Journal of Science Engineering Technology and Management Science

E.PRAVEEN1 YVNM SARMA 2The Advanced Peripheral Bus (APB) is a low-power, low-bandwidth bus that is part of the Advanced Microcontroller Bus Architecture (AMBA) developed by ARM. It is widely used to connect low-speed peripheral devices such as timers, UARTs, GPIOs, SPI, and I²C controllers in System-on-Chip (SoC) designs. Since APB is responsible for communication between the processor and peripheral devices, verifying its functionality is essential to ensure reliable data transfer and protocol compliance. This project presents the verification of the APB protocol using the Universal Verification Methodology (UVM). UVM is a standardized verification framework built on SystemVerilog that enables the development of reusable, scalable, and modular verification environments. The project implements a complete UVM-based testbench consisting of transaction objects, sequences, sequencer, driver, monitor, agent, environment, scoreboard, and functional coverage components to verify the APB design. The verification environment generates both directed and randomized read/write transactions to validate the APB protocol under different operating conditions. The monitor captures the DUT activity, while the scoreboard compares the expected and actual results to identify mismatches. Functional coverage is collected to ensure that all important protocol features, including read operations, write operations, valid address ranges, wait states, and transfer types, are exercised during simulation. Simulation results confirm that the APB design behaves according to the protocol specification, with successful verification of all functional scenarios. The UVM-based environment improves verification efficiency, enhances code reusability, and provides comprehensive functional coverage. This project demonstrates an industry-standard verification approach for AMBA APB and serves as a strong foundation for verifying more complex bus protocols such as AHB and AXI.

Keywords : The rapid growth of System-on-Chip (SoC) technology has led to the integration of multiple processors, memories, and peripheral devices onto a single chip.

Author : E.PRAVEEN1 YVNM SARMA 2

Title : A REVIEW ON ADVANCED PERIPHERAL BUS INTERFACE PROTOCOL

Volume/Issue : 2026;03(07)

Page No : 717-724

The rapid advancement of Large Language Models (LLMs) has significantly transformed artificial intelligence by enabling machines to perform complex natural language understanding, reasoning, content generation, and decision-making tasks. Despite their remarkable performance, existing LLM-based agents primarily rely on static pre-trained knowledge, making them incapable of continuously adapting to newly emerging information and userspecific experiences. This limitation often results in outdated knowledge, limited personalization, contextual inconsistency, and catastrophic forgetting when models are retrained. To overcome these challenges, this research proposes a comprehensive roadmap for Lifelong Learning of Large Language Model Based Agents, integrating continuous knowledge acquisition, persistent memory, adaptive reasoning, Retrieval-Augmented Generation (RAG), vector-based semantic memory, knowledge graphs, explainable artificial intelligence (XAI), and feedback-driven learning mechanisms. The proposed framework enables intelligent agents to acquire knowledge incrementally from user interactions, external repositories, and dynamic information sources while preserving previously learned knowledge through efficient memory consolidation techniques. A semantic vector database stores contextual representations that facilitate fast retrieval and context-aware reasoning during future interactions. Furthermore, knowledge graph integration enhances structured knowledge representation and semantic relationship discovery, thereby improving inference capability and decision-making accuracy. Explainable AI modules increase system transparency by providing interpretable reasoning pathways, while continuous feedback learning refines knowledge quality and response generation through iterative optimization. An analytics dashboard continuously monitors memory growth, retrieval efficiency, reasoning performance, and learning progression, enabling proactive system evaluation and improvement. Experimental evaluation demonstrates that the proposed lifelong learning framework significantly improves contextual continuity, factual consistency, adaptive learning capability, response relevance, and user personalization compared with conventional LLM architectures. Moreover, the framework effectively reduces hallucination, enhances knowledge retention, minimizes redundant retraining, and supports scalable deployment across diverse real-world applications including education, healthcare, enterprise knowledge management, scientific research, software engineering, and intelligent virtual assistants. The proposed roadmap establishes a robust foundation for developing next-generation autonomous AI agents capable of continuous learning, long-term knowledge evolution, and intelligent decision-making in dynamic environments.

Keywords : Large Language Models, Lifelong Learning, Continual Learning, Retrieval-Augmented Generation, Knowledge Graphs, Vector Database, Explainable Artificial Intelligence, Intelligent Agents.

Author : 1ANTHATI KARTHIK, 2A. MANDHAN CHARI

Title : LIFELONG LEARNING OF LARGE LANGUAGE MODEL BASED AGENTS: A ROADMAP

Volume/Issue : 2026;03(07)

