Animal Detection In Farmlands Using Artificial Intelligence And IoT: A Case Study Of Thalavady Region, Erode District
Authors: Ms.B.Primila
Abstract: Agriculture remains the backbone of the Indian economy, providing livelihood for a large portion of the population. However, farmers living near forest boundaries frequently experience severe crop losses due to wildlife intrusion. In regions such as Thalavady in the Erode district of Tamil Nadu, animals including elephants, wild boars, deer, monkeys, and cattle often enter agricultural lands and destroy crops. Traditional crop protection methods such as manual monitoring, fencing, and scare devices are inefficient and require continuous human effort. This research proposes an intelligent animal detection system based on Artificial Intelligence (AI), computer vision, and Internet of Things (IoT) technologies to monitor farmland and detect wildlife intrusion in real time. The system utilizes camera modules and edge computing devices to process images using deep learning algorithms such as Convolutional Neural Networks (CNN) and YOLO object detection models. When animals are detected, alerts are sent to farmers through mobile notifications, and deterrent mechanisms such as sound alarms and lights are activated. The proposed system aims to reduce crop damage, enhance farmland security, and support coexistence between agriculture and wildlife. Experimental results suggest that AI-based detection systems can achieve high accuracy and significantly reduce farmer workload.
CyberSentinel: Fake Product Review Detection Using Machine Learning
Authors: V. Latha Sivasankari, Pratheep Kumar V, Preethika G, Pravin B
Abstract: Online marketplaces increasingly suffer from deceptive product reviews that manipulate customer perception and distort purchasing decisions. Traditional rule-based and manual moderation approaches struggle to detect sophisticated opinion spam, especially as review volumes grow exponentially across e-commerce platforms. The proposed system, Fake Product Review Detection Using Machine Learning, introduces an automated text analytics pipeline for identifying deceptive reviews using supervised learning techniques. The system processes raw review text through data preprocessing stages including tokenization, stop-word removal, normalization, and stemming, followed by feature extraction using TF-IDF vectorization. Multiple classification algorithms such as Logistic Regression, Naïve Bayes, and Support Vector Machine (SVM) are evaluated to determine optimal performance. A trained model is integrated into a Flask-based web application that enables real-time review classification as Fake or Genuine. The system architecture ensures seamless interaction between preprocessing, feature engineering, model inference, and user interface components. Performance evaluation conducted on a labeled dataset demonstrates an accuracy of 85%, with balanced precision and recall values, confirming reliable detection capability. The modular Python-based implementation ensures scalability, maintainability, and ease of deployment on standard computing environments. This approach enhances trustworthiness in online review ecosystems by providing an efficient, intelligent, and automated fake review detection solution.
The Integration Of 5MW Solar Power Into Port Harcourt Town Using Unified Power Flow Controller
Authors: Tombari Dubon, Hachimenum Nyebuchi Amadi, Onyebuchi Nelson Igbogidi, Richeal Chinaeche Ijeoma
Abstract: This study investigates the integration of a 5MW solar power system into the Elekahia Housing Estate grid to address challenges such as renewable energy intermittency, voltage instability, and transmission losses. A Particle Swarm Optimization technique was employed to optimally tune the Unified Power Flow Controller, while Flexible AC Transmission System devices were used to provide dynamic voltage regulation and impedance control. Energy storage systems were incorporated to mitigate renewable power fluctuations and support peak demand. Simulation results show that the inclusion of energy storage increases total grid output to a peak of 8.9MW, with storage contributing between 0.45MW and 1.8MW, thereby smoothing the demand curve and supporting peak loads between 18:00 and 21:00 hours. The State of Charge (SOC) analysis indicates effective battery management, with SOC rising to about 60% during off-peak hours and dropping to approximately 45% during high-demand periods. The integration of the 5MW solar generation further enhances system capacity, enabling the network to meet a demand of 7.9MW during evening peaks, compared to the original 4MW capacity. Voltage and current fluctuations observed in the absence of control devices were significantly reduced with the implementation of the optimized UPFC. The PSO-optimized UPFC demonstrated superior voltage regulation, reduced current peaks, and improved power flow stability compared to the conventional UPFC. Overall, the combined integration of renewable energy, energy storage, and advanced control technologies significantly enhances grid stability, operational efficiency, and reliability. The findings provide strong evidence that optimized FACTS control and energy storage systems can effectively support high-penetration solar power integration, reduce transmission losses, and improve voltage stability in urban distribution networks. The study recommends policy adoption and grid modernization strategies that incorporate PSO-optimized UPFC, energy storage systems, edge computing, and quantum-enhanced optimization to support sustainable and resilient renewable energy deployment.
