Journal of Science Engineering Technology and Management Science

The rapid advancement of wildlife monitoring and ecological research has increased the demand for intelligent systems capable of automatically identifying animal species using non-invasive techniques. Bioacoustic recordings, which capture animal vocalizations, provide a reliable and scalable alternative to traditional visual monitoring, particularly in dense forests and low-visibility environments. With the growing integration of machine learning and audio signal processing, automated analysis of animal sounds has emerged as a promising approach for biodiversity conservation and environmental surveillance. This research proposes an advanced bioacoustic species classification system using a fusion-based hybrid ensemble learning framework. The system processes raw audio recordings and converts them into meaningful feature representations through techniques such as Mel-Frequency Cepstral Coefficients (MFCC), chroma features, spectral contrast, Mel spectrogram, zero-crossing rate, and root mean square energy. These features effectively capture the temporal, spectral, and harmonic properties of animal sounds, enabling accurate species differentiation. Multiple machine learning models, including Nearest Centroid Classifier (NCC), Decision Tree Classifier (DTC), and Gradient Boosting Classifier (GBC), are implemented and evaluated. To address the limitations of individual models, a hybrid ensemble approach combining Support Vector Machine (SVM) and Light Gradient Boosting Machine (LGBM) using a soft voting mechanism is introduced. This approach aggregates probability outputs to improve prediction accuracy. Experimental results demonstrate that the proposed model significantly outperforms traditional methods in terms of accuracy, precision, recall, and F1- score. The system provides a robust, scalable, and efficient solution for real-time wildlife monitoring and ecological research.

Keywords : Bioacoustics, Animal Species Classification, Machine Learning, Feature Extraction, Ensemble Learning, Support Vector Machine (SVM), Light Gradient Boosting Machine (LGBM), Wildlife Monitoring.

Author : P Navya, Kasturi Kaveri, Kommuka Amulya, Orunganti Uday

Title : Fusion-Augmented Ensemble Learning for Intelligent Interpretation of Bioacoustic Signals in Wildlife Ecosystems

Volume/Issue : 2026;03(04)

Page No : 480-489

Recent advancements in artificial intelligence have significantly transformed modern defence systems by enhancing decision support through automated data analysis. The proposed system, AI-Driven Military Decision Support System Using Deep Learning and Tactical Image Intelligence (AIDMDSSUDLTII), addresses the growing need for rapid and accurate interpretation of large-scale military visual data. In modern warfare, massive volumes of images generated from drones, satellites, and reconnaissance systems require efficient processing for timely and strategic decisions. Traditional approaches relying on manual analysis and rule-based techniques were time-consuming, less scalable, and prone to inconsistencies in dynamic battlefield conditions, highlighting the need for an intelligent, data-driven solution. To overcome these challenges, the system integrates machine learning and deep learning models for automated classification of military assets. Baseline techniques such as Perceptron and Decision Tree are combined with advanced architectures like Deep Neural Networks (DNN) and a hybrid Convolutional Neural Network with Long Short-Term Memory (CNN-LSTM). This hybrid approach effectively captures both spatial features and sequential patterns in tactical images, enabling robust feature extraction and improved classification performance across multiple military categories. Additionally, the system is deployed through a graphical user interface supporting dataset management, preprocessing, model training, evaluation, and real-time prediction. By leveraging deep learning and tactical image intelligence, the framework enhances decision accuracy, reduces processing time, and improves operational efficiency, providing a scalable and effective solution for intelligent military decision-making in modern defence environments.

Keywords : Artificial intelligence, military decision support system, deep learning, tactical image intelligence, convolutional neural network–long short-term memory (CNN–LSTM), image classification, real-time prediction, operational efficiency.

Author : M. Hemanth, Mattegajam Rakesh, Mylapaka Vennela, Naini Gayathri, Sk Shahbaz

Title : AI-Driven Military Decision Support System Using Deep Learning and Tactical Image Intelligence

Volume/Issue : 2026;03(04)

Page No : 490-499

The rapid expansion of networked systems and digital communication has significantly increased the occurrence of cyber threats, making network traffic classification an essential component of modern security systems. The problem addressed in this work is the accurate detection and classification of network intrusions using structured traffic data, where both binary and multi-class classification are required for effective analysis. Traditional systems are primarily manual-based, relying on rule-driven inspection and human expertise to identify malicious activities, which makes them time-consuming, error-prone, and inefficient for large-scale and dynamic network environments. These systems suffer from limitations such as inability to handle high-dimensional data, delayed response to evolving attack patterns, and lack of scalability. These challenges highlight the need for an automated and intelligent classification approach capable of processing large volumes of network data efficiently. To address these issues, the proposed system introduces a hybrid classification framework integrating Adaptive Boosting (AB), Balanced Random Forest (BRF), Easy Ensemble Classifier (EEC), and a novel Quantum Supers parse Linear Integer Model (QSLIM). The system incorporates preprocessing, exploratory data analysis, model training, evaluation, and prediction within a unified Django-based architecture. The system performs classification on two target variables, namely label for binary classification of normal and attack traffic, and type for multi-class classification of different attack categories. The proposed model utilizes Quantum Auto Encoder (QAE) for enhanced feature transformation and Super sparse Linear Integer Model (SLIM) for efficient and interpretable classification. The significance of the system lies in its superior performance, achieving near-perfect accuracy values, outperforming all integrated models in both binary and multi-class classification tasks.

