Journal of Science Engineering Technology and Management Science

The global workforce landscape has undergone a seismic shift, transitioning from traditional office-centric environments to flexible, hybrid configurations. For a telecommunications giant like Bharti Airtel Ltd., which operates at the intersection of digital connectivity and infrastructure, the adoption of a hybrid work model is not merely a logistical change but a strategic pivot. This research project explores the multifaceted impact of the hybrid work model on employee engagement, work-life balance, and overall organizational productivity within Airtel’s corporate and regional operations. The primary objective of this study is to evaluate how the "Work from Anywhere" (WFA) and "Flexi-Office" policies implemented between 2023 and 2025 have influenced the behavioral and performance metrics of the workforce. The research employs a Descriptive Research Design, utilizing a mix of primary and secondary data. Primary data was collected through a structured questionnaire administered to 100 employees across various departments of Airtel, focusing on parameters such as digital fatigue, collaboration efficacy, and job satisfaction.The study investigates the dual nature of hybrid work: while it provides employees with enhanced autonomy and reduced commuting stress, it also presents challenges regarding social isolation and the "always-on" culture. Furthermore, the research analyzes the role of Airtel’s internal digital ecosystem (such as BlueJeans, Airtel IQ, and Workday) in facilitating seamless collaboration. Preliminary findings indicate a significant positive correlation between flexible work arrangements and employee retention rates. However, the data also suggests that middle management faces increased pressure in maintaining team cohesion without physical proximity. The study concludes with strategic recommendations for Airtel’s HR leadership to refine their hybrid policies, emphasizing the need for "Purposeful Presence" in the office and the integration of AI-driven wellness tools to mitigate employee burnout. This project serves as a comprehensive guide for understanding how telecommunication leaders can balance operational efficiency with employee-centric flexibility in a post-pandemic economy.

Keywords : The conceptualization of work has undergone a radical transformation in the last five years, moving away from the rigid, factory-inspired "9-to-5" office model toward a fluid, resultoriented framework known as the hybrid work model.

Author : N VIJAYA SREE ,MRS. D SUSHMA KIRAN

Title : A STUDY ON HYBRID WORK MODEL IMPACT

Volume/Issue : 2026;03(08)

Page No : 335-348

In the hyper-competitive global talent market of the 2024–2026 era, the role of recruitment consulting has shifted from mere database management to high-stakes strategic talent advisory. This project provides an in-depth analysis of the Screening Process, the most critical and labor-intensive phase of the recruitment lifecycle, within Inkonsul Technologies. As a technology-focused consulting firm, Inkonsul operates in an environment where the "Cost of a Bad Hire" is exceptionally high, making the technical and behavioral filtration of candidates a paramount concern for organizational success.The primary objective of this research is to evaluate the various screening methodologies— ranging from traditional resume parsing to contemporary AI-driven behavioral assessments—employed by Inkonsul Technologies. The study explores how these processes impact the "Quality of Hire," the "Time-to-Fill" metric, and the overall satisfaction of the client organizations. The research adopts a descriptive and analytical methodology, utilizing a sample size of 100 HR professionals and recruitment consultants within the organization. Data collection was facilitated through a structured Likert-scale questionnaire, supplemented by secondary data from the firm’s Applicant Tracking System (ATS) and internal performance audits. Key focus areas of the investigation include the integration of Generative AI in initial screening, the efficacy of Pre-employment Testing, and the impact of Unconscious Bias during the shortlisting phase. Preliminary findings suggest that while Inkonsul Technologies has successfully automated 60% of the initial screening workflow, there remains a critical need to refine the "Human-in-the-Loop" validation to ensure cultural fit and soft-skill alignment. The data indicates a strong correlation between rigorous multi-stage screening and reduced 90-day attrition rates at client firms. The project concludes with strategic recommendations for the HR department, including the implementation of "Blind Screening" techniques to enhance diversity and the adoption of "Predictive Talent Analytics" to forecast candidate success. By aligning technological efficiency with human intuition, Inkonsul Technologies can optimize its screening funnel to deliver elite talent in a volatile market.

Keywords : The global human resource landscape has undergone a tectonic shift, transitioning from a purely administrative function to a core strategic pillar that dictates the competitive survival of modern enterprises.

Author : MUTHA PRATHYUSHA , MR.R SRINIVASA RAO

Title : A STUDY ON SCREENING PROCESS IN A RECRUITMENT CONSULTING FIRM

Volume/Issue : 2026;03(08)

Page No : 349-363

Digital banking has transformed the way customers access and manage financial services by providing convenient, secure, and efficient banking solutions through internet and mobile platforms. This study examines the level of customer satisfaction with digital banking services by evaluating key factors such as ease of use, service quality, transaction speed, security, reliability, accessibility, and customer support. The research is based on primary data collected through structured questionnaires and supported by secondary data from banking reports, journals, and published literature. Statistical tools such as percentage analysis and graphical representation are used to analyze customer responses and identify the factors influencing satisfaction. The findings indicate that most customers are satisfied with digital banking services due to their convenience, 24/7 availability, and quick transaction processing, while concerns regarding cybersecurity, technical issues, and digital literacy continue to affect user experience. The study concludes that continuous technological innovation, enhanced security measures, and improved customer awareness programs are essential for increasing customer confidence and achieving higher levels of satisfaction with digital banking services.

Keywords : Modern banks play an important role in promoting economic development of a country.