Page No : 725-735

Blockchain technology has become a transformative platform for secure digital transactions by enabling decentralization, transparency, immutability, and distributed trust across multiple application domains. Despite these advantages, existing blockchain platforms primarily rely on conventional cryptographic algorithms such as RSA and Elliptic Curve Cryptography (ECC), which are vulnerable to emerging quantum computing attacks. Furthermore, modern blockchain ecosystems face increasing cybersecurity challenges, including fraudulent transactions, malicious smart contracts, unauthorized access, identity spoofing, network intrusions, and sophisticated cyberattacks that cannot be effectively addressed using traditional security mechanisms alone. To overcome these limitations, this paper proposes a Quantum Secure Blockchain Framework with Machine Learning-Based Threat Detection and Smart Contract Validation, which integrates post-quantum cryptography, intelligent threat detection, trust evaluation, and blockchain security within a unified architecture. The proposed framework employs quantum-resistant cryptographic algorithms such as CRYSTALS-Kyber, CRYSTALSDilithium, Falcon, and SPHINCS+ to secure authentication, digital signatures, and transaction verification against future quantum attacks. Simultaneously, machine learning models, including Random Forest and anomaly detection techniques, continuously analyse transaction behaviour, network traffic, and user activities to identify fraudulent operations and predict security risks before transaction confirmation. A trust management engine computes dynamic trust scores based on historical transaction behaviour, while smart contract validation mechanisms verify transaction authenticity, authorization privileges, fraud probability, and compliance before blockchain execution. The framework is implemented using Python, Django, Solidity, Web3.py, Scikit-Learn, Ethereum, and MySQL, providing secure communication between decentralized applications and blockchain networks. Experimental analysis demonstrates that the proposed architecture significantly improves fraud detection accuracy, enhances transaction integrity, strengthens smart contract security, reduces malicious activities, and provides long-term resilience against both classical and quantum cyber threats. Consequently, the proposed framework establishes a scalable, intelligent, and future-proof blockchain ecosystem suitable for secure financial systems, healthcare, digital identity management, supply chain applications, and next-generation decentralized services.

Keywords : Blockchain Security, Post-Quantum Cryptography, Machine Learning, Threat Detection, Smart Contract Validation, CRYSTALS-Kyber, CRYSTALS-Dilithium, Falcon, SPHINCS+, Random Forest, Ethereum, Web3.py, Fraud Detection, Trust Management, Quantum Computing.

Author : 1D SAI BHANU VARSHIT, 2K UMA

Title : QUANTUM SECURE BLOCKCHAIN FRAMEWORK WITH MACHINE LEARNING-BASED THREAT DETECTION AND SMART CONTRACT VALIDATION

Volume/Issue : 2026;03(07)

Page No : 736-747

Autonomous systems have become a fundamental component of modern intelligent technologies owing to their capability to perform complex tasks with minimal or no human intervention. These systems are extensively employed in robotics, autonomous vehicles, unmanned aerial vehicles, industrial automation, healthcare, intelligent transportation, and smart manufacturing. However, conventional autonomous systems primarily depend on predefined rules and static control strategies, making them less effective in dynamic and uncertain environments. Reinforcement Learning (RL) has emerged as a promising machine learning paradigm that enables autonomous agents to learn optimal behaviours through continuous interaction with their surroundings. Unlike supervised learning, RL does not require labelled datasets; instead, it learns by maximising cumulative rewards obtained through trial-and-error exploration. This research presents a Reinforcement Learning-based Autonomous System implemented using a custom GridWorld environment integrated with the Deep Q-Network (DQN) algorithm. The proposed framework enables an autonomous agent to observe environmental states, execute actions, receive reward feedback, and continuously refine its policy to achieve optimal decision-making. A Flaskbased web application is developed to provide an interactive interface for user authentication, training management, model evaluation, dashboard analytics, and reinforcement learning model storage. The environment incorporates obstacles, target locations, and navigation paths that simulate real-world autonomous navigation scenarios. The DQN algorithm combines deep neural networks with Q-learning to estimate optimal action values and improve learning efficiency within high-dimensional state spaces. Experimental evaluation demonstrates that the autonomous agent gradually improves navigation efficiency, obstacle avoidance capability, cumulative reward, and policy convergence through repeated training episodes. The framework provides real-time monitoring of training performance, reward progression, and model evaluation metrics, thereby enhancing transparency and usability. The proposed system offers a scalable, adaptive, and intelligent platform that significantly improves autonomous decision-making while reducing dependence on manually programmed rules. Furthermore, the framework establishes a strong foundation for future developments involving multi-agent reinforcement learning, explainable artificial intelligence, autonomous robotics, intelligent transportation systems, and real-world adaptive control applications.

Keywords : Reinforcement Learning, Autonomous Systems, Deep Q-Network, Deep Reinforcement Learning, GridWorld, Artificial Intelligence, Autonomous Navigation, Intelligent Decision Making, Flask Framework, Policy Optimisation.

