatic monitoring, and an I2C LCD for localized status reporting. To mitigate the inconsistencies of manual labor, the system automates critical livestock care through motor-driven feed trays and controlled irrigation via water pumps. Furthermore, environmental stability is maintained through automated foggers and DC fans that activate based on real-time atmospheric thresholds. Leveraging the ESP32’s dual-core architecture and integrated Wi-Fi, the system enables seamless data transmission to a web-based dashboard, allowing farmers to remotely monitor livestock conditions and configure management parameters. Results indicate that this scalable, cost-effective solution significantly reduces manual intervention, minimizes resource waste, and ensures a stress-free environment for cattle. This intelligent farming model provides a viable technological path for small-to-medium-scale dairy enterprises to transition toward precision agriculture.

Keywords : Precision Livestock Farming (PLF), ESP32 Microcontroller, Internet of Things (IoT), Smart Dairy Automation, Climate Control, Sustainable Agriculture

Author : B. Suresh Kumar, B. Bharath Kumar Reddy, K. Yaswanth Kumar Reddy, Dabbugodala Mahesh, Kampa V Balu Mahendra

Title : Design and Implementation of an IoT-Based Autonomous Environment and Nutrition Management System for Precision Dairy Farming

Volume/Issue : 2026;03(04)

Page No : 1-7

Urban traffic congestion remains a primary impediment to emergency medical services, where critical delays in ambulance transit times directly correlate to increased mortality rates. Research indicates that a one-minute reduction in response time can improve patient survival outcomes by 7% to 10%. This paper proposes a decentralized Emergency Vehicle Preemption (EVP) system designed to establish an instantaneous “Smart Green Corridor” using a heterogeneous microcontroller framework. The system architecture utilizes an ESP32 microcontroller at the transmitter (TX) node, integrated within the emergency vehicle, and an Arduino Uno at the receiver (RX) node to manage the Traffic Signal Control (TSC) logic. Wireless communication is established via the Zigbee (IEEE 802.15.4) protocol, providing a low-power, high-reliability data link that operates effectively in high-interference urban environments. The TX unit, powered by the dual-core processing of the ESP32, transmits road-specific priority signals which are intercepted by the RX unit’s Arduino Uno. Upon signal reception, the TSC executes a preemptive interrupt algorithm that overrides the standard four-phase traffic cycle, immediately transitioning the requested lane to a "Green" state while holding conflicting manoeuvres at "Red." Experimental validation of the prototype demonstrates a significant reduction in the Average Waiting Time (AWT) for ambulances, achieving near-zero delay at signalled intersections. By utilizing a costeffective combination of ESP32 and Arduino Uno, this research contributes a scalable, low-latency solution for intelligent transportation systems that operates independently of centralized cloud processing or line-of-sight dependent infrared sensors

Keywords : Emergency Vehicle Preemption (EVP); Zigbee Communication; Smart Traffic Control; Green Corridor; Intelligent Transportation Systems (ITS); Arduino Microcontroller

Author : M. Suhasini, Kommi Jyothi, Koduru Chandra Lekha, Amari Sindhu, Gadde Suhitha

Title : Design and Implementation of an Intelligent Green Corridor System for Emergency Vehicle Preemption

Volume/Issue : 2026;03(04)

Page No : 8-15

Traditional information dissemination in educational institutions relies heavily on manual, paper-based notice boards, which are prone to delays, high maintenance costs, and physical constraints. This paper proposes a centralized, real-time IoT-based Campus Display Board (ICDB) system powered by the high-performance Raspberry Pi 5. The proposed architecture integrates a web-based administrative server with distributed edge nodes via a secure IoT communication layer. Utilizing a Flask-driven backend and a dynamic HTML5/CSS3 frontend, authorized administrators can remotely broadcast multimedia content—including high-definition video, static images, and emergency alerts—from any location. The Raspberry Pi 5 serves as the core processing unit, leveraging its quad-core capabilities and improved networking stack to ensure lag-free rendering and continuous synchronization with the server via a polling-based manifest protocol. Experimental results indicate that the system significantly reduces the latency between announcement creation and public display compared to conventional methods. Furthermore, the modular design promotes sustainability by eliminating paper waste and offers a scalable infrastructure for future smart-campus integrations, such as AI-driven content scheduling and automated cloud synchronization. This research demonstrates a cost-effective, energyefficient, and user-friendly solution for modernizing institutional communication and enhancing administrative transparency in a digitally driven academic environment.

Keywords : Internet of Things (IoT), Raspberry Pi 5, Digital Signage, Flask Framework, Smart Campus, Real-time Communication.