DOI: https://doi.org/10.5281/zenodo.18950585
Environmental And Social Impacts Of Wind Power: A Review
Authors: Madhu Rani
Abstract: The rapid increase in global energy demand caused by population growth, industrialization, and technological advancement has intensified the exploitation of fossil fuel resources such as coal, oil, and natural gas. These conventional energy sources contribute significantly to environmental degradation, including air pollution and climate change. Consequently, renewable energy sources have gained considerable attention as sustainable alternatives. Wind power is one of the most widely adopted renewable energy technologies due to its ability to generate electricity without emitting greenhouse gases during operation. However, despite its environmental advantages, wind energy development also presents certain environmental and social challenges. This research paper examines the environmental benefits of wind power, explores its ecological impacts, and analyzes its social implications. The study highlights both the positive and negative aspects of wind energy and emphasizes the importance of careful planning, environmental assessments, and community engagement to ensure sustainable wind energy development.
Paper Evaluation And Grading System Using Artificial Intelligence
Authors: Ganga Sruthi Sai, V. James Prabhakar, Leela Venkat Sai, M. Prasad
Abstract: The quick increase in schools and big exams has made grading papers by hand more difficult. Old ways of grading depend a lot on people, which makes the process slow, not always fair, and can be affected by things like tiredness or personal opinions. While machines work well for multiple-choice questions, grading longer, written answers is still hard because understanding language isn't easy for computers. This paper suggests a smart, automated system that uses AI, OCR, NLP, and machine learning. It turns handwritten or printed tests into text that computers can read, checks multiple-choice answers by matching them to the correct answers, and evaluates written responses by looking at how similar they are to the right answers using machine learning. The system also uses explainable AI to make sure the grading is clear and fair. Tests show that this system saves time, makes grading more consistent, and is as accurate as humans. It offers a better, fairer, and more efficient way to grade exams for the future.
DOI:
Blockchain Based Water Management System Using IOT Sensors
Authors: N.Akshaya Reddy, G.Bala Ruthik Raja Reddy, K.Nithya Sri, Shaik Inthiyaz
Abstract: This research introduces a Blockchain-Based Water Management System designed to boost transparency, efficiency, and trust in how water is distributed and monitored. The system uses IoT-based water sensors to gather real-time information on how much water is used, how much is flowing, and whether there are leaks. This data is securely stored on a blockchain network. Smart contracts are used to automatically track water use, handle billing, and control access, making sure the data can't be changed or tampered with. A decentralized ledger means we don’t rely on a single authority, which stops people from altering data—this ensures a fair share of water for everyone involved. A web-based dashboard gives authorities and consumers real-time data, helping them make better decisions and save water. Testing shows data is sent securely, transactions are validated reliably, and there's more transparency than traditional systems. This system has strong potential for managing water resources sustainably in smart cities and rural areas.
A Blockchain-Based Decentralized Exam System For Safely Sharing Test Papers
Authors: Bandi Sai Sathwik, Dhanvanth Rahul Nayak, Masham Sanjay, Pagadala Anurag Kubera
Abstract: The use of digital tools in education exams has brought up new issues like keeping exams secure, fair, and honest. Traditional systems where everything is controlled from one place are easy targets for problems like leaking exam papers, letting in the wrong people, fake identities, and changing results. This paper introduces a new platform for exams that uses blockchain, deep learning, and biometric methods to solve these problems. Blockchain helps keep exam papers safe from changes, manages exam data without a single point of failure, and makes the exam process open and clear through smart contracts. The system also uses deep learning to create exam papers, watch over exams, and grade them. Biometric checks are used to stop people from pretending to be someone else or getting in without permission. Testing shows this system works well in removing single points of failure and reducing the need for human help. It is a secure and reliable way to handle digital exams in education.