Keywords : Network Traffic Classification, Intrusion Detection Systems (IDS), Ensemble Learning, Quantum Machine Learning, Multi-class Classification, Cybersecurity Analytics

Author : Amgoth Ashok Kumar, Vynala Rakesh, Shaik Ghouse Pasha, Chandanala Ganapathi, Kallepelli Pranay

Title : QSLIM: A Quantum-Enhanced Super sparse Learning Framework for High-Precision Network Intrusion Classification

Volume/Issue : 2026;03(04)

Page No : 500-510

The global e-commerce market is expected to exceed USD 7 trillion by 2030, with over 80% of consumers depending on product reviews to guide their purchasing decisions. However, manual sentiment analysis of these reviews is neither scalable nor consistent, often resulting in inaccurate interpretations and delayed business insights. To address these challenges, this study proposes a robust Natural Language Processing (NLP) framework for automated sentiment analysis using a labeled product review dataset. The proposed methodology begins with comprehensive NLP preprocessing and Exploratory Data Analysis (EDA) to clean, normalize, and understand data distribution. For semantic representation, Sentence Bidirectional Encoder Representations from Transformers (SBERT) is employed to generate context-aware embeddings, capturing deeper linguistic relationships compared to traditional techniques. To handle class imbalance within sentiment categories, the Synthetic Minority Over-sampling Technique (SMOTE) is utilized to generate synthetic samples, ensuring balanced model training. Unlike conventional classifiers such as Random Forest Classifier (RFC), Light Gradient Boosting Machine (LGBM), and Extreme Gradient Boosting (XGBoost), the proposed framework incorporates Deep Neural Network (DNN)-based feature selection combined with a Boosted Rules Classifier (BRC). This hybrid approach enhances both model interpretability and predictive performance. The system classifies customer sentiments into three categories: Negative, Neutral, and Positive. Experimental results demonstrate improved classification accuracy and reduced bias, highlighting the effectiveness of the proposed model.

Keywords : Sentiment Analysis, Natural Language Processing (NLP), SBERT (Sentence-BERT), Boosted Rules Classifier (BRC), Deep Neural Network (DNN), SMOTE (Synthetic Minority Oversampling Technique).

Author : T. Srilekha, K. Sharmila Reddy, Gandhe Vamshi Krishna, Sripathi Manideep, Dhadi Ram Charan, Konreddy Shivamani

Title : SentimentX: Transformer-Driven Embedding Fusion with Rule-Boosted Intelligence for Product Opinion Mining

Volume/Issue : 2026;03(04)

Page No : 511-522

The rapid growth of digital platforms has led to the generation of large volumes of employee feedback data, making workforce satisfaction analysis an important area of study. Traditionally, organizations relied on manual surveys and basic statistical methods to evaluate employee satisfaction, which were often time-consuming and limited in capturing complex textual insights. With advancements in Natural Language Processing (NLP) and Machine Learning (ML), automated analysis has become feasible. However, existing approaches struggle with unstructured text, class imbalance, and multi-dimensional prediction tasks. The primary problem addressed in this study is the accurate prediction of workforce satisfaction factors such as work-life balance, skill development, salary and benefits, job security, career growth, and overall satisfaction from textual employee reviews. Traditional systems fail to process large-scale data efficiently and lack consistency in predictive performance. This creates the need for an intelligent framework capable of handling complex textual patterns and multi-label classification. To overcome these challenges, the proposed system integrates NLP preprocessing, transformer-based feature extraction using Google PaLM (Pathways Language Model – PaLM), and SMOTE (Synthetic Minority Over-sampling Technique). Multiple ML models including Quadratic Discriminant Analysis (QDA), Linear Discriminant Analysis (LDA), and Histogram-Based Gradient Boosting (HGB) are implemented and compared with the proposed Transformer-Guided Adaptive Model (TGAM). The results show that traditional models achieve moderate accuracy ranging from approximately 51% to 56%, while the proposed TGAM model achieves 100.00% accuracy across all target columns including work-life balance, skill development, salary and benefits, job security, career growth, and work satisfaction. This significant improvement highlights the effectiveness of the proposed approach in handling complex workforce data. The system also includes evaluation metrics and visualization techniques for better interpretability.

Keywords : Natural Language Processing (NLP), Machine Learning (ML), Transformer Models, Workforce Satisfaction Analysis, Multi-label Classification, SMOTE (Synthetic Minority Oversampling Technique)

Author : P. Praveen Kumar, Miriyala Trivedh, S. Sai Manikanta, Manchala Venkat, Sriramula Dinesh

Title : Semantic Embedding–Driven Multi-Output Learning Architecture for Fine-Grained Workforce Experience Modelling in Enterprise Systems

Volume/Issue : 2026;03(04)