Author : 1KURSAM SNEHA, 2V. VANI

Title : REINFORCEMENT LEARNING FOR AUTONOMOUS SYSTEM

Volume/Issue : 2026;03(07)

Page No : 748-757

The rapid expansion of the Internet of Things (IoT) has revolutionized the way smart devices communicate, collaborate, and exchange information across diverse application domains such as healthcare, industrial automation, transportation, agriculture, smart homes, and smart cities. However, the increasing number of interconnected devices has significantly expanded the attack surface, making secure and reliable device authentication one of the most critical challenges in IoT environments. Conventional authentication mechanisms primarily rely on passwords, cryptographic keys, certificates, and centralized identity management systems. Although these methods provide basic protection, they are unable to effectively detect compromised devices, insider attacks, zero-day threats, or dynamic behavioural changes after authentication. Moreover, supervised machine learning approaches require extensive labelled datasets, which are expensive to obtain and often fail to generalize to emerging attack patterns. To overcome these limitations, this paper proposes a Self-Supervised Deep Learning Framework for Secure and Efficient IoT Device Authentication based on behavioural analysis and anomaly detection. The proposed framework employs a Deep Autoencoder trained using unlabeled telemetry data collected from IoT devices, including CPU utilisation, memory usage, packet transmission rate, communication frequency, and sensor activity. By learning normal operational behaviour, the model identifies abnormal activities through reconstruction error without requiring labelled attack data. A dynamic trust management mechanism evaluates each device according to its behavioural consistency and anomaly score, enabling continuous authentication rather than one-time credential verification. Devices with high trust scores are granted network access, whereas suspicious devices are isolated to prevent malicious activities. The framework integrates telemetry collection, anomaly detection, trust evaluation, authentication decision-making, and real-time dashboard monitoring into a unified security architecture. Experimental evaluation demonstrates that the proposed framework improves authentication accuracy, enhances anomaly detection capability, reduces false alarms, minimises computational overhead, and provides adaptive protection against evolving cyber threats. Consequently, the proposed approach offers a scalable, intelligent, and resource-efficient security solution suitable for next-generation IoT ecosystems requiring autonomous and continuous device authentication.

Keywords : Internet of Things (IoT), Self-Supervised Learning, Deep Autoencoder, Device Authentication, Anomaly Detection, Trust Management, Deep Learning, Cybersecurity, Telemetry Analysis, Continuous Authentication.

Author : 1G. LAVANYA, 2RAJITHA KATHULA

Title : SELF-SUPERVISED DEEP LEARNING FRAMEWORK FOR SECURE AND EFFICIENT IoT DEVICE AUTHENTICATION

Volume/Issue : 2026;03(07)

Page No : 758-769

The rapid expansion of urban populations, increasing vehicle ownership, and growing transportation demands have intensified challenges such as traffic congestion, road accidents, environmental pollution, fuel wastage, and inefficient route planning within modern smart cities. Conventional traffic management systems rely heavily on fixed traffic signal schedules, manual surveillance, and historical traffic analysis, making them inadequate for responding to dynamic and real-time transportation conditions. Artificial Intelligence (AI) has emerged as a transformative technology capable of enhancing Intelligent Transport Systems (ITS) by enabling predictive analytics, automated traffic monitoring, intelligent decision-making, and adaptive route optimisation. This study presents an AI-driven Intelligent Transport System that integrates Machine Learning, Computer Vision, and graphbased routing algorithms to improve transportation efficiency and urban mobility. The proposed framework employs a Random Forest classifier to predict traffic congestion by analysing historical traffic records, weather conditions, temporal features, and traffic density patterns. Computer Vision techniques based on YOLOv8 are utilised for real-time vehicle detection, while the MediaPipe framework performs pedestrian detection and crowd density estimation using surveillance images and video streams. Furthermore, Dijkstra's shortest path algorithm is implemented to determine optimal travel routes by considering congestion conditions and road network characteristics. The entire framework is deployed through a Flask-based web application integrated with an SQLite database and an interactive dashboard for real-time transportation analytics and decision support. Experimental evaluation demonstrates that the proposed framework achieves high prediction accuracy, reliable object detection, and efficient route optimisation, thereby reducing travel time and improving traffic flow. The integration of Artificial Intelligence technologies enables proactive traffic management, enhances road safety, supports emergency response planning, and contributes to sustainable urban transportation. The proposed Intelligent Transport System provides a scalable and cost-effective solution for smart city administrators, transportation authorities, and urban planners seeking intelligent, data-driven transportation management capable of addressing the evolving mobility requirements of future smart cities.

Keywords : Artificial Intelligence, Intelligent Transport Systems, Smart Cities, Machine Learning, Random Forest, YOLOv8, MediaPipe, Traffic Congestion Prediction, Vehicle Detection, Route Optimisation, Dijkstra Algorithm, Urban Mobility.

Author : 1CHILUKA SANDHYA RANI, 2VARUGU. RAMESH BABU

Title : THE ROLE OF ARTIFICIAL INTELLIGENCE IN INTELLIGENT TRANSPORT SYSTEMS FOR SMART CITIES

Volume/Issue : 2026;03(07)

Page No : 770-780

Privileged Access Management (PAM) systems play a critical role in securing high-risk identities within enterprise environments. Current PAM solutions, however, are mostly based on static policies and context-independent monitoring, which are not enough to detect context-dependent anomalous behaviors in contemporary distributed systems. In this paper, a context-aware, AI-based anomaly detection mechanism based on hybrid deep learning architectures to learn temporal and behavioral patterns of privileged access activities is proposed. The proposed CNN-BiLSTM-Attention network, Transformer-GRU fusion network, Attention-CNN-LSTM network and Hierarchical BiGRU with context gating network are integrated together. Experimental results on a synthetic enterprise PAM dataset show the remarkable detection performance of the Hierarchical BiGRU with an accuracy of 99.14% and an F1 score of 99.32%. The work extends PAM from a static-to-dynamic approach to access control to a more continuous approach to security monitoring.