A Centralized Cloud Security Storage System Using Blockchain Technique
Authors: K.A.S.L.U. Maheswari, Gugulothu Mythili, Jitta Rithika Reddy, Kolipaka Vineeth Nihal
Abstract: This study introduces a Blockchain-Based Zero Trust Network Access (ZTNA) solution that is designed to solve security problems caused by the centralised design of cloud storage systems, like data leaks, unauthorised access, and reliance on third-party providers. It uses blockchain, specifically Ethereum, along with the Zero Trust approach of "never trust, always verify" to create a secure, transparent, and unchangeable access control system. Smart contracts written in Solidity automate authentication, permission checks, and access validation, while AES encryption ensures strong protection for sensitive information in the cloud. The system sorts files into public and private groups based on user roles, and all access requests, permission changes, and activity logs are permanently stored on the blockchain, making it easier to keep track of who did what and when. The system’s lack of central control reduces the risk of failures, increases dependability, and builds confidence among users. The system is meant to be scalable, work with mixed cloud setups, and could be linked to future security tools like advanced threat detection systems. In general, this solution offers a secure, checkable, and reliable platform for managing valuable digital assets in today’s environment.
Perceiving The Fake Profiles & Botnets Using GNNs
Authors: Akkala Shivani Reddy, Janardhan Sreedharan, Veldi Karunakar, Erukali Shiva Kumar, Kommu Sony
Abstract: India's 600+ million social media users face unprecedented threats from sophisticated fake profiles and coordinated botnets that undermine platform integrity, spread disinformation, and influence elections. Traditional machine learning approaches relying on isolated account features fail to capture complex relational patterns and coordinated behaviors characteristic of modern botnets. This research proposes a novel Graph Neural Network (GNN) framework that models social networks as G=(V,E) graphs, where nodes represent user profiles with rich behavioral features and weighted edges capture interaction patterns. The architecture combines Graph Convolutional Networks (GCN) for neighborhood aggregation with Graph Attention Networks (GAT) for dynamic relationship weighting, enabling hierarchical feature learning across three GNN layers. Trained on combined TwiBot-22, Cresci-2015, and India-specific datasets, the model achieves state-of-the-art performance: 96.3% accuracy, 95.7% precision, 96.8% recall, and 96.2% F1-score, outperforming SVM (82.1%), Random Forest (85.3%), and other baselines by 11-18%. Key innovations include multi-scale graph embeddings capturing both individual account anomalies and bot cluster topologies, temporal interaction modeling, and real-time deployment as a scalable web application (<500ms inference/profile). Feature importance analysis reveals follower-following ratios, clustering coefficients, and posting variance as strongest discriminators. Successfully detecting a 47-account botnet with 95.7% recall, the framework addresses India's unique multilingual, high-density social ecosystem challenges. This GNN-based solution provides social media platforms with production-ready tools for maintaining authenticity, combating misinformation, and ensuring digital trust at national scale.
Insects As Bio Indicators Of Environmental Health: A Review
Authors: Dr.S.Swetha, CH.Ramya
Abstract: Insects are among the most diverse and abundant organisms on Earth and play essential roles in ecosystem functioning. Due to their sensitivity to environmental changes, short life cycles, and wide ecological distribution, insects are increasingly recognized as effective bioindicators of environmental health. Changes in insect diversity, abundance, behavior, and community composition reflect alterations in habitat quality, pollution levels, climate change, and land-use practices. This review examines the role of insects as bioindicators, highlights major insect groups used in environmental monitoring, discusses methodologies and applications, and outlines current challenges and future perspectives in sustainable environmental assessment.