Author : G. Tejaswi, Mopuru Rajesh, Veeramreddy Pratap Reddy, Balli Sarath Chandra, Nanda Bhaskar Rao

Title : IoT-Enabled Campus Digital Signage Framework using Flask-Based Edge Computing

Volume/Issue : 2026;03(04)

Page No : 16-24

In advanced IC manufacturing, yield losses contribute to nearly 20–30% of total fabrication cost, with variations in die size and transistor scaling responsible for more than 60% of yield degradation, while modern fabs generate terabytes of process data per production cycle, making efficient prediction essential. Existing manual and traditional yield prediction approaches rely on low-level statistical analysis and expert-driven rule formulation, resulting in high time consumption, poor scalability, limited ability to model non-linear interactions, and reduced reliability at advanced technology nodes. To address these limitations, this work proposes a Quantum Neural Network–based yield prediction framework for accurate estimation of die size and transistor scaling, where the Integrated Chip (IC) manufacturing dataset is first subjected to comprehensive data preprocessing including normalization, noise reduction, and missing-value handling, followed by Exploratory Data Analysis (EDA) to identify key statistical trends and process correlations. For performance comparison, existing models such as the Restricted Boltzmann Machine (RBM) Regressor, Gradient Boosting Regressor (GBR), and Extreme Gradient Boosting (XGB) Regressor are implemented to evaluate classical learning capabilities. The proposed system integrates a Variational Quantum Neural Network (VQNN) for advanced quantum feature extraction, leveraging parameterized quantum circuits to capture highdimensional, non-linear, and entanglement-based relationships among manufacturing parameters, which are difficult to model using classical methods. These quantum-enhanced features are then processed using an Ensemble Oblique Trees (EOT) regressor to achieve robust and highly accurate yield prediction, significantly improving prediction accuracy, adaptability, and computational efficiency, thereby enabling early-stage yield optimization and cost reduction in next-generation IC manufacturing

Keywords : Quantum Neural Network, IC Manufacturing Yield Prediction, Variational Quantum Neural Network, Ensemble Oblique Trees, Transistor Scaling, Die Size Optimization

Author : G. Kiran Kumar, Nandimandalam Sivarama Raju, Mohammad Nawaz, Nayudu Pradeep

Title : Variational Quantum Circuit Regressors for Joint Optimization of Transistor Scaling and Die Footprint in Advanced IC Manufacturing

Volume/Issue : 2026;03(04)

Page No : 25-36

Defect classification in industrial components is critical to ensuring product quality, operational safety, and cost efficiency, as manufacturing industries face increasing defect rates due to highspeed production and complex processes. Studies indicate that a significant percentage of industrial failures originate from undetected surface and structural defects, leading to rework, downtime, and financial loss. This research is motivated by the need for accurate and automated defect detection in machinery parts, painted surfaces, and welded joints, including subtypes such as cracks, corrosion, paint blisters, scratches, porosity, lack of fusion, and weld spatter. The expected outcome is a robust classification system capable of reliably identifying defect categories and subcategories across these domains. Traditional defect inspection relies heavily on manual visual inspection, which is time-consuming, subjective, and prone to human error. Such manual systems struggle with consistency, scalability, and real-time deployment in modern industrial environments. In this work, RGB images of industrial components are utilized, followed by image preprocessing techniques including resizing and normalization to enhance feature consistency and model performance. Existing machine learning approaches such as K-Nearest Neighbours (KNN) and Decision Tree Classifier (DTC) are reviewed as baseline models for defect classification. The proposed approach employs Convolutional Neural Network (CNN)-based feature extraction combined with Logistic Regression (LR) for efficient and accurate classification. The system outputs precise defect classification results for machinery, paint, and welding components, including their respective defect subtypes, demonstrating improved accuracy and reliability over traditional methods.

Keywords : Industrial Defect Classification, Automated Defect Detection, Machine Learning, Quality Inspection, Predictive Maintenance

Author : P. C. N. Lalithya, Sreemanthula V Sai Chethana, Madireddy Dharani, Panthangi Manasa

Title : Deep Feature Fusion for Hierarchical Defect Classification in Industrial Inspection Systems

Volume/Issue : 2026;03(04)

Page No : 37-46

In modern era, construction of high-rise buildings is rapidly increasing throughout the world. Due to decrease of available free land and due to wide spread urban area, the architects and the engineers have started developing cities vertically. Recently, the dia grid structural system has been widely used for tall buildings due to structural efficiency and aesthetic potential provided by triangulation of the system. Compared to the conventional frame buildings having exterior vertical column, dia grid structure resists the lateral loads more efficiently due to presence of inclined columns. In dia grid system the lateral loads are resisted by the axial action of the inclined columns that are placed at the exterior periphery of the buildings. Seismic isolation and energy dissipating systems present an effective way to common seismic design for improving the seismic performance of structures. These techniques reduce the seismic forces by changing the stiffness and damping in the structures, whereas conventional seismic design is required for an additional strength and ductility to resist seismic forces. In the present study a 21 storied dia grid building is analyzed with in different seismic zones by using ETABS software . The results like story drift, story shear, story bending, time period, model stiffness are compared for different seismic zones as response spectrum analysis.

Keywords : diagrid, ETABS, Seismic isolation, story drift, story shear, story bending, time period, model stiffness.