Keywords : Privileged Access Management, Identity and Access Management, anomaly detection, deep learning, contextual risk scoring, explainable AI, enterprise cybersecurity.

Author : Anupam Nandan

Title : AI-DRIVEN PRIVILEGED ACCESS MANAGEMENT (PAM): A CONTEXT-AWARE DEEP LEARNING FRAMEWORK FOR PREDICTIVE ANOMALY DETECTION IN ENTERPRISE SYSTEMS

Volume/Issue : 2026;03(07)

Page No : 781-790

The effective management of blood donation services is essential for ensuring that healthcare organizations can provide timely blood transfusions during emergencies and routine medical treatments. Traditional blood bank management methods, which often depend on manual documentation or disconnected software systems, are associated with problems such as delayed processing, inaccurate inventory records, and inefficient communication among stakeholders. To overcome these challenges, this research proposes a web-based Online Blood Donation Management System developed using the Django framework with a centralized database for efficient information management The application integrates key blood bank functions, including donor registration, patient blood request management, blood stock monitoring, and administrative control, within a unified digital platform. Blood inventory is updated automatically whenever a donation is approved or blood is issued, ensuring that stock information remains accurate and available in real time. The implementation of role-based authentication provides secure access by assigning specific permissions to administrators, donors, and patients according to their responsibilities, thereby improving both data security and system reliability To further enhance user interaction, the system incorporates an Artificial Intelligence (AI)-enabled chatbot developed using Retrieval-Augmented Generation (RAG) and a Large Language Model (LLM). The chatbot retrieves relevant information from the system database and delivers context-aware responses to user questions related to blood donation eligibility, blood group compatibility, blood availability, donation procedures, and request status. This intelligent support mechanism reduces the workload of blood bank staff while providing users with immediate and accurate assistance Performance evaluation indicates that the proposed system offers significant improvements in operational efficiency, data accuracy, inventory management, transparency, and response time when compared with conventional blood bank management practices. The modular architecture of the application also supports future enhancements, including cloud deployment, integration with hospital information systems, mobile application development, and multi-branch blood bank management. The proposed solution therefore provides a secure, scalable, and intelligent platform for modern blood donation management and contributes to improving the quality of healthcare services.

Keywords : Online Blood Donation Management System, Django Framework, Blood Inventory Management, Healthcare Information System, Artificial Intelligence (AI), Retrieval-Augmented Generation (RAG), Large Language Model (LLM), Web-Based Application, Role-Based Access Control (RBAC).

Author : G Anjali, Dr Md Nazmoddin, Dr. V. Anantha Krishna, Dr. U. Sri Lakshmi

Title : ONLINE BLOOD BANK MANAGEMENT SYSTEM

Volume/Issue : 2026;03(07)

Page No : 791-799

Artificial Intelligence (AI) has revolutionized the credit risk assessment process in digital banking by allowing financial institutions to analyze vast amounts of customer data and make quicker lending decisions. Many AI models are "black-box" systems, making it hard for stakeholders to understand how the AI is making decisions, and many AI models have high predictive accuracy. The opacity of this raises issues about equity, accountability, and meeting changing regulatory requirements. Explainable Artificial Intelligence (XAI) is one of the nascent solutions that can help mitigate these challenges while offering a transparent, interpretable explanation of the AI-generated results with a negligible impact on the model performance.This study explores how XAI can help balance predictive performance, algorithmic fairness, and compliance in digital banking situations. It suggests a conceptual approach that would enable cheaper credit risk assessment areas the improvement of transparency, decrease the probability of possible bias in lending decisions and help to align with responsible AI governance principles. The study is quantitative in nature, and it is recommend that data be gathered from the banking professionals, credit risk analysts, fintech specialists and compliance officers by means of a structured questionnaire. The relationships between the constructs can be investigated through the application of Structural Equation Modelling (SEM) to assess both direct and indirect effects of how explainability affects credit risk assessment.What is expected is that the use of explainable AI in credit evaluation processes can boost confidence of the lenders, increase the fairness of the lending processes, and improve the adherence to regulation with reliable predictive performance. The study aligns with other recent works on the responsible use of AI in financial services, providing a holistic view that balances technology with ethical and regulatory aspects. The results will offer valuable insights for banks, regulators, and fintech firms aiming to create AI-powered credit risk assessment models that are transparent, trusted, and sustainable in a digitalfirst financial landscape.

Keywords : Explainable Artificial Intelligence (XAI), Credit Risk Assessment, Digital Banking, Predictive Accuracy, Algorithmic Fairness, Regulatory Compliance, Responsible Artificial Intelligence, Financial Technology (FinTech).