DOI: https://doi.org/10.5281/zenodo.18954970
NEXTGEN: College Voting System
Authors: Kaustubh Nitin Salunke, Vinayak Amol Shewale, Anurag Sanjay Shigwan, Omkar Vinod Tate
Abstract: The escalating demand for transparent, tamper-proof, and efficient electoral processes in educational institutions necessitates a modern digital alternative to conventional paper-based voting. This paper presents NEXTGEN: College Voting System, a secure, fully web-based election management platform designed specifically for college-level institutional elections. The system is architected on a three-tier client-server model employing Java Servlets and JavaServer Pages (JSP) for backend processing, HTML5/CSS3 with Bootstrap 5 for the frontend, MySQL 8.0+ as the relational database engine, Apache Tomcat 11 as the servlet container, and the Jakarta Mail API for OTP-based Two-Factor Authentication (2FA). The platform features two primary role-based modules: an Admin Module offering complete election lifecycle control including student registration management, candidate management, election activation/deactivation/reset, and real-time result monitoring; and a Student Module providing secure registration, OTP-verified login, position-wise vote casting, and OTP-based password recovery. Security is enforced through SHA-256 password hashing, session management, role-based access control, dual-layer duplicate vote prevention (application-layer logic and database UNIQUE constraints), and time-bound OTP verification (5-minute validity). Testing validated 100% vote-count accuracy, 100% duplicate vote rejection, and OTP delivery within 5–10 seconds. The system eliminates manual counting errors, drastically reduces administrative overhead, and enables instant, verifiable election results. Future directions include biometric authentication, blockchain-based vote immutability, SMS-OTP support, and cloud deployment.
Machine Learning-Based Cellular Traffic Prediction Using Data Reduction Techniques
Authors: Dr G Rama Subba Reddy, Vaddi Obulesu, Ajay Gujjari, pattupogula Lakshmikala, Vamshi Nalapalli
Abstract: Estimating and analyzing traffic patterns is essential for managing Quality of Service (QoS) metrics in cellular networks. Cellular network planners often employ various approaches to predict network traffic. However, existing algorithms rely on large datasets, leading to significant time complexity and resource demands. To address this issue, we introduce a novel algorithm, AML-CTP (Adaptive Machine Learning-based Cellular Traffic Prediction), which is trained on a small, accurate dataset to enhance prediction accuracy while reducing complexity. Our methodology includes data normalization using the Min-Max Scaler, feature selection via the Select-K-Best algorithm, and dimensionality reduction through PCA. We apply density-based clustering techniques (DBSCAN and Kernel Density) to identify high-similarity clusters for training. We evaluate several machine learning algorithms, including Support Vector Machine (SVM), Linear Regression, Decision Tree, Light Gradient Boosting, and XGBoost, using a Cellular LTE dataset from an Egyptian company. The results demonstrate that the Decision Tree algorithm achieved the highest R² score of 96%, followed by the extension XGBoost model, which reached a remarkable R² score of 98%, indicating its superior performance in cellular traffic prediction.
DOI:
The Role Of Telemedicine In Post-Pandemic Healthcare
Authors: Sheeja S, Selvasurya S, G Surriya Vel
Abstract: The COVID-19 crisis reshaped healthcare systems across the world in ways never seen before. As hospitals struggled to manage rising infection rates, traditional face-to-face consultations quickly became risky. In response, healthcare providers rapidly turned to telemedicine as a safer and more practical alternative. What initially began as an emergency response soon demonstrated long-term value. Virtual healthcare services have since proven effective in expanding access, improving chronic disease management, reducing operational costs, and maintaining continuity of care. This paper examines how telemedicine evolved during the pandemic, the technologies that support it, the benefits and limitations it presents, and its growing importance in shaping the future of global healthcare delivery.
DOI:
Hybrid Renewable Energy Generation Using Piezoelectric And Solar
Authors: Mr. Sahil Mahale, Mr. Shivam Gangurde, Mr. Pankaj Ahire, Mr. Harshal Kushare, Mr. A.S.Parkhe
Abstract: The increasing demand for electrical energy and the rapid depletion of conventional energy resources have made renewable energy sources an important alternative for sustainable power generation. This paper presents a hybrid renewable energy generation system that utilizes both solar energy and piezoelectric energy for electricity generation. Solar panels convert sunlight into electrical energy using photovoltaic cells, while piezoelectric sensors generate electrical energy when mechanical pressure such as human footsteps is applied. By combining these two energy sources, the efficiency and reliability of energy generation can be improved. In this system, solar energy is used as the primary source of power during daytime, while piezoelectric sensors generate electricity from mechanical pressure created by human movement in crowded areas. The electrical energy generated from both sources is stored in a rechargeable battery and can be used to power small electrical loads such as LED lighting systems, sensors, or low-power electronic devices. This hybrid renewable energy system can be implemented in public places such as railway stations, bus stands, shopping malls, and footpaths where human movement is frequent. The system helps in utilizing wasted mechanical energy and natural solar energy effectively. The proposed system contributes to energy conservation, reduces dependence on conventional power sources, and promotes the use of clean and sustainable energy technologies.