Author : MUNUKUNTLA HARSHITHA ,MRS. J MANASA

Title : A STUDY ON DIGITAL BANKING CUSTOMER SATISFACTION

Volume/Issue : 2026;03(08)

Page No : 364-377

The experiences from the Indian capital market are now the history for many market participants due to the dramatic changes in the Investment Banking pattern of small equity investors. The investor can make the share trading as a beneficial Investment Banking area. The business firms issue the shares of their firms and mobilize funds from the individual savers. Equity share is a part of the ownership of a company and the holder of such a share is a member of the company and eligible to get benefits from the company. Trading in stocks is quiet simple that possess some basic knowledge of the security trading. Investment Banking pattern refers to a regular sequence of actions followed by the Investment Banking decisions of investor. Understanding the Investment Banking pattern of small equity investors in Investment Banking decision making is important in stock trading. The attitude of the investors has been changing due to the changes in the stock market scenario. When the investors avail the accurate and reliable information, then he can enjoy the taste of success from the share market. The authorities, like SEBI, NSDL etc., should organize more seminars and awareness programs for these under privileged retail investors.

Keywords : Investment Banking is the allocation of funds with the hope of future gains. Investment Banking benefits not just the economy but also society.

Author : MUDA UJWALA , MRS. D SUNITHA

Title : A STUDY ON ROLE OF ANALYTICS IN INVESTMENT BANKING

Volume/Issue : 2026;03(08)

Page No : 378-391

The contemporary corporate landscape has witnessed a paradigm shift where human capital is no longer viewed merely as a resource, but as the primary driver of competitive advantage. This project explores the efficacy and strategic importance of Employee Wellbeing Programs within Inkonsul Technologies, a dynamic player in the technology services sector. In an era characterized by high-pressure environments, rapid digital transformation, and the blurring lines between professional and personal lives, the holistic health of an employee—encompassing physical, mental, and emotional dimensions—has become a boardroom priority. The primary objective of this research is to evaluate the existing well-being initiatives at Inkonsul Technologies and determine their correlation with employee engagement, retention, and overall operational productivity. The study adopts a descriptive research design, utilizing a mix of primary and secondary data. Primary data was gathered through a structured questionnaire administered to a sample size of 100 employees across various departments, while secondary data was sourced from HR manuals, annual reports, and reputable academic journals.Key areas of investigation include the impact of flexible work arrangements, mental health support systems, stress management workshops, and physical fitness incentives. Preliminary analysis suggests that while Inkonsul Technologies has established a robust framework for physical health, there remains a significant opportunity to enhance "psychological safety" and "digital detox" initiatives to combat burnout in the post-2023 hybrid work era.The findings of this project highlight that well-being is not merely a "perk" but a strategic HR intervention. Data analysis indicates a positive linear relationship between well-being satisfaction levels and the Net Promoter Score (eNPS) of the organization. The study concludes with actionable recommendations for the HR department, including the implementation of personalized wellness pathways and the integration of AI-driven sentiment analysis to proactively identify employee distress. This project serves as a blueprint for aligning organizational goals with human-centric values to foster a resilient and high-performing workforce.

Keywords : The concept of employee well-being has evolved from a secondary HR peripheral into a core strategic imperative that defines the resilience and sustainability of modern corporate entities.

Author : MONDI MANEESHA , MRS. D UMA RANI

Title : A STUDY ON EMPLOYEE WELL-BEING PROGRAMS

Volume/Issue : 2026;03(08)

Page No : 392-407

The success of a contemporary engineering enterprise is intrinsically linked to the agility and technical proficiency of its human capital. This research project, titled "A Study on Training Need Analysis (TNA) at Uniscient Engineering," is an analytical endeavor to evaluate the systematic process of identifying gaps between current employee competencies and the evolving demands of the global engineering landscape. In an era defined by Industry 4.0, automation, and complex project management, the traditional "one-size-fitsall" training approach is no longer viable. This study focuses on how Uniscient Engineering identifies these "competency voids" at the individual, departmental, and organizational levels. The primary objective of this study is to assess the existing training frameworks within the organization and determine their alignment with strategic business goals. Utilizing a descriptive research design, primary data was gathered from a sample of 100 employees across various hierarchies—including design engineers, project managers, and administrative staff—using structured questionnaires and interviews. The research examines several critical dimensions, including the transition toward Digital Twin technologies, the impact of soft-skills training on cross-functional collaboration, and the role of Agentic AI in personalizing learning pathways.The findings of the research indicate that while Uniscient Engineering possesses a robust technical training foundation, there is a distinct need for more proactive Strategic TNA. A significant portion of the workforce highlighted a gap in "Future-Skills," particularly in sustainable engineering practices and advanced data analytics. Furthermore, the study identifies a correlation between personalized training interventions and employee retention rates, suggesting that TNA is not merely a pedagogical tool but a vital component of the Employee Value Proposition (EVP). This project concludes with actionable recommendations, suggesting the implementation of a Continuous Competency Mapping system and the integration of real-time performance data into the training lifecycle. By bridging these identified gaps, Uniscient Engineering can ensure that its workforce remains at the forefront of engineering excellence, driving both operational efficiency and long-term organizational resilience.

Keywords : The concept of Training Need Analysis (TNA) has transitioned from a basic administrative checklist to a core strategic pillar within modern Human Resource Management, particularly in technical sectors like engineering.