Page No : 523-533

The growing dependence on cloud-based storage systems has introduced critical challenges in maintaining secure file sharing, reliable user authentication, and data confidentiality. As digital data continues to expand, protecting sensitive information from unauthorized access and cyber threats has become increasingly important. Traditional file-sharing systems typically rely on single-factor authentication and basic encryption techniques, which are often inadequate for modern security requirements. These approaches are vulnerable to data breaches, identity spoofing, and performance inefficiencies when processing large volumes of data. The primary problem addressed in this work is the design of a secure and efficient cloud-based file-sharing system that enhances authentication strength and encryption performance while ensuring controlled access to data. Existing systems lack multi-layer security mechanisms, biometric verification, and effective performance evaluation of cryptographic techniques, resulting in limited scalability and weaker protection. To overcome these limitations, the proposed system adopts a hybrid approach that integrates advanced cryptographic methods with multi-factor authentication. It utilizes Elliptic Curve Cryptography (ECC) for secure asymmetric encryption and ChaCha20 for fast and efficient symmetric encryption. The system is implemented using the Django framework with a My Structured Query Language (MySQL) database to manage user credentials, file metadata, and access control. Additionally, authentication is strengthened through password hashing combined with fingerprint-based verification. The system also compares the computational efficiency of ECC and ChaCha20, presenting the results through graphical analysis. The significance of this approach lies in its ability to provide enhanced security, efficient encryption, and scalable performance, making it a reliable solution for secure cloud-based file storage and sharing applications.

Keywords : Cloud Storage Security, Multi-Factor Authentication, Elliptic Curve Cryptography (ECC), ChaCha20 Encryption, Secure File Sharing, Data Confidentiality

Author : Bhaskar Babu Kuchanapally, Bollu Sairaj, Vemula Pavan Kalyan, Tholla Sampath*, Manikayala Vinay, Vanga Ankitha

Title : An Intelligent Privacy-First Anonymous Authentication System for Cloud Computing with Advanced Multi-Factor Safeguards

Volume/Issue : 2026;03(04)

Page No : 534-543

Unmanned Aerial Vehicles (UAVs) have gained significant importance in recent years due to their wide range of applications in areas such as surveillance, mapping, agriculture, disaster management, and logistics. Autonomous operation of UAVs requires reliable control mechanisms, efficient communication protocols, and safe testing environments. This project presents the design and implementation of an autonomous drone control system using DroneKit Python integrated with Mission Planner simulation. The proposed system utilizes DroneKit, a Python-based application programming interface, to implement autonomous flight logic including vehicle connection, arming, takeoff, waypoint navigation, telemetry monitoring, and safe landing. Communication between the control program and the simulated drone is achieved using the MAVLink protocol, which enables real-time bidirectional data exchange. The Software-In-The-Loop (SITL) simulation environment is employed to emulate the behavior of a real flight controller, while Mission Planner serves as the ground control station for mission planning, visualization, and telemetry analysis.The system was tested extensively in a simulation environment, and the results demonstrate successful autonomous mission execution with stable communication, accurate waypoint navigation, and reliable telemetry feedback. The use of simulation eliminates the risks and costs associated with physical drone testing, making the approach safe and suitable for academic and research applications. The project also provides a scalable framework that can be extended to realworld UAV deployment with minimal modifications. Overall, this project highlights the effectiveness of combining DroneKit Python and Mission Planner simulation for developing and validating autonomous UAV systems. The proposed solution offers a practical, costeffective, and industry-relevant platform for learning, experimentation, and future advancements in drone automation

Keywords : Significant,Surveillance,Communication,Environments,Demonstrate,Eliminat es,Automation.

Author : Y. Dilip Siva Nagendra Babu, S. Moulya Sri, Sk. Y. Hasina, P. Aiswarya, Y. Avinash, M. Durga Bhavani

Title : DRONEKIT PYTHON INTEGRATED WITH MISSION PLANNER SIMULATION

Volume/Issue : 2026;03(04)

Page No : 544-551

With the increasing adoption of digital education platforms, maintaining the security, integrity, and transparency of academic data have become a major challenge. Traditional centralized college management systems are vulnerable to data tampering, unauthorized access, and single point failures. To address these limitations, this project proposes a Blockchain Based Virtual College Network that leverages decentralized blockchain technology to securely manage academic operations.The system is implemented using Ethereum blockchain tools, including Ganache for creating a local blockchain environment, Remix IDE for developing and deploying smart contracts, and MetaMask for enabling secure user authentication and interaction with the blockchain network. Smart contracts written in Solidity define the rules for storing, updating, and accessing academic data, ensuring that all transactions are executed automatically and transparently without thirdparty intervention.The application provides role based dashboards for Admin, Teacher, and Student, ensuring controlled access and data privacy. Administrators manage user roles and system configuration s, teachers handle attendance, examination results, and academic materials, while students can securely view their academic records, fee details, notification s, and career guidance. Each operation performed by a user is recorded as a block chain transaction, making the data immutable and auditable.By storing academic records in a decentralized and tamperproof ledger, the proposed system eliminates the risk of data manipulation an d enhances trust among all stakeholders. The blockchain-base approach improves data reliability, prevents unauthorized modifications, and ensures long term record preservation. Overall, this project demonstrates how block chain technology can be effectively applied to build a secure, transparent, and trustworthy virtual college management system

Keywords : Security,Integrity,Transparency,Ethereum,Manipulation,Trustworthy

Author : S. Ishitha, T. Tejaswini, Sk. Chand Kousar, T. Venkata Meghana, T. Satish Kumar, Dr. M. Veera Kumar

Title : AN VIRTUAL BLOCKCHAIN TECHNOLOGY FOR DATA PROTECTION

Volume/Issue : 2026;03(04)

Page No : 552-558

The Automated Pest and Disease Detection System leverages advanced computer vision and deep learning to mitigate the limitations of manual agricultural monitoring, such as human error and delayed intervention. By integrating Convolutional Neural Networks (CNN) for precise disease classification and the YOLO (You Only Look Once) framework for real-time pest localization, the system transforms raw crop imagery into actionable diagnostic data. This automated approach facilitates early-stage detection and targeted pesticide application, significantly reducing economic losses while promoting environmental sustainability. Ultimately, the project bridges the gap between expert knowledge and field-level implementation, providing a scalable solution for modernizing global food security through data-driven, precision agriculture.