Author : P SUBHASRI1 , KONDEPOGU ABHINESH2 , SHAIK ARSHAD3 , POLUDASU DEEPAK KUMAR4

Title : SEISMIC LOAD ANALYSIS AND WIND LOAD ANALYSIS OF 25 STOREY BUILDING COMPARATIVE ANALYSIS OF G+20 DIA GRID BUILDING IN DIFFERENT SESIMIC ZONES BY USING ETABS

Volume/Issue : 2026;03(04)

Page No : 47-54

Recent studies report that unplanned machine failures account for nearly 20–30% of total production downtime in smart manufacturing environments. With Industry 4.0 enabling continuous sensor-based monitoring, industries now generate massive volumes of operational data, yet effective fault analysis and decision-making remain a major challenge. Conventional manual fault analysis systems suffer from critical limitations, including heavy dependence on human expertise and periodic inspections, which often result in delayed fault detection and inconsistent decision-making. In this study, a comprehensive data set is utilized containing parameters such as timestamp, machine id, temperature, vibration level, power consumption, pressure, material flow rate, cycle time, error rate, downtime, maintenance flag, efficiency score, and production status. The data undergoes systematic preprocessing, including noise handling, normalization, missing-value treatment, and feature alignment, followed by Exploratory Data Analysis (EDA) to understand operational patterns, fault correlations, and feature importance. Existing machine learning models such as AdaBoost-CART, XGBoost-CART, and Passive-Aggressive (PA)- CART are implemented as baseline methods. To overcome the limitations of fixed-feature learning and manual feature engineering, a proposed Neural Architecture Search (NAS)-based feature extraction framework integrated with a Greedy Rule Forest (GRF)-CART model is introduced. The NAS component automatically learns optimal feature representations from complex sensor interactions, while the GRF-CART enhances interpretability and decision robustness. The proposed framework performs classification tasks to predict downtime occurrence, maintenance requirement (maintenance flag), and production status, along with a regression task to accurately estimate the efficiency score. Experimental results demonstrate that the proposed NAS–GRF–CART approach significantly improves fault prediction accuracy, reduces false maintenance alerts, and provides reliable efficiency assessment, making it well-suited for intelligent, data-driven maintenance strategies in Industry 4.0 environments

Keywords : Industry 4.0, Neural Architecture Search (NAS), Greedy Rule Forest (GRF)-CART, Predictive Maintenance, Feature Representation Learning.

Author : K. Sravan Kumar, Naguru Navya, Surayapalem V Naga Dharmika, Perumalla Vyshnavi

Title : Data-Driven Fault Intelligence and System Optimization in Modern Industrial Environments

Volume/Issue : 2026;03(04)

Page No : 55-68

This research presents the design and implementation of an intelligent, multi-purpose robotic system developed to enhance public health and workplace safety through automated sanitization and hazard detection. Built on the ESP32 microcontroller architecture, the robot integrates ultrasonic-based obstacle avoidance with specialized chemical sensing for fire and gas leak detection. Unlike static sanitization units, this mobile platform utilizes a high-pressure pumping system for disinfectant dispersal, controlled via a real-time Internet of Things (IoT) interface. The system employs a Wi-Fienabled communication protocol to transmit environmental data including obstacle proximity, flammable gas concentrations, and thermal anomalies to a centralized PHP-based cloud server. Experimental results demonstrate a significant reduction in human exposure to hazardous environments, as the robot can be remotely maneuverer via Serial-over-Wi-Fi commands while providing instantaneous feedback through a Liquid Crystal Display (LCD) and a remote web dashboard. The study concludes that the integration of low-cost, high-efficiency sensors with IoT logging provides a scalable solution for maintaining hygiene standards in hospitals, laboratories, and manufacturing hubs, effectively bridging the gap between manual labor and fully autonomous industrial safety protocols.

Keywords : Internet of Things, ESP32 Microcontroller, Autonomous Sanitization, Hazard Detection, Industrial Automation.

Author : U. Penchalaiah, Shaik Saleha Nazini, Pralayakaveri Swathi, Singala Smana Sree

Title : IoT-Enabled Autonomous Robot for Real-Time Pathogen Sanitization and Hazard Mitigation in Industrial Environments

Volume/Issue : 2026;03(04)

Page No : 69-78

Digital financial inclusion has increasingly become a cornerstone of inclusive economic growth, particularly in developing economies like India where regional disparities in financial access remain pronounced. The rapid expansion of digital financial services such as mobile banking, online payments, and digital wallets has transformed the way households’ access and utilize financial resources, thereby influencing their overall financial well-being. This study examines the impact of digital financial inclusion on household financial well-being, with a specific focus on comparing urban and rural households. It investigates how access to digital financial services, frequency of usage, and levels of financial literacy contribute to improved financial stability and security. The study is based on primary data collected from 140 households, comprising 70 urban and 70 rural respondents, through a structured questionnaire. Statistical techniques, including descriptive analysis, correlation, and multiple regression, were applied using SPSS software to analyze the data. The findings reveal that digital financial inclusion has a significant positive effect on household financial well-being. However, the magnitude of this impact is considerably higher among urban households, primarily due to better digital infrastructure, higher awareness, and greater financial literacy. Rural households, in cont rast, face constraints related to accessibility and digital skills, limiting the effective utilization of financial services. The study concludes that bridging the urban–rural digital divide through targeted policy interventions, improved infrastructure, and financial education is essential for achieving equitable financial inclusion and sustainable economic development.