Review Of Rural Consumer Satisfaction Towards Digital Marketing In India: A Secondary Data Perspective”
Authors: Ms. Shristi Singh
Abstract: The increasing penetration of the internet and the widespread use of smartphones have transformed the way consumers obtain information and purchase products. In the modern digital environment, marketing activities have shifted from traditional methods to digital platforms such as social media, search engines, websites, and e-commerce portals. These platforms allow companies to communicate with customers quickly and effectively while promoting their products and services. With the expansion of digital connectivity in India, the influence of digital marketing is no longer limited to urban regions. Rural areas are also experiencing rapid digital adoption. Improved internet infrastructure and affordable smartphones have enabled rural consumers to access online information, compare products, and engage in digital transactions. The present study explores the satisfaction level of rural consumers toward digital marketing practices. The research relies on secondary data sources such as academic journals, books, research reports, and online publications related to rural marketing and digital consumer behaviour. The findings indicate that digital marketing enhances rural consumers’ access to product information, increases product availability, and offers convenient purchasing options. However, challenges such as limited digital literacy, weak network connectivity, and concerns about online security still influence consumer satisfaction in rural areas.
DOI: https://doi.org/10.5281/zenodo.18979257
AI-Driven Livestock Health Monitoring and Remote Veterinary Triage
Authors: Pragadeeshwaran R, Mohanapriya D, Dr.S.Sheeja
Abstract: Conventional animal health management practices involve extensive manual observation and documentation, resulting in late disease detection and ineffective veterinary care, especially in rural areas. To fill this pressing need, this paper proposes a comprehensive AI-assisted web application for proactive animal health monitoring. The proposed system employs a strong three-tier architecture, combining a React.js front end, a Node.js API gateway, and Supabase for secure and real-time data management. The system is segmented into role-based portals for Farmers, Veterinarians, and Administrators, supporting bilingual functionality (English and Tamil) for broad grassroots reach. The key innovation here is the combination of two Artificial Intelligence components: a Convolutional Neural Network (CNN) for the quick diagnosis of dermatological and visible diseases from user-submitted images and a Natural Language Processing (NLP) engine that combines unrefined farmer observations into formatted clinical reports. By leveraging the digital recording of longitudinal vitality parameters such as temperature and food intake, along with AI-driven diagnoses, the proposed system enables precise remote veterinary diagnosis. This system greatly minimizes the time gap between disease manifestation and treatment, thus enhancing animal well-being, preventing economic losses for farmers, and optimizing the workflow of veterinary experts.
DOI: https://doi.org/10.5281/zenodo.18979262
Evaluating Quantum And Classical Computing Approaches In Modern Drug Discovery
Authors: R. Saniya Paul, Livistone S P, Dr. S. Sheeja
Abstract: Drug discovery is inherently complex and expensive with many requisites in terms of precision with respect to interactions' molecular modelling, biological activity prediction and chemical compounds optimisation. Classical computing methods have contributed substantially to the progress of computational drug discovery via molecular simulations, machine learning models and high-throughput virtual screening. However, challenges emerge from the exponentiality of molecular configuration space and the low efficiency of classical algorithms. Quantum computing as a new computing paradigm that offers a novel approach to computation based on various phenomena such as superposition and entanglement and therefore offers a way to overcome the previous limitations. This work presents a comparison of classical and quantum computing approaches in drug discovery with emphasis on their strengths and weaknesses, current progress and future prospects in different aspects of pharmaceutical research.