Author : MOHAMMAD ASMABEGUM ,MR. P SAGAR KUMAR

Title : A STUDY ON TRAINING NEED ANALYSIS

Volume/Issue : 2026;03(08)

Page No : 408-422

The commodities’ markets are one of the fastest growing areas in the investment world. A commodity market is an exchange for buying and selling of commodities for future delivery. Commodity trading in India started much before it started in many other countries. However, years of foreign rule, draughts and periods of scarcity and government policies, caused the commodity trading in India to diminish. Commodity trading was however restarted in India recently, but a lot more developments and initiatives needs to be taken in this avenue. Investing in commodities offers protection against risk, diversified portfolio, trading on lower margin and safety. The study focuses on understanding the concepts and mechanism of commodity trading with special reference to crude Oil. It also aims to analyze the factors that influence the prices of oil and analyze the crude Oil trend in the commodity market.

Keywords : A commodity market: commodities is a market that exchanges the essential monetary segment as opposed to fabricated items, for example, cocoa, foods grown from the ground.

Author : MEDI SWAPNA ,DR MOHD ABDUL HAFEEZ

Title : A STUDY ON COMMODITY ANALYSIS

Volume/Issue : 2026;03(08)

Page No : 423-435

Workforce Management (WFM) has emerged as the strategic backbone of the modern retail industry, particularly within hypermarket formats where labor costs represent a significant portion of operational expenditure. This research project titled “A Study on Workforce Management at Smart Bazaar” aims to evaluate the systemic integration of human resource planning, labor scheduling, and employee productivity tracking within one of India’s most iconic retail chains. The study is situated in the transitional era of 2024–2026, analyzing how Smart bazaar—a pioneer in organized retail—navigates the complexities of workforce optimization amidst shifting ownership and digital transformation. The primary objective of this study is to investigate the effectiveness of existing WFM strategies in balancing labor supply with fluctuating customer footfall. The research utilizes a Descriptive Research Design, gathering primary data from a sample of 100 employees across various operational levels (Front-end sales, inventory management, and floor supervisors) at selected Smart bazaar outlets in the Hyderabad region. Data was collected through a structured questionnaire and analyzed using statistical tools including Percentage Analysis and Weighted Average Methods. Key findings of the research indicate that while Smart bazaar maintains a robust traditional framework for shift management, there is a significant need for the integration of Agentic AI and Automated Scheduling to reduce the "idle-time" of staff during non-peak hours. The study reveals that employee engagement is highly correlated with the flexibility of work schedules and the transparency of productivity-linked incentives. Furthermore, the research highlights the challenges of "Labor Shrinkage" and the high attrition rates typical of the retail sector, suggesting that a move toward a more "Employee-Centric WFM" model can enhance long-term retention.The study concludes with strategic recommendations for HR practitioners, emphasizing the adoption of Real-time Performance Dashboards and cross-functional training to create a "Fluid Workforce." By optimizing the deployment of human capital, Smart bazaar can significantly improve its Sales-per-Labor-Hour (SPLH) and enhance the overall customer shopping experience, ensuring sustainable competitive advantage in the highly volatile Indian retail landscape.

Keywords : Workforce Management (WFM) in the contemporary global business landscape has transitioned from a basic administrative function of scheduling and payroll into a sophisticated, data-driven strategic discipline that sits at the very heart of organizational efficiency.

Author : MATTEGAJAM CHANDANA , DR. M NARASIMHA

Title : A STUDY ON WORKFORCE MANAGEMENT

Volume/Issue : 2026;03(08)

Page No : 436-449

Terrain analysis has become an important application of computer vision in various fields such as autonomous navigation, robotics, agriculture, and environmental monitoring. Accurate identification of different terrain types helps intelligent systems make better decisions in realworld environments. This project presents the development of a Computer Visionbased Terrain Analysis System using Deep Learning techniques. The proposed system utilizes a Convolutional Neural Network (CNN) to classify terrain images into four categories: Grass Terrain, Marshy Terrain, Rocky Terrain, and Sandy Terrain. Image preprocessing techniques such as resizing and normalization are applied to improve classification performance. The CNN model is developed using TensorFlow and Keras, while OpenCV is used for image processing. A Flask-based web application provides a simple interface for uploading terrain images and displaying prediction results. The proposed system improves classification accuracy by automatically extracting important visual features without manual intervention. It provides an efficient, reliable, and user-friendly solution for automated terrain recognition and can be applied in autonomous vehicles, precision agriculture, robotic navigation, and environmental monitoring.

Keywords : Computer Vision, Deep Learning, Image Classification, Convolutional Neural Network (CNN), Terrain Analysis, TensorFlow, Flask.

Author : 1Mr. Kunchala Ramesh, 2Pamidi Sowmya,3Ranga Sonia,4P. Prasanna

Title : DEVELOPMENT OF COMPUTER VISION TECHNIQUES FOR TERRAIN ANALYSIS

Volume/Issue : 2026;03(08)

Page No : 450-457

Communication between hearing-impaired individuals and people who do not understand sign language can be difficult, leading to communication barriers in daily life. To overcome this issue, the Capturing Non-Manual Features of Indian Sign Language and Converting It into Text system uses Artificial Intelligence and Computer Vision to recognize both manual hand gestures and non-manual features such as facial expressions and head movements. The system is developed using Python, OpenCV, and deep learning techniques to capture and process sign language in real time. It identifies Indian Sign Language gestures and converts them into meaningful text with improved accuracy. The application provides a simple and user-friendly interface for capturing, processing, and displaying the translated text. The system is accurate, efficient, and easy to use, helping improve communication between hearing-impaired individuals and the general public while promoting accessibility and inclusion.