Keywords : Automated,Leverages,Mitigate,Facilitates,Sustainability,Modernizing,Agricul ture.

Author : T.Naga Pavan, K.Akhil Kumar, V.Dharani, Sk.Asma, Mrs. T. Tejaswi

Title : AUTOMATED PEST AND DISEASE DETECTION FOR AGRICULTURE

Volume/Issue : 2026;03(04)

Page No : 559-564

The rapid expansion of mobile technologies and widespread internet accessibility has significantly transformed the traditional retail ecosystem, particularly in the grocery sector. Conventional grocery shopping methods require customers to physically visit stores, resulting in time consumption, long waiting queues, limited product comparison, and inconvenience in managing daily household needs. To address these challenges, this project proposes the design and development of a Go Grocery App, a smart mobile-based online grocery ordering system that enables users to purchase grocery items conveniently, securely, and efficiently through a digital platform.The Go Grocery App provides a comprehensive solution by integrating essential features such as user registration and authentication, product browsing, cart management, online order placement, digital payment processing, and real-time order tracking. The system supports multiple user roles including customers, administrators, and delivery personnel, ensuring smooth coordination between order management, inventory control, and delivery operations. A centralized backend server manages application logic, data storage, and secure communication between system components. To enhance transaction transparency and data security, the proposed system incorporates blockchain concepts for recording order and payment transactions. Blockchain technology ensures immutability, prevents unauthorized data modification, and improves trust among users by maintaining a tamper-proof transaction ledger. Secure authentication mechanisms, encrypted data storage, and trusted payment gateway integration further strengthen system reliability and protect sensitive user information.The implementation of the Go Grocery App demonstrates significant improvements in shopping convenience, operational efficiency, and transaction security when compared to traditional grocery purchasing methods. Experimental results and user evaluations indicate faster order processing, reduced manual effort, improved data integrity, and high user satisfaction. The proposed system offers a scalable and adaptable framework that can be extended in the future with advanced technologies such as artificial intelligence–based product recommendations, multi-vendor marketplace support, and full-scale blockchain deployment. Overall, the Go Grocery App serves as an effective and modern solution for digital grocery management in today’s fast-paced lifestyle.

Keywords : Widespread,Ecosystem,Grocery,Significant,Demonstrates,Blockchain.

Author : L.Anusha, K.Narendra, G.Tirupathi, P.Pranathi, K.Ganesh, Mr. N. Prasanth

Title : GO GROCERY ANDRIOD APPLACATION

Volume/Issue : 2026;03(04)

Page No : 565-571

Grama Soil Express is a comprehensive digital agriculture application designed to empower farmers with real-time insights into soil health, crop suitability, and disease management. The application integrates soil testing, leaf disease detection, and intelligent recommendations through an intuitive mobile interface. By leveraging AI-based voice assistance, and cloud-based backend services, the system provides accurate soil parameter analysis, crop-specific fertilizer guidance, and alternative crop suggestions. The Soil Test module evaluates pH, Electrical Conductivity (EC), Nitrogen, Potassium, and Organic Carbon (%), generating actionable recommendations to optimize crop yield. The Leaf Scan module uses convolutional neural networks to detect plant diseases from captured leaf images, providing treatment suggestions and confidence levels. Results from both modules are consolidated in a digital Soil Health Card, which offers features such as PDF download and read-aloud voice output for accessibility. Grama Soil Express addresses the limitations of traditional soil testing methods and existing agricultural applications by combining precision, ease of use, and real-time decision support. Through backend integration with Firebase, real-time updates, and modular architecture, the app ensures scalability, security, and reliability. Performance and usability testing confirm that the application is robust and user-friendly, making it a practical tool for farmers seeking sustainable and efficient crop management.The project demonstrates the potential of digital agriculture and AI technologies in improving soil fertility, reducing crop loss, and supporting informed agricultural practices, paving the way for smart, technology-driven farming solutions.

Keywords : Agriculture,Suitability,Intelligent,Treatment,Performance,Demonstrates,Farmi ng.

Author : P. Bala Swathi Priya, D. Rajashekhar, G. Gayathr, K. Kartheek, P. Ravi Chandra, Dr. M. Veera Kumari

Title : A NOVEL GRAMA SOIL EXPRESS MOBILE APPLICATION

Volume/Issue : 2026;03(04)

Page No : 572-577

PathFindr is an advanced AI-driven academic and career guidance platform designed to address the growing challenges faced by students in managing academic workloads and preparing for professional opportunities. As identified in the seminar document (page 3 of ), students often struggle with inefficient study practices, lack of personalization, and limited access to career preparation tools. This research proposes an intelligent system that integrates machine learning, natural language processing, and adaptive learning mechanisms to automate note generation, provide personalized study recommendations, and simulate real-time mock interviews. The system leverages modern web technologies and AI APIs to deliver scalable and user-friendly solutions. Experimental results demonstrate improved student engagement, productivity, and performance compared to traditional systems. The proposed model contributes to the evolution of AI in education by offering a holistic, datadriven, and adaptive learning ecosystem.