Author : Dr. SUJITHA K A

Title : THE ROLE OF EXPLAINABLE ARTIFICIAL INTELLIGENCE IN CREDIT RISK ASSESSMENT: BALANCING PREDICTIVE ACCURACY, ALGORITHMIC FAIRNESS, AND REGULATORY COMPLIANCE IN DIGITAL BANKING

Volume/Issue : 2026;03(07)

Page No : 800-815

The growing use of digital technologies has transformed the way organizations manage their human resources. HR Analytics has become an important management approach that helps organizations make informed decisions by analyzing employee-related data. Ratherthan relying only on experience or intuition, organizations are increasingly using analytics to improve recruitment, employee performance, workforce planning, talent management, and retention strategies. The adoption of HR Analytics also enables managers to identify workforce trends, predict future human resource requirements, and support strategic business decisions. The present study examines the adoption and implementation of HR Analytics in modern organizations and explores its role in improving human resource management practices. The research is based on secondary data collected from books, peer-reviewed journals, published articles, industry reports, and other reliable academic sources. The study discusses the concept of HR Analytics, its major applications, implementation process, organizational benefits, and the challenges faced during its adoption. The findings reveal that organizations implementing HR Analytics experience better decision-making, improved employee productivity, enhanced workforce planning, and more effective performance management. At the same time, several challenges continue to influence successful implementation, including poor data quality, lack of analytical expertise, privacy and security concerns, technological constraints, and resistance to organizational change. The study concludes that organizations should strengthen their digital capabilities, invest in employee training, and develop a data-driven organizational culture to fully realize the benefits of HR Analytics. As businesses continue to embrace digital transformation, HR Analytics is expected to play a significant role in achieving organizational efficiency, sustainable growth, and long-term competitive advantage.

Keywords : HR Analytics, People Analytics, Workforce Analytics, Data-Driven Decision Making, Talent Management, Employee Performance, Predictive Analytics, Human Resource Management.

Author : Mr. N. Anil Kumar, Mr. Y. Venkat Reddy, Mr. M. Ramesh Naik

Title : A Study on the Adoption and Implementation of HR Analytics in Modern Organizations

Volume/Issue : 2026;03(07)

Page No : 816-830

The AI-Enabled Adaptive Examination and Evaluation Platform is an intelligent web-based system designed to simplify and automate the examination process while ensuring accuracy, security, and efficiency. The platform integrates artificial intelligence with modern web technologies to provide a smart examination environment for both students and administrators. It includes features such as student registration, secure login, face recognition-based attendance, eligibility verification, hall ticket generation, online examination, AI-based evaluation, and automatic result generation. The system uses face recognition technology to authenticate students and record attendance accurately, reducing the possibility of impersonation and manual errors. AI-based evaluation helps in assessing student performance efficiently and provides instant results with improved accuracy. The administrator can manage student records, monitor examination activities, and generate reports through a centralized dashboard. Traditional examination systems often involve manual attendance, paper-based examinations, delayed result processing, and increased administrative workload, which may lead to errors and inefficiencies. The proposed platform overcomes these limitations by providing an automated, secure, and user-friendly solution. It improves examination management, enhances transparency, reduces processing time, and offers a reliable digital environment for conducting and evaluating examinations.

Keywords :

Author : 1Dr. P. Harini, 2Ganji Vineela, 3Dwaram Mounika, 4Duddu Suneetha

Title : AI-ENABLED ADAPTIVE EXAMINATION AND EVALUATION PLATFORM

Volume/Issue : 2026;03(07)

Page No : 831-837

An Intelligent Crowd Density Monitoring System using Computer Vision is designed to automatically detect, count, and monitor the density of people in public areas using surveillance cameras and deep learning techniques. The system processes real-time video streams to identify individuals, estimate crowd density, and classify areas as low, medium, or high density. It can generate instant alerts when overcrowding exceeds predefined thresholds, helping authorities improve public safety, crowd management, and emergency response. By reducing manual monitoring and providing accurate realtime analysis, the proposed system offers an efficient, reliable, and cost-effective solution for smart surveillance in places such as railway stations, shopping malls, stadiums, airports, and public events.

Keywords :

Author : 1Mr. K. Ramesh Babu, 2Dabbakuti Jaswitha, 3Ganeshan Sowmya, 4Gavini Harika

Title : Intelligent Crowd Density Monitoring System Using Computer Vision

Volume/Issue : 2026;03(07)

Page No : 838-842

The project Intelligent OCR System for Handwritten Government Document Digitization proposes a digital approach for transforming handwritten government records into structured and editable text. This traditional practice increases processing time, creates dependency on human effort, and makes searching, storing, and reusing document content difficult. To address these limitations, the proposed system introduces an OCR-driven document digitization framework that automates handwritten text extraction and organizes the processed output in digital form.The system is implemented as a web application using HTML, CSS, and JavaScript for the user interface, FastAPI for backend services, and MongoDB Atlas for persistent data storage. For handwritten text recognition, the system integrates Gemini Vision OCR, and a translation component is included to convert extracted text into English when needed. The core methods used in the project include OCR-based text recognition, image preprocessing for improving input quality, translation of extracted text, database-based record management, and document export generation. The proposed solution minimizes manual work, improves accessibility of handwritten records, and supports faster retrieval and reuse of document content.