Keywords : Digital Financial Inclusion; Household Financial Well-Being; Urban–Rural Divide; Financial Literacy; Digital Payments; Financial Access; India

Author : M. Ramesh Naik, Kavali Rudransh, K. Saraschandra

Title : DIGITAL FINANCIAL INCLUSION AND HOUSEHOLD FINANCIAL WELL-BEING: A COMPARATIVE STUDY OF URBAN AND RURAL INDIA

Volume/Issue : 2026;03(04)

Page No : 79-87

Human Resource practices and functions have a far reaching impact on the employees morale and performance, which in turn, affects the overall performance of the organization. This is why they are claimed to be closely related to a business’s ‘balance scorecard’ through “productivity, people, and processes” (Ulrich,). Given its criticality, a regular assessment of the HR function, like that of finance function, becomes essential for sustaining organizational health and growth. The need for such assessment is even greater in today’s dynamic and, at times, turbulent, environment, where human resource management needs continuous up-gradation and re-alignment. Moreover, with increased importance of the human contribution to organizations’ competitive advantage, especially in the knowledge driven economy, the human resource function itself is under transformation. It is gradually moving from the role of a service provider to that of a strategic business partner. In order to perform this emerging role effectively, the HR function has to continually assess: Whether it is adding tangible value to the organization through its strategies, policies, processes and practices; Whether it is doing so at a competitive cost; and Whether it is doing so in a manner that is satisfying to its people, acceptable to the society and the law, and, from a long term perspective, sustainable.

Keywords :

Author : SHAIK SHAHEENA, EPHRON. K. PAUL

Title : A STUDY ON HR POLICIES AND PRACTICIES

Volume/Issue : 2026;03(04)

Page No : 88-98

Total Quality Management (TQM) is an approach that organizations use to improve their internal processes and increase customer satisfaction. When it is properly implemented, this style of management can lead to decreased costs related to corrective or preventative maintenance, better overall performance, and an increased number of happy and loyal customers. However, TQM is not something that happens overnight. While there are a number of software solutions that will help organizations quickly start to implement a quality management system, there are some underlying philosophies that the company must integrate throughout every department of the company and at every level of management. Whatever other resources you use, you should adopt these seven important principles of Total Quality Management as a foundation for all your activities. TQM is a way of life for a company. It has to be introduced and led by top management. This is a key point. Attempts to implement TQM often fail because top management doesn't lead and get committed - instead it delegates and pays lip service. Commitment and personal involvement is required from top management in creating and deploying clear quality values and goals consistent with the objectives of the company, and in creating and deploying well defined systems, methods and performance measures for achieving those goals. These systems and methods guide all quality activities and encourage participation by all employees. The development and use of performance indicators is linked, directly or indirectly, to customer requirements and satisfaction, and to management and employee remuneration

Keywords :

Author : SADDAPALLI SIRAJ, P. ANIL SAI

Title : A STUDY ON TOTAL QUALITY MANAGEMENT IN MODERN ORGANIZATIONS

Volume/Issue : 2026;03(04)

Page No : 99-106

Women empowerment and gender equality have become topics of utmost importance in the recent times, because gender inequality and its socio-economic and cultural dimensions are all pervasive in the third world as well as in the developed world. However, in the third world, the problem of gender inequality is more acutely associated with economic disempowerment of women. And therefore, of recent, several initiatives are being taken up in the third world countries for the economic empowerment of women so as to reduce the gender inequality. Among these initiatives, the Self-Help Group (SHG) movement, which is getting wide spread all over the third world, has become the prominent one. The research interest of the present study was mainly to examine whether SHGs actually contribute to empower women economically as well as socially. The study has also examined another problem that whether there is significant variation in the performance of government-run and NGO- run SHGs. The study depends mainly on primary data, collected through sample survey of households of SHG women. Apart from the household survey, a few interviews with the respondents and officers in charge of different SHGs were also conducted.

Keywords :

Author : PULAGUTTAPALLI SAMATHA, P. ANIL SAI

Title : A STUDY ON DIGITAL MARKETING

Volume/Issue : 2026;03(04)

Page No : 107-119

Women empowerment and gender equality have become topics of utmost importance in the recent times, because gender inequality and its socio-economic and cultural dimensions are all pervasive in the third world as well as in the developed world. However, in the third world, the problem of gender inequality is more acutely associated with economic disempowerment of women. And therefore, of recent, several initiatives are being taken up in the third world countries for the economic empowerment of women so as to reduce the gender inequality. Among these initiatives, the Self-Help Group (SHG) movement, which is getting wide spread all over the third world, has become the prominent one. The research interest of the present study was mainly to examine whether SHGs actually contribute to empower women economically as well as socially. The study has also examined another problem that whether there is significant variation in the performance of government-run and NGO- run SHGs. The study depends mainly on primary data, collected through sample survey of households of SHG women. Apart from the household survey, a few interviews with the respondents and officers in charge of different SHGs were also conducted.

Keywords :

Author : PARADESI KAVITHA, Y. MAMATHA

Title : A STUDY ON WOMEN IN CORPORATE WORLD

Volume/Issue : 2026;03(04)

Page No : 120-131

Performance appraisal refers to all formal procedures used in working conditions to evaluate personalities and contributions and potential of group members The literature review section examines the importance of search studies, company data or industry reports that serve as a foundation for the setup of study. The research dimension of the related literature and the relevant information begins from an explanatory perspective, approaching towards specific studies which do related to the judge the limitations and informational gaps in data from the secondary sources. This analysis may reveal conclusions from past studies to realize the reliability of the secondary sources and their credibility. This in turn enables one to rely on a comprehensive review for the study. Most appraisal methods used throughout the world today are based, to some extent at least upon the following techniques: Graphic rating scales; behaviorally anchored rating scales (BARS), behavioral observation scales (BOS); mixed standard rating scales; and management by objectives (MBO). Most commentators agree that goal-based appraisal systems, in which an employee‟ work performance is measured against specific goals, are the most satisfactory (Dorfman et al., 1986; Locke and Latham, 1984; Lastly, in the past few years, there has been growing interest in the practice community for what has been termed “non-traditional” appraisal systems (e.g., Coens and Jenkins, 2000; Lawler, 2000). These systems are less structured than the more traditional systems, with less emphasis on ratings or rankings, and more emphasis on developmental meetings between supervisors and employees as needed. The study of Bladen (2001) indicated that these approaches have been growing in popularity, but most firms that have moved in this direction have developed hybrid models, which still retain some aspects of the traditional systems