Keywords :

Author : P. Ramu, Palreddy Dedeepya, Shamala Charitha Reddy, Bathula Sudeeksha

Title : PathFindr: AI-Powered Academic and Career Guidance System Using Adaptive Learning and Intelligent Automation

Volume/Issue : 2026;03(04)

Page No : 578-582

The construction industry is one of the major sources of global waste, and as such, it poses significant demands on our natural resources and landfill space. Construction and demolition waste (C&DW) accounts for 25-40% of total waste generated globally, yet current waste management practices are more focused on waste disposal rather than prevention. The current work proposes a new direction in the evolution from the linear "Take, Make, Dispose" concept to a digitalized circular economy concept. By adopting Building Information Modeling (BIM) and Internet of Things (IoT) technologies during the entire project life cycle, we propose a conceptual roadmap to reduce waste by approximately 15-35%. The current work is based on existing literature and introduces a new techno-managerial model to overcome existing financial and communication hurdles, providing a Smart Zero Waste vision for the modern infrastructure industry

Keywords : Zero Waste; Construction Waste Management (C&WM); Circular Economy (CE); Digital Twin (DT); Building Information Modeling (BIM); Internet of Things (IoT); Sustainable Infrastructure; Modular Construction; Techno-Managerial Framework.

Author : Dr. Hasan Çiçek, Ibrahim Nazeer Ahmed Khan

Title : Integrating Digital Twins and Zero-Waste Principles: A Techno-Managerial Framework for the Construction Project Lifecycle

Volume/Issue : 2026;03(04)

Page No : 583-593

The rapid adoption of electric vehicles (EVs) has intensified the need for accurate battery health monitoring and degradation prediction to ensure safety, reliability, and cost efficiency. Battery degradation is influenced by diverse operating characteristics such as driving patterns, charging behavior, environmental conditions, and load variations, which vary significantly across different EV users and vehicle types. Traditional battery management systems often rely on simplified models that fail to capture these complex, real-world operating differences. This work proposes a battery degradation prediction framework that explicitly considers variations in electric vehicle operating characteristics. By leveraging data-driven machine learning techniques and multifeature analysis, the proposed framework aims to accurately estimate battery health and predict future degradation trends. Such a system can support predictive maintenance, extend battery life, and enhance overall EV performance and user confidence.

Keywords : Electric Vehicles (EVs), Battery Degradation Prediction, Machine Learning, Lithium-Ion Batteries, State of Health (SOH), Predictive Modeling, Battery Management Systems (BMS), Data-Driven Analytics, Energy Storage Systems, Deep Learning.

Author : 1Peethala. Bindu Priya, 2B. Keerthana, 3K. Manikanta Kumar Naidu, 4G. Mohith Reddy, 5P. Dhanujaya Rao,6L.N.S.D. Prasanna

Title : AN INTELLIGENT MACHINE LEARNING FRAMEWORK FOR PREDICTING ELECTRIC VEHICLE BATTERY DEGRADATION

Volume/Issue : 2026;03(04)

Page No : 594-599

The increasing demand for efficient post-harvest management in agriculture has highlighted the need for advanced grain drying solutions, as nearly 30–40% of global agricultural produce is lost annually due to improper storage and drying techniques, while traditional drying methods can consume up to 25% more energy compared to optimized systems. These environments require adaptable systems capable of maintaining optimal drying conditions under varying climatic factors. Conventional grain drying methods are labor-intensive, time-consuming, and lack precise temperature control, often resulting in over-drying or under-drying, which degrades grain quality and increases post-harvest losses. Additionally, manual monitoring leads to inefficiencies, inconsistent results, and higher energy consumption. To address these challenges, the proposed Raspberry Pi Pico-controlled temperaturecontrolled harvester introduces an automated and intelligent grain drying system. The system integrates temperature sensors, a fan-based airflow mechanism, and a Raspberry Pi Pico microcontroller to continuously monitor and regulate the drying environment. Real-time data acquisition enables adaptive control of temperature levels, ensuring uniform and optimal drying conditions. The user interface allows farmers to set desired parameters, while the system autonomously adjusts operations based on environmental variations. This energy-efficient design minimizes resource utilization while improving drying accuracy and consistency. Finally, the proposed solution enhances grain quality, reduces post-harvest losses, and supports sustainable and smart agricultural practices through automation and precision control

Keywords : Agricultural Automation, Energy Efficiency, Grain Drying System, Post-Harvest Management, Precision Agriculture, Raspberry Pi Pico, Smart Farming, Temperature Control

Author : Tangerala Pradeep Kumar, Mandhapuri Roshini, Radarapu Rakesh, Guguloth Raju, Pakala Santhosh

Title : Smart Grain Drying System Using Raspberry Pi Pico with Automated Humidity Control and Temperature Regulation

Volume/Issue : 2026;03(04)