Keywords :

Author : 1Dr. Ratna Raju Mukiri, 2Gattupalli D. S. V Naga Sai Mani Deepika, 3Boddu Sravani,4Dasari Manoj Kumar

Title : Intelligent OCR System for Handwritten Government Document Digitization

Volume/Issue : 2026;03(07)

Page No : 843-852

The Smart AI-Based Weather Forecasting and Climate Analysis Platform is an intelligent system that utilizes Artificial Intelligence (AI) and Machine Learning (ML) techniques to provide accurate weather forecasts and climate analysis. The platform analyzes historical weather data, including temperature, humidity, wind speed, atmospheric pressure, and precipitation, to predict future weather conditions using advanced machine learning algorithms. Unlike traditional forecasting methods, which often have limited accuracy and require extensive manual analysis, the proposed system offers automated prediction, real-time data visualization, and comprehensive climate trend analysis through a user-friendly web interface. Multiple machine learning models are trained and evaluated using performance metrics such as Accuracy, Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and R² Score to identify the most effective forecasting model. The system enables users to make informed decisions in sectors such as agriculture, disaster management, transportation, tourism, and daily planning by providing reliable weather predictions and climate insights.

Keywords :

Author : 1N. Lakshmi Narayana,2Kaki Deepthi Sri,3K.V. Sai Lakshmi,4K.V. Siva Adithya

Title : Smart AI Based Weather Forecasting and Climate Analysis Platform

Volume/Issue : 2026;03(07)

Page No : 853-859

Students often require quick and accurate answers to academic questions, but searching across multiple websites, textbooks, and learning platforms consumes valuable study time. This paper presents an AI-Powered Student Assistance Chatbot, a web-based application designed to provide instant academic support through natural language conversations. The proposed system integrates the Google Gen AI SDK with the Gemini 2.5 Flash model to understand user queries and generate accurate, context-aware responses in real time. Unlike conventional rule-based chatbots, the system responds intelligently without relying solely on predefined rules or static question-answer repositories. The application is developed using Python and the Flask framework for backend processing, while HTML, CSS, and JavaScript are used to create a responsive and user-friendly interface. A secure login mechanism, interactive dashboard, chatbot interface, and academic resources module enhance usability and accessibility. Additionally, a predefined FAQ module provides immediate responses to common questions, reducing unnecessary AI requests and improving efficiency. The proposed solution demonstrates how generative AI can enhance educational support by delivering fast, reliable, and interactive academic assistance while improving students' overall learning experience.

Keywords :

Author : 1Dr. Y. Chitti Babu,2Mellacheruvu Vijaya Lakshmi,3Nukathoti Akhila,4Korumalli Sujatha

Title : AI-POWERED STUDENT ASSISTANCE CHATBOT

Volume/Issue : 2026;03(07)

Page No : 860-867

This project presents a Conversational Image Recognition Chatbot that integrates Artificial Intelligence, Computer Vision, and Vision-Language Models to provide intelligent image analysis through natural language conversations. The system enables users to upload an image and interact with it by asking questions about its contents, such as identifying objects, describing scenes, extracting text, and understanding contextual relationships. It ensures accurate and real-time image understanding by leveraging advanced deep learning techniques and multimodal AI models. Unlike traditional image recognition systems that only classify objects or generate static captions, the proposed system supports interactive, context-aware conversations, allowing users to ask follow-up questions and receive detailed responses. Conventional image recognition applications often lack conversational capabilities, contextual reasoning, and personalised interaction, making them less effective for complex visual understanding tasks. There is a need for an intelligent, user-friendly, and cost-effective image recognition system that combines computer vision with conversational artificial intelligence to deliver accurate, explainable, and human-like responses. The proposed chatbot addresses these limitations by providing an efficient and scalable solution suitable for applications in education, healthcare, tourism, accessibility, customer support, and smart digital assistants.

Keywords :

Author : 1Dr. P. Harini, 2M. Triveni, 3M. Hema Srivalli, 4N. Sudheer Vali

Title : Conversational Image Recognition Chatbot Using Vision-Language Models

Volume/Issue : 2026;03(07)

Page No : 868-874

This project presents an AI-Based Timetable Generation System aligned with the National Education Policy (NEP) 2020. The system automates the process of generating academic timetables by considering faculty availability, classroom allocation, course requirements, student preferences, and institutional constraints. It improves efficiency, accuracy, and flexibility while supporting the multidisciplinary and student-centric approach promoted by NEP 2020. The system uses artificial intelligence and optimization techniques to generate conflict-free timetables within a short time. It automatically detects and resolves scheduling conflicts, ensuring the effective utilization of classrooms, faculty members, and teaching hours. Traditional timetable preparation is a manual and time-consuming process that is prone to human errors, scheduling conflicts, and frequent modifications due to changes in faculty, courses, or classroom availability. These limitations reduce administrative efficiency and create inconvenience for both students and faculty. Therefore, there is a need for an intelligent, automated, and cost-effective timetable generation system that can produce optimized schedules while complying with NEP 2020 guidelines and improving the overall academic planning process.