Keywords : Artificial Intelligence (AI), Indian Sign Language (ISL), Computer Vision, Deep Learning, Non-Manual Features, Gesture Recognition, Image Processing, Text Conversion.

Author : 1Mrs.V. L. N. S. Swapnika, 2Gudivada Akhila,3Ande Bhagya Raju

Title : CAPTURING NON-MANUAL FEATURES OF INDIAN SIGN LANGUAGE AND CONVERTING IT INTO TEXT

Volume/Issue : 2026;03(08)

Page No : 458-464

Medical plants widely used in traditional and modern medicine for treating various diseases. Accurate identification of medicinal plants and raw materials is essential for ensuring their correct usage and preventing harmful substitutions. This project presents an image processing and Machine learning-based system for identifying different medicinal plants and herbal raw materials leaf or plant images. The proposed system utilizes image processing, feature extraction, and a Convolution Neural Network(CNN) model to classify plant species accurately. Users can upload an image through a web application, and the train model predicts the plant name along with its scientific name, medicinal users, and confidence score. The developed system improves identification accuracy, reduces manual effort, and provides a fast and reliable solution for researchers, students, farmers, and health care professionals.

Keywords : Medicinal plants, Image Processing, Machine Learning, Deep Learning, Convolutional Neural Network(CNN), Medicinal Plant Identification, Herbal-Medicine plant, Computer Vision.

Author : 1Mr. N. Lakshmi Narayana,2N. Pavani,3N. Anil Kumar,4L. Sowmya

Title : IDENTIFICATION OF DIFFERENT MEDICAL PLANTS/RAW MATERIALS THROUGH IMAGE POCESSING USING MACHINE LEARNING ALGORITHM

Volume/Issue : 2026;03(08)

Page No : 465-470

This project presents an Artificial Intelligence (AI)-Based Drone Application for intelligent surveillance, monitoring, and real-time object detection. The system integrates drone technology with Artificial Intelligence, Computer Vision, and Deep Learning to perform autonomous aerial operations. The drone captures live video through an onboard camera and processes the captured images using AI algorithms to identify people, vehicles, obstacles, and suspicious activities in real time. Traditional drone systems require continuous human control and lack intelligent decision-making capabilities, making them less efficient in complex environments. The proposed system enables autonomous navigation, obstacle avoidance, real-time object detection, and accurate aerial monitoring. It improves operational efficiency, enhances safety, reduces human effort, and provides a costeffective solution for applications such as security surveillance, disaster management, agriculture, traffic monitoring, and environmental monitoring.

Keywords : Artificial Intelligence (AI), Drone Technology, Computer Vision, Deep Learning, Object Detection, Autonomous Navigation, Image Processing, Real-Time Monitoring, Machine Learning, Surveillance.

Author : 1Dr. G. Prasuna, 2Nakkala Gayatri, 3Myla Sowmya Sree, 4Katta Joel

Title : Artificial Intelligence-Based Drone Application for Intelligent Surveillance and Monitoring

Volume/Issue : 2026;03(08)

Page No : 471-475

This project presents an Visual question and answering with satellite image is an intelligent system developed to analyze satellite imagery and generate meaningful answers to user queries. The proposed system integrates image classification and a rule based keyword matching algorithm to improve the accuracy of question answering. It is implemented using python, flask, HTML, CSS, JavaScript, TensorFlow, SQLite, and matplotlib to provide a responsive web application. The uploaded satellite image is processed to identify its category, while the input question is analyzed to extract important keywords for answer predication. The system also provides graphical analysis and generates downloadable PDF reports for better interpretation of result. This approach offers a simple, efficient, and user-friendly solution for satellite image understanding and supports application in remote sensing, environmental monitoring, and geospatial analysis.

Keywords : Visual Question Answering (VQA), Satellite Image Analysis, Remote Sensing, Rule-Base Keyword Matching Algorithm, Image Classification, TensorFlow, Flask Framework, natural Language Processing (NLP), Geospatial Intelligence, PDF Report Generation.

Author : 1Dr. P. V. S. Sarma, 2Manchala Prasanna Lakshmi, 3Mekala Sharon Priya Dharshini, 4 Nakka Kiran Babu

Title : Visual Question and Answering with Satellite Image

Volume/Issue : 2026;03(08)

Page No : 476-482

Most schools and colleges still use manual attendance systems based on roll numbers, which consume time, increase teachers' workload, and allow proxy attendance. To overcome these issues, the Smart AI-Based Attendance and Engagement Monitoring System uses face recognition to automate the attendance process. The system is developed as a desktop application using Python, OpenCV, and the face_recognition library. It identifies registered users by matching their faces with stored records and automatically records attendance with the date and time in an Excel sheet. During registration, multiple face images are captured from different angles to improve recognition accuracy. The application provides separate interfaces for users and administrators to register students, manage face data, and record attendance. The system is simple, secure, accurate, and time-saving, making attendance management more efficient while allowing teachers to focus on education instead of manual attendance.

Keywords : Artificial Intelligence (AI), Face Recognition, Computer Vision, Deep Learning, Real-Time Detection, Image Processing, Face Authentication, Smart Attendance System.