Keywords :

Author : NASANAKOTA ROJA, Y. MAMATHA

Title : A STUDY ON ROLE OF PERFORMANCE APPRAISAL SYSTEM AND ITS IMPACT ON EMPLOYEES MOTIVATION

Volume/Issue : 2026;03(04)

Page No : 132-142

Natural disasters such as floods, earthquakes, cyclones, and extreme weather conditions pose significant threats to human life, infrastructure, and the environment. Early detection and timely response are crucial to minimize the impact of such disasters. This project presents a Real-Time Emergency Response Location Tracking System for Climate Disasters using Artificial Intelligence, designed to predict disaster occurrences and facilitate efficient communication between users and administrators. The proposed system utilizes environmental parameters such as temperature, humidity, wind speed, precipitation, seismic activity, and atmospheric pressure to analyze potential disaster situations. Machine learning and deep learning models, including Random Forest, Gradient Boosting, Long Short-Term Memory (LSTM), and Convolutional Neural Networks (CNN), are implemented to improve prediction accuracy. Among these, the CNN model demonstrates higher performance in identifying disaster patterns. The system is developed using a web-based architecture where users can input environmental data and receive real-time disaster predictions. The backend is implemented using the Flask framework, while SQLite is used for data storage. An administrative module allows dataset uploading, model training, monitoring of user activity, and broadcasting emergency alerts to users. Additionally, the system maintains a history of predictions and provides timely notifications to enhance disaster preparedness. By integrating artificial intelligence with real-time data processing, the proposed system aims to support early warning mechanisms and improve disaster management efficiency

Keywords : Artificial Intelligence, Deep learning, disaster detection,CNN, LSTM

Author : DR.DJ SAMATHA NAIDU, Y.VIJAYA BHASKAR REDDY

Title : REAL TIME EMERGENCY RESPONSE LOCATION TRACKING APP FOR CLIMATE DISASTERS USING ARTIFICIAL INTELLIGENCE

Volume/Issue : 2026;03(04)

Page No : 143-149

This work presents the modelling and simulation of an enhanced renewable energy–based microgrid incorporating an Artificial Neural Network (ANN)-based control strategy for intelligent power management. The proposed system extends a conventional off-grid microgrid comprising photovoltaic and wind energy sources supported by a diesel generator by integrating a utility grid as an emergency backup source. Unlike traditional grid-connected systems, the grid is utilised only under critical operating conditions when renewable generation and diesel support are insufficient to meet load demand, thereby preserving the autonomous nature of the microgrid while improving reliability. The ANN-based controller continuously monitors the real-time power contribution from renewable sources and dynamically determines the required diesel generator output to maintain power balance. This approach ensures accurate load matching, reduced fuel consumption, and improved dynamic response under fluctuating generation conditions. Furthermore, the system’s scalability is evaluated by increasing the load capacity from 15 MW to 20 MW at unity power factor. Simulation results demonstrate that the coordinated operation of renewable sources, ANNcontrolled diesel generation, and grid backup successfully maintains stable and reliable power supply under varying operating scenarios. The proposed system significantly enhances the resilience, efficiency, and scalability of modern microgrids.

Keywords : Microgrid, Artificial Neural Network, Renewable Energy, Diesel Generator Control, Grid Backup, Power Management, MATLAB Simulation

Author : MS. MYLA SUSMITHA, SK MUJAHIRA, K RAVINDRA, V BHARATH NAIK, AALA NAGA RAJU

Title : MODELING AND SIMULATION OF ANN-BASED CONTROL OF RENEWABLE ENERGY MICROGRIDS

Volume/Issue : 2026;03(04)

Page No : 150-162

The cost generated per unit in a thermal power station is dependent on fixed cost and variable cost. The duty of an electrical engineer is to generate the power without outage of a power and at the same time the cost of power generated per unit is as low as possible. An engineer can able to reduce the cost of generated power only when the engineer knows on what factors the cost of a generated power depends. Hence the engineer must know on what factors the fixed cost and variable cost may depend. The Central Electricity Regulatory Commission (CERC) has the power of deciding the tariff or electricity generated by various power stations [1]. Tariff is calculated on the basis of fixed cost and variable cost. The power plants have fixed and variable costs. The fixed cost dependent on return on equity, interest on capital loan, depreciation, interest on working capital, operation& maintenance cost, cost of secondary oil. The variable cost dependent on primary fuel costs, secondary fuel oil consumption and auxiliary energy consumption In the Availability Tariff mechanism, the fixed and variable cost components are treated separately.. Cost index is a useful parameter to monitor and compare cost of energy for specific products manufactured by the industry. In the event of an increase or decrease (due to perhaps a conservation measure) in cost index, the particular source can be investigated immediately. In this paper, a case study of three Power Stations namely Simhapuri Thermal Power Station, Nellore, Andhra Pradesh and Koradi thermal power station, Koradi, Nagpur and Sri Damodaram Sanjeevaiah Thermal Power Station, Muthukur, Nellore, Andhra Pradesh has been considered and Tariff calculations, Cost Index of thermal power plants have been implemented with MATLAB Environment and the effectiveness of the work will be verified and compared with real time analysis. The generated program in MATLAB can be applicable for any capacity of Thermal power station and any number of power stations.