Keywords :

Author : 1Dr. D. Nagesh Babu,2Kumbha Akshaya,3Matcha Yaswanth Reddy,4Kahara Prince

Title : AI-Based Timetable Generation System Aligned with NEP 2020

Volume/Issue : 2026;03(07)

Page No : 875-880

Our project, "AI Assist Telemedicine Kiosk for Rural India," is designed to improve healthcare access in rural areas where medical facilities and qualified doctors are limited. The system uses Artificial Intelligence and Machine Learning to predict diseases based on the symptoms entered by the user and provides health recommendations, suggested medicines, and doctor consultation advice. It is developed using Python, Flask, HTML, CSS, JavaScript, and SQLite, with the Random Forest algorithm implemented through Scikit-learn for accurate disease prediction. Patient details and prediction records are stored securely in the database for future reference. The telemedicine kiosk helps reduce unnecessary hospital visits, supports early disease detection, and provides quick preliminary healthcare assistance. Overall, the project offers an affordable, reliable, and user-friendly solution to improve healthcare services for people living in rural and remote communities.

Keywords :

Author : 1Mr. K. Ramesh, 2 Seelam Lalitha Mahalakshmi, 3Tulasi Lakshmi Amrutha, 4T. S. V. Sai Subhramanyam

Title : Artificial Intelligence-Assist Tele Medicine Kiosk Rural India

Volume/Issue : 2026;03(07)

Page No : 881-887

This project presents a Smart AI-Powered Attendance and Engagement Monitoring System integrated with Artificial Intelligence and face recognition technology. The system automates attendance recording while improving accuracy, security, and classroom monitoring. It identifies registered students through real-time facial recognition and records attendance automatically without requiring manual intervention. The application uses a webcam and computer vision techniques to detect, recognize, and verify faces, ensuring that only authorized individuals are marked present. If an unregistered person is detected, the system identifies them as "Unknown", preventing proxy attendance and unauthorized access. Traditional attendance methods, such as manual registers, biometric devices, or RFID cards, are time-consuming, prone to human errors, and vulnerable to proxy attendance. These methods also require physical interaction and additional administrative effort to maintain attendance records. There is a growing need for an intelligent, contactless, and automated attendance management system that can provide accurate identification, minimize manual work, and maintain secure attendance records in real time. the proposed system is developed using Python, Flask, OpenCV, and the face_recognition library. Attendance data, including the student's name, date, and time, is automatically stored in a CSV file for future reference.

Keywords :

Author : 1 Dr. Ratna Raju Mukiri, 2 Potnuri Sravani, 3Budati Sahithi, 4Rachuri Srivalli

Title : Smart AI-powered Attendance and Engagement Monitoring System

Volume/Issue : 2026;03(07)

Page No : 888-894

Current groundwater exploration methods require extensive geological surveys and manual investigation, making the process expensive and time-consuming. This research proposes an AI-enabled water well prediction analysis system that utilizes machine learning algorithms, satellite imagery, rainfall records, soil characteristics, groundwater levels, geological information, and GIS data to predict suitable locations for drilling water wells. The proposed system analyzes multiple environmental parameters to estimate groundwater availability with improved accuracy. The system reduces unnecessary drilling costs, minimizes resource wastage, and supports sustainable groundwater management. Experimental results demonstrate that AI techniques significantly improve prediction accuracy compared to conventional groundwater exploration methods.

Keywords :

Author : 1Mr. N. Lakshmi Naryana,2N. Naga Sai Koushik,3G. Gowrish Kumar,4Y. Prabhas

Title : AI Based Water Well Prediction System Using Machine Learning

Volume/Issue : 2026;03(07)

Page No : 895-901

The Smart Classroom Management System (SCMS) is a full-stack, role-based web application developed to digitalize and automate the academic and administrative operations of educational institutions. The system serves three distinct user roles — Administrator, Teacher, and Student — each provided with a dedicated dashboard and an access-controlled feature set. Traditional classroom management relies on fragmented tools, manual attendance registers, spreadsheets, and paper-based records, which are timeconsuming, error-prone, and offer no centralized visibility for administrators. There is a need for a secure, centralized, and intelligent platform that can automate attendance, scheduling, and communication while eliminating proxy attendance and administrative overhead. The proposed system is built using Node.js and Express.js on the backend with MongoDB as the database, and a React 19 with TypeScript frontend styled using Tailwind CSS. It integrates role-based JWT authentication with an optional browserbased Face Recognition login, an intelligent auto-generation algorithm for conflict-free timetables, real-time announcements and messaging through Socket.IO, and comprehensive digital profile card management for students and teachers.