Author : 1MRS. N. Sulakshna,2Asritha Pallapu,3Bole Sowmya,4Amarthaluri Pramod Kumar

Title : SMART AI-POWERED ATTENDANCE AND ENGAGEMENT MONITORING SYSTEM

Volume/Issue : 2026;03(08)

Page No : 483-488

The Conversational Image Recognition Chatbot is an intelligent webbased application designed to analyze uploaded images and provide accurate responses to user queries using Artificial Intelligence. Traditional image recognition systems generally identify objects but fail to support natural language interaction, making it difficult for users to obtain detailed contextual information about an image. To overcome this limitation, the proposed system integrates advanced vision-language capabilities that enable users to upload an image and ask questions in conversational language, receiving meaningful and context-aware responses. The system is developed using HTML, CSS, JavaScript, and Flask for the user interface and backend, while SQLite is used for user authentication and data management. Google Gemini VisionLanguage Model serves as the core AI engine for image understanding and natural language response generation. The system employs image preprocessing, visual feature extraction, and promptbased conversational reasoning to interpret image content and generate accurate answers. This application can be used in education, accessibility support, smart assistance, healthcare, retail, and content analysis, where users require quick and interactive understanding of visual information. By combining computer vision with conversational artificial intelligence, the proposed chatbot provides an efficient, user-friendly, and scalable solution for intelligent image analysis and human-computer interaction.

Keywords : Conversational Image Recognition, Artificial Intelligence, Computer Vision, Google Gemini, VisionLanguage Model(VLM), Image Understanding, Natural Language Processing(NLP), Flask Framework, Human-Computer Interaction.

Author : 1Dr. G. Prasuna, 2D. Mounika, 3G. Pujitha, 4G. Samuel Kiran, 5G. Aishwarya

Title : CONVERSATIONAL IMAGE RECOGNITION CHATBOT SYSTEM

Volume/Issue : 2026;03(08)

Page No : 489-496

Agriculture plays a vital role in ensuring food security and supporting economic development. However, predicting crop yield accurately is a challenging task due to variations in soil conditions, rainfall, temperature, humidity, and other environmental factors. Traditional farming methods mainly depend on farmers' experience and historical practices, which may not always provide reliable predictions. To address these challenges, the proposed AI-Based Crop Yield Prediction and Smart Farming system utilizes Artificial Intelligence (AI) and Machine Learning (ML) techniques to predict crop yield and provide smart farming recommendations. The system collects agricultural parameters such as soil type, rainfall, temperature, humidity, and crop information from the user and processes them using a trained machine learning model. Based on the analysis, it predicts the expected crop yield and suggests suitable farming practices, including crop selection, irrigation planning, fertilizer usage, and pest management. The application is developed using Python, Flask, HTML, CSS, and Machine Learning technologies, providing a simple and user-friendly web interface. The proposed system improves prediction accuracy, reduces manual effort, optimizes resource utilization, and supports sustainable farming practices. It serves as an effective decision-support tool for farmers, agricultural researchers, and organizations by enhancing productivity and promoting data-driven agriculture.

Keywords : Artificial Intelligence (AI), Machine Learning (ML), Crop Yield Prediction, Smart Farming, Precision Agriculture, Soil Analysis, Weather Prediction, Flask Framework, Sustainable Agriculture, Data Analytics.

Author : 1Mr. N. Lakshmi Narayana, 2Nakka Pavani, 3Rangisetty Sai Madhav, 4Pamidi Hanok

Title : AI – BASED CROP YEILD PREDICTION AND SMART FARMING

Volume/Issue : 2026;03(08)

Page No : 497-506

Artificial Intelligence (AI) has significantly transformed document processing by enabling automatic translation and summarization across multiple languages. The AI-Powered Multilingual Document Translation and Summarization System is designed to help users translate documents into different languages while generating concise summaries that preserve the original meaning and context. The system supports document upload in formats such as PDF, information, identifies the source language, translates the content into the user's preferred language, and produces a meaningful summary using advanced Natural Language Processing (NLP) techniques and Generative AI models. The application is developed using Python, Flask, HTML, CSS, JavaScript, and the Gemini API to provide an interactive and user-friendly web interface. Compared to tradition manual translation methods, the proposed system improves translation accuracy, reduces processing time, and enhances accessibility for multilingual users. It is useful in education, business, healthcare, research, and government sectors where quick understanding of multilingual documents is essential. The system provides an efficient, scalable, and intelligent solution for modern document translation and summarization needs.

Keywords : Artificial Intelligence (AI), Multilingual Translation, Document Summarization, Natural Language Processing (NLP), Gemini API, Flask, Machine Learning.

Author : 1Dr. Y. Chitti Babu, 2Pasumarthi Bhargavi, 3Pinjala Siva Kesava, 4PittuVimalaDevi

Title : AI - Powered Document Multilingual Translation and Summarization System

Volume/Issue : 2026;03(08)

Page No : 507-513

Research and Development of an Autonomous Precision Planting System Focused on Crop and Weed Classification Precision agriculture has become an essential approach to improving agricultural productivity while minimizing resource consumption and environmental impact. One of the major challenges in modern farming is the accurate identification of crops and weeds during the early stages of plant growth. This project presents the research and development of an autonomous precision planting system focused on crop and weed classification using a web-based application. The system is developed using Python Flask as the backend and HTML, CSS, and JavaScript as the frontend, providing an interactive and user-friendly interface for farmers and agricultural researchers. The proposed system allows users to upload plant images through the web application. The uploaded images are processed, and the system classifies them as either crop or weed. In the demonstration version, a rule-based prediction mechanism is implemented, while the architecture supports integration with deep learning models such as TensorFlow/Keras (.h5 model) for real-time image classification. User authentication is implemented using SQLite to provide secure registration and login functionality.