Page No : 600-606

The rising global demand for electricity and the need for efficient energy utilization have accelerated the adoption of smart metering technologies, with smart energy meter deployment expected to exceed 1 billion units worldwide and energy losses due to inefficient consumption and theft accounting for nearly 20–25% in developing regions. Traditional energy meters rely on manual readings and postpaid billing systems, which often lead to inaccurate billing, delayed monitoring, energy wastage, and electricity theft. Furthermore, conventional systems lack real-time feedback, remote accessibility, and prioritized load control, reducing efficiency and user awareness. To address these challenges, the proposed IoT-based smart prepaid energy meter with prioritized load switching utilizes the ESP32 microcontroller to enable an intelligent and automated energy management system. The system continuously monitors electricity consumption and transmits real-time data to a centralized IoT platform for remote access and analysis. It incorporates a prepaid billing mechanism where users can monitor their balance and receive alerts when consumption approaches predefined thresholds. A prioritized load switching feature ensures that critical loads remain operational while non-essential loads are automatically disconnected during low balance conditions. Remote control capabilities allow users and providers to manage loads efficiently, while automated alerts and additional charge mechanisms enhance billing transparency. This solution improves energy efficiency, reduces losses, promotes sustainable consumption, and supports the development of smart and reliable power distribution systems.

Keywords : Energy Monitoring, ESP32, Internet of Things, Load Management, Prepaid Energy Meter, Prioritized Load Switching, Smart Grid, Smart Metering, Threshold Alert System

Author : Appala Sravan Kumar, Paladugula Harika, Annakusa Rohith, Macharla Sidhardha, Punnam Rohith

Title : Smart Electricity Management System Using IoT with Prepaid Metering and Priority Based Load Switching

Volume/Issue : 2026;03(04)

Page No : 607-613

The rapid increase in vehicular traffic and urbanization has significantly raised concerns about road safety, with over 1.3 million fatalities reported annually due to traffic accidents and overspeeding contributing to nearly 30% of these incidents, while smart traffic enforcement systems are projected to grow at over 16% annually. Traditional traffic policing relies heavily on manual observation and intervention, which is prone to human error, delays, and corruption, while also lacking real-time tracking and automated penalty mechanisms. Furthermore, conventional systems do not provide seamless integration of identification, evidence collection, and instant notification, reducing their effectiveness in modern traffic management. To address these challenges, the proposed RFID-GSM Based Signal Jump E-Challan System with Auto Alert utilizes the ESP32-CAM to develop an intelligent and automated traffic enforcement solution. The system integrates IR sensors to measure vehicle speed by calculating travel time between fixed points, while RFID technology uniquely identifies each vehicle. When a violation such as overspeeding or signal jumping is detected, the ESP32-CAM captures an image as evidence, and the system automatically generates a digital echallan. A GSM module then sends the violation details and penalty notification directly to the registered mobile number of the vehicle owner. This IoT-enabled system ensures accurate, transparent, and real-time enforcement, reduces human intervention, minimizes corruption, and supports the development of efficient and scalable smart traffic management systems.

Keywords : Automatic Traffic Enforcement, E-Challan System, GSM Communication, Intelligent Transportation System, Smart City Infrastructure, Speed Detection, Traffic Violation Monitoring

Author : Kumati Durga Prasad, Keerthi Gowthami, Bommineni Sindhu, Madipoju Srianjun, Rampelli Rajesh

Title : IoT Based Smart Traffic Enforcement System Using RFID GSM and ESP32 CAM for Automated E Challan Generation

Volume/Issue : 2026;03(04)

Page No : 615-621

The increasing reliance on renewable energy has highlighted the importance of improving solar panel efficiency, as solar power installations are expected to exceed 3 terawatts globally by 2030 while efficiency losses of up to 15–25% occur due to high temperatures, dust accumulation, and suboptimal power extraction. Traditional solar systems operate without active monitoring or cooling mechanisms, leading to overheating, reduced efficiency, energy losses, and lack of real-time performance tracking. Furthermore, conventional setups lack remote control capabilities and intelligent power optimization, limiting their effectiveness under dynamic environmental conditions. To address these challenges, the proposed Solar Efficiency Improvement System utilizes the ESP32 microcontroller integrated with IoT technology to develop an intelligent solar management solution. The system employs temperature and voltage sensors to continuously monitor panel conditions, while a Maximum Power Point Tracking (MPPT) circuit ensures optimal energy extraction. A relay-controlled cooling mechanism, such as a humidifier or cooling unit, is automatically activated when temperature thresholds are exceeded, maintaining optimal operating conditions. The system provides real-time data visualization through an LCD display and enables remote monitoring and control via a web interface. This smart approach enhances solar panel efficiency, reduces energy losses, improves system reliability, and supports sustainable energy utilization through intelligent automation and remote accessibility.

Keywords : Energy Optimization, Internet of Things, Maximum Power Point Tracking, Remote Monitoring, Renewable Energy Systems, Smart Solar System, Voltage Monitoring, Web-Based Control

Author : Kandukuri Vishnu, Dayyala Manusha, Eslavath Lokesh, Mukkala Shashi Kumar, Bussa Shiva Sunhith

Title : Solar Efficiency System Using ESP32 with IoT Integration and Automated Temperature Based Cooling

Volume/Issue : 2026;03(04)