Keywords : Plant load factor, fixed cost and variable cost, Generation Cost, Cost Index, Electricity Act, Electricity tariff, MATLAB

Author : Dr. PADAVALA VENKATA NARENDRA KUMAR, PYLA KAVYA KALYANI, DARAM VIJAYA KUMAR, PATNALA PRASAD

Title : REAL-TIME COST ESTIMATION OF THERMAL POWER STATIONS USING MATLAB

Volume/Issue : 2026;03(04)

Page No : 163-170

The rapid advancement of healthcare technologies and the increasing availability of patient data have created new opportunities for predictive analytics in medical diagnosis. Health risk prediction using Machine Learning (ML) has emerged as a powerful approach to identify potential diseases at an early stage, thereby improving patient outcomes and reducing healthcare costs. This paper presents a Health Risk Prediction System that utilizes machine learning algorithms to analyze patient health parameters and predict the likelihood of diseases such as heart disease, diabetes, and hypertension. Traditional healthcare systems rely heavily on manual diagnosis, which can be time-consuming, error-prone, and often delayed. In contrast, the proposed system automates the prediction process by leveraging supervised learning techniques and data-driven decisionmaking. The system collects patient data including age, blood pressure, blood sugar levels, cholesterol, heart rate, and Body Mass Index (BMI). This data is preprocessed and transformed into a structured format suitable for machine learning models. Various algorithms such as Logistic Regression, Decision Trees, and Support Vector Machines are applied to classify patients into risk categories such as low risk and high risk. The system is implemented using Python programming language with a Flask-based web interface and SQLite database for efficient data storage and retrieval. Experimental results demonstrate that the proposed system achieves high accuracy and reliability in predicting health risks. The system not only reduces the burden on healthcare professionals but also enables early disease detection and preventive care. Furthermore, the integration of machine learning with healthcare systems enhances decision-making capabilities and supports continuous monitoring of patient health. The proposed model is scalable and can be extended to incorporate additional medical parameters and advanced deep learning techniques. Overall, this research contributes to the development of intelligent healthcare systems that improve diagnosis, reduce human error, and promote proactive health management.

Keywords :

Author : 1Mrs.V.Murali Krishna, 2Potla Bindu, 3Mandalapu Srividya, 4Ch Nithin, 5Jasti Vishnu Vardhan

Title : HEALTH RISK PREDICTION SYSTEM USING MACHINE LEARNING

Volume/Issue : 2026;03(04)

Page No : 171-178

The Job Portal System is a web-based application designed to bridge the gap between job seekers and employers by providing a centralized digital platform for recruitment and job searching. In traditional job search methods, candidates rely on newspapers, consultancy services, or personal references, which are inefficient, time-consuming, and lack real-time updates. Similarly, employers face challenges in managing large volumes of applications manually, leading to delays and potential errors in candidate selection. To overcome these limitations, the proposed system automates the recruitment process using modern web technologies and database management systems. The system enables job seekers to register, create profiles, upload resumes, search for job opportunities, and apply for positions online. Employers can register, post job vacancies, review applications, and shortlist candidates efficiently. The system also includes an admin module that manages users, monitors activities, and generates reports for analysis. The application is developed using HTML, CSS, and JavaScript for frontend design, Python Flask for backend processing, and SQLite database for data storage. The system ensures secure data handling, fast response time, and a user-friendly interface. Experimental results demonstrate that the system improves efficiency, reduces manual workload, and enhances the recruitment experience for both job seekers and employers. The Job Portal System is scalable and can be extended with advanced features such as AIbased job recommendations, resume parsing, and analytics. Overall, the proposed system provides a reliable, efficient, and cost-effective solution for modern recruitment management.

Keywords :

Author : 1Mr.Nagoor Meeravali, 2Javisetti Amareswari, 3Vysyaraju Sairaju, 4Madhira Salman Raju, 5Sanka Durga Dinesh

Title : JOB PORTAL SYSTEM

Volume/Issue : 2026;03(04)

Page No : 179-183

Rapid urbanization and the increasing number of vehicles have made parking management a significant challenge in modern cities. Inefficient parking systems lead to traffic congestion, fuel wastage, increased pollution, and driver frustration. Traditional parking systems rely heavily on manual monitoring, where drivers search for vacant spaces, resulting in time consumption and poor space utilization. To address these issues, this paper presents an intelligent Parking Lot Management System using Internet of Things (IoT) technology that enables real-time monitoring and efficient utilization of parking spaces. The proposed system integrates IoT sensors, microcontrollers, and web-based applications to automate parking management. Sensors installed in each parking slot detect the presence or absence of vehicles and transmit data to a central system. The system processes this data and updates the parking status in real time. A web-based interface developed using Flask allows users to view available parking slots instantly, reducing the time spent searching for parking. Additionally, the system stores parking data in an SQLite database for monitoring and analysis. The implementation uses low-cost sensors and scalable architecture, making it suitable for deployment in various environments such as shopping malls, airports, hospitals, and educational institutions. The system ensures efficient space utilization, reduces traffic congestion, and enhances user convenience. Experimental results demonstrate that the system achieves high accuracy in detecting parking availability with minimal response time. Furthermore, the system contributes to smart city initiatives by integrating IoT technologies with urban infrastructure. Future enhancements may include mobile application integration, automated payment systems, and AI-based predictive parking analytics. Overall, the proposed IoT-based parking management system provides an efficient, reliable, and scalable solution to modern parking challenges, improving traffic flow and user experience while reducing environmental impact.