Keywords : Precision Agriculture, Crop Classification, Weed Detection, Autonomous Planting System, Flask Framework, Machine Learning, TensorFlow, Smart Farming.

Author : 1Mr. K. Kiran Kumar, 2Dusi UmaDevi,3Katta Mythili,4Kokkiligadda Jahnavi

Title : Research And Develop A Design on Automous Small Precision Focused Machine for Planting Crops or Weeding

Volume/Issue : 2026;03(08)

Page No : 514-520

The Video Metadata Generation and Classification project is a web-based application developed to automatically generate metadata and classify videos based on their content. With the rapid growth of video content, manually generating metadata has become a time-consuming process. To address this problem, the proposed system automates the process of video analysis using speech recognition and keywordbased classification techniques. Users can upload a video through a Flask-based web interface, where the uploaded video is first previewed. The system then extracts the audio using FFmpeg and converts the speech into text using Google Speech Recognition, which implements Automatic Speech Recognition (ASR). The extracted text is analyzed to generate relevant keywords and classify the video into predefined categories such as Sports, Food, Education, and General using a Keyword-Based Classification Algorithm. The system is developed using Python, Flask, HTML, CSS, FFmpeg, and the SpeechRecognition library. It provides a simple, efficient, and cost-effective solution for automated video organization and retrieval, making it suitable for educational platforms, digital libraries, media organizations, and multimedia content management systems.

Keywords : Video Metadata Generation, Video Classification, Automatic Speech Recognition (ASR), FFmpeg, Google Speech Recognition, Flask, KeywordBased Classification, Python.

Author : 1Dr. Y. Chitti Babu, 2Damisetty Bhagya Sri,3Madasani Meghana, 4 Immadisetty Mohana Lakshmi

Title : Video Metadata Generation & Classification

Volume/Issue : 2026;03(08)

Page No : 521-527

Runtime Remote Video Quality Assessment is a real-time video analysis system designed to evaluate the quality of video streams without requiring the original reference video. With the rapid growth of applications such as video conferencing, online education, telemedicine, live streaming, and remote surveillance, maintaining high video quality has become essential for ensuring a better Quality of Experience. However, factors such as network congestion, bandwidth limitations, packet loss, compression artifacts, and environmental conditions can significantly degrade video quality during transmission. The proposed RVQA system uses computer vision and machine learning techniques to analyze video quality automatically. The system accepts a video as input, extracts frames using OpenCV, preprocesses the frames, and computes important visual features such as brightness, contrast, sharpness, blur, and noise. These extracted features are then processed by a machine learning model to estimate the overall video quality and classify it into categories such as Excellent, Good, Fair, or Poor. A webbased interface developed using Flask allows users to upload videos, perform real-time quality analysis, and view the assessment results through graphs and quality metrics. The system is implemented using Python, Flask, OpenCV, NumPy, Matplotlib, and Scikit-learn, providing a lightweight, scalable, and user-friendly solution for runtime video quality monitoring. The proposed system helps detect quality degradation efficiently and supports applications including multimedia streaming, online learning, video conferencing, telemedicine, and intelligent surveillance. Overall, the Runtime Remote Video Quality Assessment system offers an effective approach for improving video quality monitoring and enhancing the overall user experience in modern multimedia communication environments.

Keywords : Runtime Remote Video Quality Assessment (RVQA), Video Quality Assessment (VQA), No-Reference Video Quality Assessment (NR-VQA), Computer Vision, Machine Learning, OpenCV, Real-Time Video Processing, Quality of Experience (QoE), Flask.

Author : 1Mr. Kunchala Ramesh, 2G. Sai Kiran, 3B. Lokesh, 4A. Rajesh Reddy

Title : RUNTIME TEMOTE VIDEO QUALITY ASSESSMENT

Volume/Issue : 2026;03(08)

Page No : 528-538

Industrial automation has become an essential component of modern manufacturing systems, where continuous equipment monitoring and rapid fault detection are critical for ensuring operational reliability, worker safety, and production efficiency. Unexpected equipment failures can lead to production downtime, increased maintenance costs, reduced product quality, and potential safety hazards. Conventional fault detection systems generally rely on periodic inspections or standalone monitoring devices, which often fail to identify faults at an early stage and provide limited remote monitoring capabilities. Recent advancements in Field Programmable Gate Arrays (FPGA), Internet of Things (IoT), embedded systems, and cloud computing have enabled the development of intelligent industrial monitoring systems capable of highspeed fault detection and real-time remote supervision. This project presents an FPGA-Based Industrial Fault Detection Using IoT, designed to continuously monitor industrial equipment and rapidly detect abnormal operating conditions. The proposed framework integrates an FPGA controller, temperature, vibration, current, voltage, and gas sensors, WiFi communication, IoT cloud platform, and intelligent fault analysis algorithms into a unified industrial monitoring system. The FPGA processes multiple sensor inputs simultaneously through parallel hardware architecture, enabling rapid fault identification with minimal processing delay. The monitored data are transmitted to the IoT cloud platform for real-time visualization, historical storage, and remote monitoring. Whenever abnormal operating conditions such as overheating, excessive vibration, abnormal current, voltage fluctuations, or gas leakage are detected, the system immediately generates warning alerts and notifies maintenance personnel through cloud-based communication. Experimental evaluation demonstrates accurate fault detection, high-speed FPGA processing, reliable IoT communication, low response time, and stable system performance under different industrial operating conditions. The proposed framework significantly improves industrial safety, minimizes equipment downtime, supports predictive maintenance, reduces maintenance costs, and contributes to the development of intelligent Industry 4.0 manufacturing systems.