DOI: https://doi.org/10.5281/zenodo.18979549
Exploring The Role Of Quantum Technologies And Artificial Intelligence In Life Sciences And Healthcare
Authors: Nathivadhani N, Akaliya S, Dr R.Karthik
Abstract: The combination of Quantum Technologies and Artificial Intelligence (AI) is shaping a new approach in life sciences and healthcare. The growing complexity of biomedical data, along with the demand for quick and precise decision-making, has led to the exploration of new computing methods beyond traditional systems. AI has shown great success in medical diagnosis, disease prediction, drug discovery, and healthcare analytics. However, traditional AI models have drawbacks when it comes to optimization, scalability, and computational efficiency. Quantum technologies offer new computing principles based on quantum mechanics, allowing for parallel processing and better optimization. This review provides a detailed look at recent progress in quantum technologies and AI applications within life sciences and healthcare. The paper examines the basics of quantum computing, quantum-inspired algorithms, and hybrid quantum-AI frameworks, emphasizing their uses in disease diagnosis, medical imaging, genomics, molecular modeling, and drug discovery. It also discusses current challenges, practical limitations, and future research directions. This review aims to give researchers, students, and practitioners a clear understanding of the developing quantum-AI landscape and its potential effects on future healthcare systems.
DOI: https://doi.org/10.5281/zenodo.18979750
Human-AI Collaboration: The Rise Of Augmented Intelligence
Authors: Mythul Krishna, Shifa Sherin. S, Dr.R.Karthik
Abstract: Augmented Intelligence is a changing paradigm that focuses on human-AI collaboration to augment decision-making, productivity, and problem-solving. Unlike traditional AI, which seeks to automate processes, augmented intelligence concentrates on supplementing human intelligence with machine learning, data analytics, and automation. This collaboration is revolutionizing several sectors, such as healthcare, finance, and education, by enhancing accuracy, efficiency, and innovation. Nonetheless, issues of data privacy, bias in algorithms, and ethics need to be resolved in order to guarantee the deployment of responsible AI. Transparency and human intervention are necessary in developing trust and maximizing AI- based solutions. With the growth of technology, increased intelligence through augmentation is projected to reshape workspaces and social interactions and provide new fronts for collaboration between humans and AI. This paper delves into its uses, challenges, and implications in the future in the digital era.
DOI: https://doi.org/10.5281/zenodo.18980249
FlowBeats: Gesture‑Based Control Technique For Intelligent Music Interaction System
Authors: Siddhi Pawar, Anuradha Raut, Tanuja Suryawanshi, Shravani Wadghare, Pradnya Satpute
Abstract: Gesture recognition has become an important research area in Human–Computer Interaction (HCI). It enables users to control digital systems using natural hand movements instead of traditional input devices such as keyboards or touch screens. This paper presents FlowBeat, a gesture‑controlled music interaction system that allows users to control music playback using simple hand gestures captured through a webcam. The system uses computer vision techniques with OpenCV and MediaPipe to detect hand landmarks and classify gestures in real time. The recognized gestures are mapped to commands such as play, pause, next track, and previous track. The proposed system provides a low‑cost, touchless, and intuitive interface for music control. The paper discusses existing gesture recognition techniques, system architecture, algorithm design, and advantages of the proposed solution. The motivation behind developing the FlowBeat system is to create a more natural and convenient way for users to interact with multimedia applications. Traditional music control methods often require physical contact with devices, which may not always be practical in certain situations. Gesture-based interaction allows users to control music playback without touching the device, thereby improving accessibility and user comfort. The proposed system focuses on providing an efficient and user-friendly gesture recognition framework that can operate using commonly available hardware such as a standard webcam. By combining computer vision techniques with real-time gesture detection, the system aims to deliver smooth interaction and reliable performance. The study also highlights the potential of gesture-based interfaces in future multimedia systems and interactive technologies.
Face Recognition Attendence System
Authors: Prof.Mohite.B, Vaishnavi Mishra, Pranali kardale, Soniya Kerkar, Shruti Pakhare
Abstract: Traditional attendance systems in schools and industries require manual marking, which is time- consuming and prone to errors. This paper presents an *AI-based face recognition attendance system* that automatically detects and recognizes a person’s face using a camera and records attendance in a database. The system uses artificial intelligence and machine learning algorithms to identify individuals in real time. This approach improves accuracy, saves time, and eliminates proxy attendance. The system can be used in educational institutions, offices, and organizations for efficient attendance management.