Keywords :

Author : 1Dr.CH.Suresh, 2Davuluri Tulasi Sushma, 3Veesam Vijay Lakshmi Narasimha, 4Kundheti Madhu, 5Kottapalli Rohith

Title : PARKING LOT MANAGEMENT SYSTEM USING INTERNET OF THINGS

Volume/Issue : 2026;03(04)

Page No : 184-188

The increasing demand for intelligent surveillance systems has led to the development of automated solutions capable of detecting abnormal activities in real time. Traditional CCTV monitoring systems rely heavily on human operators, making them inefficient, timeconsuming, and prone to errors due to fatigue and limited attention span. This research proposes a Real-Time Anomaly Detection System in CCTV using Machine Learning and Computer Vision techniques to overcome the limitations of manual monitoring. The system is designed to automatically analyze video streams, identify unusual activities, and generate alerts without human intervention. The proposed system captures live video footage from CCTV cameras and processes it into frames using OpenCV. These frames are analyzed using machine learning algorithms that compare real-time activity with predefined normal behavior patterns. Any deviation from normal behavior is classified as an anomaly. The system is capable of detecting various abnormal events such as unauthorized entry, suspicious movements, theft, and violent activities. Upon detection, an alert notification is generated and stored along with timestamp details in a SQLite database. A web-based dashboard developed using Flask allows users to monitor alerts and system performance efficiently. The system architecture includes modules such as video capture, frame processing, feature extraction, anomaly detection, alert generation, and database management. The integration of these modules ensures real-time performance and high detection accuracy. Experimental results demonstrate that the system achieves significant accuracy while maintaining a low false alarm rate and fast processing speed. The proposed system reduces the burden on human operators and enhances surveillance efficiency in public places such as airports, banks, railway stations, and shopping malls. It provides a scalable and cost-effective solution for modern security challenges. Future enhancements may include deep learning-based models, cloud deployment, and integration with IoT devices for improved performance. Overall, this research contributes to the advancement of intelligent surveillance systems by providing a robust and automated anomaly detection framework.

Keywords :

Author : 1Mr.Jajjara Bhargav, 2Doppalapudi Satya Sai, 3Patti Venkat Gopiram, 4Kakunuri Gopaiah, 5RANGISETTI SAI SUJITHA, 6Anitha

Title : REAL-TIME ANOMALY DETECTION IN CCTV USING MACHINE LEARNING

Volume/Issue : 2026;03(04)

Page No : 189-194

The School Management System is a web-based application designed to efficiently manage academic and administrative data within educational institutions. Traditional methods of managing school data, such as maintaining registers and spreadsheets, are time-consuming, prone to human errors, and difficult to maintain, especially when dealing with large volumes of data. These limitations necessitate the development of an automated system that can handle school operations in a more efficient and organized manner. The proposed system provides a centralized platform for managing student information, teacher records, attendance, marks, timetables, and report generation. The system is developed using modern web technologies, including HTML, CSS, and JavaScript for frontend development, Python Flask for backend processing, and SQLite for database management. The system enables administrators to perform various operations such as adding and updating student and teacher details, recording attendance, managing marks, scheduling timetables, and generating reports automatically. The system ensures secure data storage, fast data retrieval, and improved accuracy in data handling. Experimental results demonstrate that the system significantly reduces manual workload, minimizes errors, and improves overall efficiency in school management. The user-friendly interface allows easy interaction with the system, making it suitable for use by school administrators and staff. The system is scalable and can be extended to include advanced features such as mobile access, cloud integration, and analytics for better decision-making. Overall, the School Management System provides a reliable, efficient, and cost-effective solution for managing school operations digitally, enhancing productivity and ensuring better data organization

Keywords :

Author : 1Mrs.P.Sindu Priya, 2Anchuri Sravani, 3Potla Vijay Kumar, 4Adusumalli Swetha, 5B. Pavani

Title : SCHOOL MANAGEMENT SYSTEM USING WEB TECHNOLOGIES

Volume/Issue : 2026;03(04)