Keywords : FPGA, Internet of Things (IoT), Industrial Fault Detection, Industry 4.0, Predictive Maintenance, Temperature Sensor, Vibration Sensor, Current Sensor, Cloud Monitoring, Industrial Automation.

Author : 1KOMMULA ANJALI, 2Mrs. V. TEJASWI, 3BALNAGAR BALAJI, 4BOBBILI DEVI AVINASH KARTHIKEYA, 5ETEKELA ROHITH

Title : AI-BASED INDUSTRIAL FAULT DETECTION AND IOT MONITORING SYSTEM USING FPGA

Volume/Issue : 2026;03(08)

Page No : 539-547

Driver drowsiness and fatigue are among the leading causes of road accidents, particularly during long-distance travel and night-time driving. In electric vehicles (EVs), continuous monitoring of the driver's alertness is essential to improve road safety and reduce the risk of accidents caused by delayed reactions or loss of concentration. Conventional monitoring systems mainly rely on manual observation or basic warning mechanisms, which are often unable to detect early signs of driver fatigue. Recent advancements in Artificial Intelligence (AI), Computer Vision, the Internet of Things (IoT), and embedded systems have enabled the development of intelligent driver monitoring systems capable of detecting drowsiness in real time. This project presents a Smart EV Vehicle Driver Monitoring System Using Eye Blink Detection with Email and ThingSpeak Alerts. The proposed framework employs a camera to continuously capture the driver's facial images during vehicle operation. The captured images undergo preprocessing operations such as face detection, eye localization, noise removal, and image normalization before being analysed using Artificial Intelligence and computer vision algorithms. Eye blink patterns and eye closure duration are continuously monitored to determine the driver's level of alertness. When prolonged eye closure or abnormal blinking behaviour indicating drowsiness is detected, the system immediately activates an audible alarm to alert the driver. Simultaneously, the detected event is uploaded to the ThingSpeak cloud platform for real-time monitoring and historical analysis. An automatic email notification containing the driver's status, event time, and alert information is also sent to authorized personnel or emergency contacts. Experimental evaluation demonstrates high eye blink detection accuracy, rapid response time, and reliable real-time monitoring under different lighting and driving conditions. The proposed intelligent framework enhances driver safety, reduces fatigue-related accidents, supports continuous remote monitoring, and contributes to the development of advanced safety systems for nextgeneration intelligent electric vehicles.

Keywords : Artificial Intelligence, Driver Drowsiness Detection, Eye Blink Detection, Electric Vehicle, Computer Vision, ThingSpeak, Email Alert, Internet of Things (IoT), Driver Monitoring System, Road Safety

Author : 1M SHIRIN MEHER , 2N. GANESH, 3VAISHNAVI TIWARI ,4K. JESHWANTH, 5G. ARUN KUMAR

Title : SMART DRIVER FATIGUE DETECTION SYSTEM USING EYE BLINK ANALYSIS WITH EMAIL AND THINGSPEAK NOTIFICATIONS

Volume/Issue : 2026;03(08)

Page No : 548-557

The rapid adoption of electric vehicles (EVs) has created a growing demand for efficient, safe, and intelligent charging technologies. Conventional plug-in charging systems often require manual intervention, are susceptible to connector wear, and may present safety concerns in harsh environmental conditions. Wireless Power Transfer (WPT) has emerged as an attractive alternative by enabling contactless energy transfer between the charging station and the electric vehicle. However, efficient wireless charging requires precise vehicle alignment, accurate vehicle detection, and intelligent control of the charging process to minimize power loss and maximize charging efficiency. Recent advancements in Artificial Intelligence (AI), computer vision, and sensor-based automation have enabled the development of smart wireless charging systems capable of automatically detecting vehicle position and initiating charging only when proper alignment is achieved. This project presents an Intelligent Wireless Power Transfer System for Electric Vehicles Using AI-Based Vehicle Detection. The proposed framework integrates cameras and proximity sensors with deep learning-based vehicle detection algorithms to accurately identify the presence and position of an electric vehicle above the charging pad. Once the vehicle is correctly aligned, the control system activates the wireless power transfer unit and continuously monitors charging efficiency, battery status, coil alignment, and energy transfer parameters. Real-time monitoring ensures safe operation by preventing unnecessary energy transmission when no vehicle is present or when alignment is inadequate. The developed intelligent system enhances charging efficiency, reduces power losses, improves user convenience, and increases operational safety through automated vehicle recognition and adaptive charging control. Experimental evaluation demonstrates high vehicle detection accuracy, reliable wireless charging performance, and efficient energy transfer under different operating conditions. The proposed AI-enabled framework supports the advancement of smart transportation infrastructure and contributes to the development of efficient, autonomous, and sustainable electric vehicle charging systems.