Page No : 622-629

The increasing need for worker safety in hazardous environments has driven the adoption of intelligent monitoring systems, with occupational accidents causing over 2.7 million deaths globally each year and industrial safety technologies growing at more than 15% annually. Additionally, realtime health monitoring and environmental sensing have become critical in reducing fatal risks in industries such as mining, construction, firefighting, and rescue operations. Traditional safety systems rely on manual supervision and periodic health checks, which are often insufficient in detecting sudden health deterioration, accidents, or environmental hazards. Furthermore, conventional systems lack continuous monitoring, wireless communication, and real-time alert mechanisms, resulting in delayed emergency response and increased risk to human life. To address these challenges, the proposed Zigbee Smart Safety Waist System utilizes the ESP32 microcontroller to develop an intelligent wearable safety solution. The system integrates DHT11 sensors for temperature and humidity monitoring, SpO2 sensors for blood oxygen and pulse rate measurement, and vibration sensors to detect falls or impacts. A GPS module provides real-time location tracking, while Zigbee communication enables reliable wireless data transmission to a remote monitoring station. At the receiver end, another ESP32 processes and displays the data, while a buzzer generates immediate alerts upon detecting abnormal conditions. IoT integration further allows remote monitoring and data logging through cloud platforms. This smart system enhances worker safety, enables rapid emergency response, and provides a scalable solution for real-time health and environmental monitoring in hazardous environments.

Keywords : DHT11 Sensor, ESP32, GPS Tracking, Hazard Monitoring, Internet of Things, SpO2 Monitoring, Wearable Safety System, Wireless Communication, Worker Safety, ZigBee Technology

Author : Challa Laxmi, Gottimukkula Usha, Gaddam Vishwas, Muppa Mayuri, Gandi Brahmam

Title : IoT Driven Smart Safety Waist System Using ESP32 with Zigbee Communication and Emergency Alert System

Volume/Issue : 2026;03(04)

Page No : 630-637

The increasing number of vehicle thefts, accidents, and unsafe driving behaviors has raised serious concerns regarding transportation safety, with global vehicle theft cases exceeding millions annually and road accidents causing over 1.3 million deaths each year, while smart vehicle security systems are projected to grow at over 15% annually. Additionally, factors such as unauthorized vehicle access, fire hazards, and drunk driving significantly contribute to vehicle-related risks, highlighting the need for intelligent monitoring solutions. Traditional vehicle security systems rely on basic alarms or manual monitoring, which are often ineffective in detecting multiple threats simultaneously and lack real-time communication and remote monitoring capabilities. Furthermore, conventional systems do not integrate multi-sensor data analysis or provide location tracking, reducing their effectiveness in modern transportation environments. To address these challenges, the proposed Zigbee Vehicle Security System utilizes the ESP32 microcontroller to develop an intelligent and comprehensive vehicle monitoring solution. The system integrates a vibration sensor to detect unauthorized movement or theft attempts, a fire sensor to identify potential fire hazards, and an alcohol sensor to monitor driver sobriety. A GPS module provides real-time vehicle location tracking, while sensor data is processed and displayed locally on an LCD. Zigbee wireless communication enables data transmission to a remote monitoring station, where another ESP32 processes the information and triggers alerts through a buzzer when abnormal conditions are detected. Additionally, IoT integration allows remote monitoring and data logging through cloud platforms. This smart system enhances vehicle security, prevents accidents, enables real-time tracking, and supports the development of intelligent and connected transportation systems.

Keywords : Alcohol Detection, ESP32, GPS Tracking, Internet of Things, Smart Vehicle Security, Vibration Sensor, Vehicle Monitoring, Wireless Communication, ZigBee Technology, Fire Detection

Author : Tangerala Pradeep Kumar, Damera Venkatesh, Bethi Prudhvika, G.Mani Kumar, Samala Vineeth

Title : Design of Smart Vehicle Security System Using ESP32 and Zigbee for Multi-Sensor Monitoring Applications

Volume/Issue : 2026;03(04)

Page No : 638-645

Agriculture is greatly affected by changing weather conditions, especially unexpected heavy rainfall, which can damage crops, wash away soil, and disturb normal plant growth. To address this problem, this project introduces an Automatic Rain Activated Shutter System that helps protect crops using a simple and responsive sensor-based approach. The system uses a rain sensor to detect rainfall and automatically activates motorized shutters or covers to protect the crop area. This immediate response reduces the need for manual work, prevents crop damage, and improves overall farming efficiency. The system is built using IoT-based components such as microcontrollers (like Arduino or ESP32), rain sensors, and actuators, making it affordable and easy to implement. It is especially useful for small-scale farmers and greenhouse environments where quick action is important. In the future, the system can be enhanced by adding weather prediction features and solar power support for better sustainability. LED indicators are also included to provide clear and simple information about the system’s working status, ensuring easy and the Smooth-operation.

Keywords :

Author : 1Mrs. K. Helini, 2K. Nandini, 3Ch. Vaishnavi, 4K. Sravanthi, 5N. Bharati Laxmi

Title : Automatic Rain Activated Shutter System For Crop protection

Volume/Issue : 2026;03(04)

Page No : 646-659

This paper presents the design and implementation of an ambulance-based Health Monitoring System for continuous tracking of patient vital parameters during transport. The system measures physiological signals such as heart rate and body temperature using biomedical sensors interfaced with a microcontroller unit. The acquired data is displayed locally on an onboard LCD screen for immediate observation by the caretaker inside the ambulance. In addition, the system hosts a dedicated web interface accessible through a unique device-specific URL, enabling real-time monitoring of patient data by hospital staff. This facilitates early preparation for medical intervention prior to the patient’s arrival. A threshold-based alert mechanism is incorporated, wherein abnormal vital readings trigger a buzzer within the ambulance to notify the caretaker. Furthermore, a Telegram-based notification system is implemented to provide continuous remote alerts to authorized personnel when abnormal conditions are detected. The proposed system offers a practical and cost-effective solution for pre-hospital patient monitoring, enhancing communication between ambulance staff and healthcare providers. The implementation demonstrates reliable real-time data transmission under standard network conditions, while limitations include dependency on network availability and sensor accuracy.