Page No : 195-198

In the modern educational environment, managing student information efficiently is a critical challenge due to the increasing number of students and the complexity of academic data. Traditional methods of managing student records using manual registers or spreadsheets are time-consuming, error-prone, and inefficient for large-scale data handling. This paper presents a comprehensive Student Management System (SMS) developed using web technologies and database systems to automate and streamline student data management processes. The proposed system is designed to manage student information such as personal details, attendance, academic performance, and report generation in a secure and efficient manner. The system is implemented using HTML, CSS, and JavaScript for the frontend, Python Flask framework for backend processing, and SQLite database for data storage. The system provides a user-friendly interface for administrators to perform various operations, including adding new student records, updating existing data, recording attendance, managing marks, and generating academic reports. By digitizing student data, the system eliminates the limitations of manual record-keeping and enhances data accuracy, security, and accessibility. The proposed system integrates multiple modules such as Admin Module, Student Module, Attendance Module, Marks Module, and Report Generation Module. These modules work collaboratively to ensure efficient data management and real-time processing. The system also ensures secure data storage and fast retrieval using structured database management techniques. Experimental results demonstrate that the system performs efficiently with high accuracy and minimal response time, making it suitable for deployment in educational institutions. Furthermore, the system reduces administrative workload and improves overall institutional efficiency. It also supports scalability, allowing institutions to manage large volumes of data without performance degradation. Future enhancements may include cloud integration, mobile application support, and advanced analytics for student performance prediction. Overall, the proposed Student Management System provides a reliable, efficient, and scalable solution for modern educational institutions, contributing to improved data management and decision-making processes.

Keywords :

Author : 1Dr.CH.Suresh, 2Thalapaneni Navya, 3Lingala Venkata Naga Rohith, 4SHAIK SHAFEENA BANU, 5Murali Krishna Tarigoppala, 6Shaik Chinna Brameswararao

Title : STUDENT MANAGEMENT SYSTEM USING WEB TECHNOLOGIES

Volume/Issue : 2026;03(04)

Page No : 199-203

In the era of digital information, the exponential growth of textual data from sources such as news articles, research papers, blogs, and social media has created a need for efficient information processing systems. Reading and understanding large volumes of text is timeconsuming and often impractical for users. Text summarization has emerged as a crucial Natural Language Processing (NLP) application that automatically condenses large text documents into shorter, meaningful summaries while preserving essential information. This paper presents an intelligent Text Summarization System using NLP and Machine Learning techniques, designed to generate concise summaries from lengthy text inputs. The proposed system employs extractive summarization techniques, where important sentences are selected based on their relevance and significance. The system performs preprocessing steps such as tokenization, stop word removal, and stemming to clean and structure the text. Word frequency analysis is then used to determine the importance of each sentence. Sentences with higher significance scores are selected to form the final summary. The system is implemented using Python programming language, with NLP libraries such as NLTK and SpaCy for text processing. A Flask-based web interface is developed to allow users to input text and view summarized outputs, while SQLite is used for storing text and summary data. The system is designed to reduce reading time and improve information accessibility. Experimental results demonstrate that the system achieves high accuracy in generating meaningful summaries while maintaining a significant compression ratio. Compared to manual summarization, the proposed system is faster, more efficient, and scalable. The system can be applied in various domains, including education, research, business, and content management. The main contribution of this research is the development of a user-friendly and efficient summarization system that leverages NLP techniques to process large text data. Future enhancements may include the integration of abstractive summarization using deep learning models such as Transformers, support for multilingual summarization, and improved semantic understanding. Overall, the proposed system provides a practical and intelligent solution for automatic text summarization.

Keywords :

Author : 1Mr.B.V.Ramakrishna, 2Potla Venkatesh, 3Panthangi Siva Sankar Reddy, 4MEENAKSHI, 5Yarraguntla Ramkumar, 6Nukavarapu Vignesh

Title : TEXT SUMMARIZATION USING NLP AND MACHINE LEARNING

Volume/Issue : 2026;03(04)

Page No : 204-208

The rapid adoption of Unified Payments Interface (UPI) systems has revolutionized digital transactions by enabling instant, secure, and convenient money transfers. However, the exponential growth of digital payments has also led to a significant rise in fraudulent activities, posing serious threats to financial security. Traditional fraud detection mechanisms rely on manual verification or rule-based systems, which are often inefficient and incapable of identifying sophisticated fraud patterns in real time. This research presents a Machine Learning-based UPI Fraud Detection System designed to identify fraudulent transactions efficiently and accurately before completion. The proposed system analyzes transaction data such as transaction amount, time, location, account behavior, and device information to detect anomalies. By leveraging machine learning algorithms, the system learns patterns from historical transaction data and classifies transactions as either normal or fraudulent. The system is implemented using Python, with Flask for web application development and SQLite for database management. The real-time processing capability ensures that fraudulent transactions are detected instantly, minimizing financial losses. The architecture of the system consists of data collection, preprocessing, feature extraction, model training, and prediction modules. The system continuously monitors transaction behavior and identifies suspicious patterns using trained models. Upon detection of a fraudulent transaction, the system generates alerts and stores transaction details in the database for further analysis. Experimental results demonstrate that the system achieves high accuracy and low error rates, making it suitable for real-world applications. The system was tested with multiple transaction datasets and achieved an accuracy of 94% with minimal response time. The proposed approach significantly enhances transaction security and reduces the dependency on manual monitoring. This research contributes to the development of intelligent fraud detection systems by integrating machine learning techniques into digital payment platforms. Future work includes the incorporation of deep learning models, realtime cloud deployment, and advanced behavioral analytics to further improve detection accuracy and scalability. Overall, the system provides a robust and efficient solution for secure digital transactions.

Keywords :

Author : 1Mr.Jajjara Bhargav, 2Kambhampati Bhavya, 3Unnam Jeevan Datta, 4Gowtham, 5Mujahid Shaik

Title : UPI FRAUD DETECTION USING MACHINE LEARNING FOR SECURE DIGITAL PAYMENTS

Volume/Issue : 2026;03(04)

Page No : 209-214