Keywords : Artificial Intelligence, Wireless Power Transfer, Electric Vehicles, AI-Based Vehicle Detection, Deep Learning, Computer Vision, Inductive Charging, Smart Charging System, Predictive Energy Management, Intelligent Transportation Systems.

Author : 1E. NAGARJUN, 2T. SOWMYA, 3P BHAVANI ,4D. YUVA RAJ, 5T. KARTHIK

Title : AI-BASED INTELLIGENT WIRELESS POWER TRANSFER SYSTEM FOR ELECTRIC VEHICLES USING VEHICLE DETECTION

Volume/Issue : 2026;03(08)

Page No : 558-566

Electrical maintenance personnel, particularly linemen, are exposed to significant risks while repairing or maintaining power distribution systems due to accidental energization of electrical circuits. Miscommunication between maintenance teams and control stations or unauthorized switching operations can result in severe injuries, electric shocks, and fatalities. Conventional circuit breaker systems mainly rely on manual switching mechanisms and often lack secure authentication methods to ensure that only authorized personnel can restore power. Recent advancements in the Internet of Things (IoT), embedded systems, wireless communication, and secure authentication techniques have enabled the development of intelligent electrical safety systems for power distribution networks. This project presents an IoT-Enabled OTP-Based Smart Circuit Breaker Control System for Lineman Safety Applications. The proposed framework integrates an embedded controller, IoT communication module, relay-based circuit breaker, cloud platform, and One-Time Password (OTP) authentication mechanism to provide secure and remote control of electrical power distribution. Before energizing the power line, the authorized operator must enter a valid OTP generated by the system. The embedded controller verifies the entered OTP, and only after successful authentication is the circuit breaker allowed to switch ON or OFF. Unauthorized switching attempts are rejected automatically, thereby preventing accidental energization during maintenance activities. The IoT platform enables real-time monitoring of breaker status, authentication logs, and switching operations from remote locations. Experimental evaluation demonstrates reliable OTP verification, secure remote communication, rapid switching response, and stable system performance under different operating conditions. The proposed intelligent safety framework significantly improves lineman protection, prevents unauthorized access to electrical systems, enhances operational security, reduces maintenance-related accidents, and supports the development of secure, intelligent, and IoTenabled smart power distribution networks.

Keywords : Internet of Things (IoT), Smart Circuit Breaker, One-Time Password (OTP), Lineman Safety, Embedded Systems, Relay Control, Electrical Safety, Remote Monitoring, Authentication System, Smart Grid.

Author : 1AFRIN , 2Mr.K. SURESH BABU, 3KURVA NAGARAJU, 4JEEJULA SAI KRISHNA

Title : IOT-BASED SMART CIRCUIT BREAKER CONTROL AND OTP AUTHENTICATION SYSTEM FOR LINEMAN SAFETY

Volume/Issue : 2026;03(08)

Page No : 567-576

The continuous growth of electrical power distribution networks has significantly increased the importance of protecting distribution transformers against electrical faults, overload conditions, and equipment failures. Distribution transformers play a critical role in supplying reliable electrical energy from substations to residential, commercial, and industrial consumers. Conventional transformer protection systems primarily rely on manual inspection and local protective devices, which often fail to provide real-time fault monitoring and precise fault localization. These limitations increase maintenance time, prolong power interruptions, reduce system reliability, and increase operational costs. Recent advancements in the Internet of Things (IoT), embedded systems, wireless communication, cloud computing, and smart sensors have enabled the development of intelligent transformer monitoring systems capable of continuously analysing transformer operating conditions and identifying faults in real time. This project presents an IoT Enabled Distribution Transformer Protection with Real-Time Fault Localization. The proposed framework integrates an ESP32/Arduino controller, voltage sensor, current sensor, temperature sensor, oil level sensor, fault detection module, GPS module, IoT communication module, cloud monitoring platform, and mobile application into a unified transformer protection system. The embedded controller continuously monitors transformer voltage, current, temperature, oil level, and fault conditions while determining the precise geographical location of the transformer using GPS. Whenever abnormal operating conditions such as overload, short circuit, overheating, low oil level, or overvoltage are detected, the system immediately isolates the fault, generates warning alerts, uploads transformer information to the cloud platform, and transmits the exact transformer location to maintenance personnel for rapid fault localization. Experimental evaluation demonstrates high fault detection accuracy, reliable sensor monitoring, stable wireless communication, accurate fault localization, low response time, and continuous remote monitoring under different operating conditions. The proposed framework significantly improves transformer protection, minimizes outage duration, reduces maintenance costs, enhances power distribution reliability, and provides a cost-effective solution for next-generation intelligent smart grid applications.

Keywords : Distribution Transformer, IoT, ESP32, Arduino, Transformer Protection, Fault Localization, GPS, Smart Grid, Cloud Monitoring, Voltage Sensor, Current Sensor, Temperature Sensor, Power Distribution System.

Author : 1PARAKALA KOTESH, 2Mrs.B.SRILEKHA, 3KOREPU SAI KIRAN, 4KALE RAMESH, 5CHALLA RAKESH

Title : IOT-BASED DISTRIBUTION TRANSFORMER PROTECTION AND REAL-TIME FAULT DETECTION SYSTEM

Volume/Issue : 2026;03(08)

Page No : 577-586