Keywords :

Author : 1Mrs.D.Kousari Kumari,2Ronagali Bhanu,3A.Udaya Prasanna,4Bakkam Ramya,5Manga Bhavana

Title : IOT Based Health Monitoring System For Real Time Analysis

Volume/Issue : 2026;03(04)

Page No : 664-671

The Smart Garage System using IoT Technology aims at providing improved security, convenience, and efficiency in the service centers of contemporary vehicles. In traditional service centers, the majority of the tasks such as vehicle tracking, customer identification, and service updates are performed manually. Such traditional practices are generally considered to be time-consuming and are likely to cause various types of errors and delays in the provision of service. In some cases, the absence of proper verification procedures can cause the wrong customer to receive the wrong vehicle, which can create serious security issues. In order to avoid the aforementioned problems and challenges, the proposed Smart Garage System uses the benefits of IoT Technology and automation to create a more intelligent service center environment. Once a vehicle enters the service center, smart cameras and sensors detect the important details of the customer and the vehicle.Upon entry of the vehicle to the service center, it recognizes all the relevant information regarding the customer and vehicle using smart camera technology. It utilizes facial recognition technology to identify the customer and records all this information in a database. Throughout the process of servicing the vehicle, all information is recorded digitally and in real-time, facilitating easier service operations for the staff and vehicle information for the customer. Upon delivery of the vehicle, it utilizes facial recognition technology to identify the customer before delivering the vehicle

Keywords :

Author : 1Mrs.K.SandhyaRani,2B. Sathvika Reddy,3R.Keerthika,4S. Harshitha,5O.Nagasri

Title : Smart Garage

Volume/Issue : 2026;03(04)

Page No : 672-677

The rapid advancement of technology has significantly transformed Human Resource (HR) management, leading to the widespread adoption of automation in HR processes. This study examines the impact of HR automation on efficiency and accuracy within organizations. The primary objective is to analyse how automated systems influence key HR functions such as recruitment, payroll processing, employee data management, and performance evaluation. The study also identifies challenges associated with implementation and explores strategies to enhance the effectiveness of automation. A descriptive and analytical research design is adopted, using both primary and secondary data. Primary data is collected from a sample of 200 respondents through structured questionnaires, while secondary data is sourced from journals, books, and online publications. Statistical tools such as percentage analysis and mean scores are used to interpret the data. The findings reveal that HR automation significantly improves operational efficiency by reducing manual workload and processing time. It also enhances accuracy by minimizing human errors in critical functions like payroll and record management. However, the study also highlights challenges such as employee resistance, lack of technical expertise, and concerns related to data security. Despite these limitations, automation enables HR professionals to focus on strategic activities, improving overall organizational performance. The study concludes that a balanced approach combining automation with human judgment is essential for achieving optimal results. Overall, this research emphasizes the importance of HR automation as a strategic tool for enhancing efficiency, accuracy, and productivity. It provides valuable insights for organizations planning to implement or improve automated HR systems and suggests directions for future research in this evolving field.

Keywords : automation, operational, resistance, balanced, accuracy, productivity

Author : Ms.JAYA GAYATHRI

Title : A STUDY ON AUTOMATION IN HR PROCESSES AND ITS IMPACT ON EFFICIENCY AND ACCURACY

Volume/Issue : 2026;03(04)

Page No : 678-689

The rapid growth in patient population and increasing demand for accessible healthcare services have exposed the limitations of traditional hospital management systems, which rely heavily on manual appointment scheduling, fragmented service delivery, and disconnected healthcare modules. To address these challenges, this paper presents An Intelligent Smart Healthcare Management and Appointment Booking Platform for Integrated Telemedicine, Laboratory Testing, Blood Donation, and Patient Assistance, a unified web-based healthcare solution designed to digitalize and streamline essential healthcare operations through a centralized platform. The proposed system integrates multiple healthcare services including real-time doctor appointment booking, specialty-based physician discovery, video consultation scheduling, laboratory test booking with home sample collection, blood donor registration and search, and an intelligent rule-based health chatbot for instant patient assistance. The platform employs role-based authentication, dynamic doctor availability management, calendarbased appointment scheduling, secure patient dashboards, and real-time healthcare service coordination to enhance operational efficiency and patient convenience. Developed using Django, MySQL, HTML, CSS, JavaScript, and Bootstrap, the system follows a modular three-tier architecture to ensure scalability, maintainability, and secure data handling. Experimental implementation results demonstrate that the proposed platform significantly reduces appointment booking complexity, improves healthcare accessibility, enhances user experience, and provides an integrated ecosystem for modern digital healthcare delivery. The system offers a practical and scalable foundation for next-generation smart healthcare environments

Keywords :

Author : P. Jaya Venkat1, P. Bhanu Prakash2, V. Naga Sairam Praveen Teja3, B. Pavan Akhil4, J. Gayatri5

Title : SMART HEALTHCARE MANAGEMENT AND APPOINTMENT BOOKING SYSTEM

Volume/Issue : 2026;03(04)

Page No : 678 - 687