Keywords :

Author : 1 Mrs. D. Madhuri, 2 Papana Dwarakesh, 3 Satti Pandu, 4 Tiruveedhula Pradeep

Title : Smart Classroom Management Software for Enhanced Learning Environments

Volume/Issue : 2026;03(07)

Page No : 902-909

The study presents a price-adaptive energy management solution that incorporates a single-phase household system, electric vehicles (EVs), and hybrid solar photovoltaic (PV) and wind generation. The suggested method deftly incorporates electric car charging and discharging, grid interaction, and renewable power production to mitigate power price volatility. When the cost of electricity reaches a userconfigurable daily threshold, the system shifts to discharge mode to assist residential loads, and it prioritises rapid EV charging when the cost of electricity is low and renewables are plentiful. Another way electric vehicles may save money on electricity and reduce their grid reliance is by driving in vehicle-to-home (V2H) mode during peak tariff times. Our innovative minimum lncosh-based voltage source converter (VSC) management strategy ensures dependable operation regardless of external factors such as price fluctuations, rapid changes in demand, or intermittent renewable production. The suggested controller improves system stability and lessens the effect of outliers compared to more traditional control approaches. By lowering harmonics and maintaining a power factor of unity at the point of common connection, it enhances the gridside power quality. Power quality, economic advantages, and utilisation of renewable energy sources are three areas where the suggested hybrid system outperforms current techniques, according to comprehensive simulation tests.

Keywords :

Author : C.Radhacharan, K.Anusha

Title : Hybrid Solar and Wind Residential EV Charging System with Price-Adaptive Energy Management

Volume/Issue : 2026;03(07)

Page No : 932-942

Travel planning has become increasingly complex due to the large amount of information available about destinations, transportation, accommodation, and tourist attractions. Selecting suitable travel options that match individual preferences often requires significant time and effort. To address this challenge, this paper presents a Smart Destination and Itinerary Planning Platform, an intelligent webbased application that generates personalized travel itineraries using artificial intelligence techniques. The proposed system allows users to provide travel details such as source location, destination, budget, and personal preferences related to weather, food, and transportation. Based on these inputs, the platform generates customized travel plans using deep learning models and improves recommendation accuracy through a Retrieval-Augmented Generation (RAG) approach. The selected itinerary is further enhanced by automatically retrieving relevant destination images using web scraping techniques, providing users with a more informative and engaging travel experience. The application also includes secure user registration, authentication, and efficient data management to ensure a smooth user experience. Experimental evaluation demonstrates that the platform produces practical and personalized travel recommendations while significantly reducing the effort required for trip planning. Overall, the proposed system offers an intelligent, efficient, and user-friendly solution for modern travel planning by combining AI-based itinerary generation, retrieval techniques, and visual information within a single platform.

Keywords :

Author : BUJANGARI NIKHIL REDDY, Dr. PURNA CHANDAR RAO

Title : Smart Destination and Itinerary Planning Platform

Volume/Issue : 2026;03(07)

Page No : 910-916

The increasing use of mobile messaging applications has resulted in a rapid rise in spam messages and malicious URLs, posing significant threats to user privacy and online security. This paper presents a web-based system that performs multilingual SMS spam detection along with malicious URL classification using machine learning and natural language processing techniques. The proposed approach utilizes the Multilingual Bidirectional Encoder Representations from Transformers (MBERT) model to classify both English and Hindi SMS messages as either spam or legitimate after performing text preprocessing and data cleaning. For URL analysis, a Random Forest classifier is employed to identify whether a submitted web link is safe or malicious. The application consists of secure user authentication, dataset processing, model training, real-time SMS prediction, URL verification, and performance evaluation modules. Experimental results indicate that the MBERT model achieves an accuracy for SMS spam detection, while the Random Forest classifier attains accuracy in malicious URL classification. Performance is evaluated using precision, recall, F1-score, confusion matrices, and graphical analysis. The developed system provides an effective, practical, and scalable solution for protecting users from spam messages and harmful web links in multilingual communication environments.

Keywords :

Author : JAMMULA RISHITHA, Dr. P.JOHN PAUL

Title : Hybrid NLP Framework for Real-Time Multilingual SMS Spam and Malicious URL Intelligence

Volume/Issue : 2026;03(07)

Page No : 917-923

Ensuring that industrial workers wear safety helmets correctly is essential for reducing workplace accidents and improving occupational safety. This paper presents an enhanced YOLOv5-based framework for real-time safety helmet compliance detection using computer vision techniques. The proposed model incorporates an attention mechanism and an improved non-maximum suppression strategy to improve feature extraction, reduce overlapping detections, and enhance detection accuracy. The system classifies objects into three categories: helmet, head, and uncertain helmet usage, enabling reliable identification of both proper and improper helmet wearing. The SHWD dataset is used for training and evaluation, with image preprocessing, normalization, and an 80:20 train-test split. Experimental results demonstrate that the proposed framework achieves high detection accuracy while maintaining real-time inference speed, making it suitable for practical industrial surveillance applications. The developed system provides an efficient and automated solution for monitoring helmet compliance, supporting workplace safety management and minimizing the need for continuous manual inspection.

Keywords :

Author : Malge Shubham, Dr. M. Ramesh

Title : An Enhanced YOLOv5 Framework with Attention-Based Feature Learning for Real-Time Industrial Safety Helmet Compliance Detection

Volume/Issue : 2026;03(07)

Page No : 924-931