Daily Archives: May 5, 2026

Authors: B. Anief, M. Sakthivanitha

Abstract: Contemporary higher education institutions operate a fragmented portfolio of digital tools — separate learning management systems, manual attendance registers, paper-based hostel outpass forms, and WhatsApp-group announcements — that impose coordination overhead on students and staff while producing no integrated data trail for institutional analytics. This paper presents the design, implementation, and evaluation of the Smart Campus Engagement System (SCES), a cloud-deployed, role-aware web platform that unifies nine functional modules — user management, AI-assisted learning, attendance and academics, hostel and outpass management, events and activities, communication and alerts, complaints and feedback, campus services, and analytics — within a single authenticated interface. The system is implemented using a Next.js 14 frontend, a FastAPI Python backend, a PostgreSQL cloud database, and a Groq API–powered LLaMA-3.3-70B language model for an AI assistant. Containerised deployment via Docker Compose supports horizontal scaling. System testing across eight functional scenarios at up to 200 concurrent users demonstrates API response times below 900 ms and a peak-load error rate of 2.8%. Security testing confirms resistance to SQL injection, JWT tampering, cross-site scripting, and unauthorised role escalation. Comparative analysis against four published smart campus systems confirms that the proposed implementation is the only system combining LLM-based AI assistance, geolocation-verified attendance, digital outpass workflow, and real-time push notifications in a single unified deployment. The system establishes a replicable, open-architecture blueprint for next-generation campus digitalisation.

DOI: https://doi.org/10.5281/zenodo.20037223

Published by: vikaspatanker

Authors: Dr. K.N.Kazi, Miss. Kolekar Akshata Bharat, Miss. Adling Snehal Bhagwat, Mr. Chorage Mahesh Santosh

Abstract: Automation plays a vital role in modern industries by improving efficiency, accuracy, and productivity. This project presents the design and development of a Packing Controlled Robotic Arm using Arduino. The system is designed to perform automated pick-and-place operations for packing applications in small-scale industries. The robotic arm is controlled using Arduino Nano, with servo motors providing movement to each joint and a gripper mechanism handling objects. Joy Sticks are used to detect the presence of items for packing, while Arduino coordinates motion control through pre-programmed instructions. The developed system aims to reduce manual labor, minimize errors, and provide a cost-effective automation solution. The prototype demonstrates the potential of using simple, low-cost components for effective packaging automation in educational and industrial setups.

DOI: http://doi.org/

Published by: vikaspatanker

Authors: Rohit Dhamale, Prathamesh Sonawane., Revati Ma’am, Archana Maam

Abstract: Artificial Intelligence (AI) has emerged as one of the most transformative technologies in modern healthcare. It has the potential to significantly improve the accuracy and efficiency of disease diagnosis and treatment. One of the most important applications of AI in healthcare is early disease detection. Early detection allows medical professionals to identify diseases in their initial stages, enabling timely treatment and improving patient survival rates. AI technologies such as machine learning, deep learning, natural language processing, and predictive analytics can analyze large volumes of medical data quickly and accurately. These systems can process electronic health records, laboratory reports, medical images, and patient history to identify patterns that indicate the early onset of diseases. AI-based systems assist doctors by providing data-driven insights and predictions that help in clinical decision-making. This research paper explores the role of artificial intelligence in early disease detection and its impact on modern healthcare systems. The study examines different AI technologies used in disease diagnosis, the methodology used to implement these systems, and the challenges associated with AI integration in healthcare environments. Furthermore, the paper discusses the benefits of AI-driven diagnostic systems in improving healthcare efficiency, reducing medical errors, and enhancing patient outcomes.

DOI: https://doi.org/10.5281/zenodo.20036666

Published by: vikaspatanker

Authors: Prof. Rahul D. Ingle, Prof. Rohan B. Kokate, Jyoti Ramesh Lanjewar

Abstract: The rapid advancement of digital technology has significantly transformed financial transactions, leading to the widespread adoption of cashless payment systems. Among these, QR code-based payment systems have emerged as one of the most convenient and efficient methods for conducting fast and contactless transactions. However, despite their growing popularity, these systems still face critical challenges such as transaction fraud, unauthorized access, phishing attacks, and security vulnerabilities. To overcome these limitations, there is a need to integrate intelligent technologies that can enhance both security and user experience. This project presents the design and development of a QR Based Online Payment System for Enhanced Convenience Using Machine Learning (ML). The primary objective of the system is to provide a secure, fast, and user-friendly digital payment platform that allows users to make payments simply by scanning QR codes. The system eliminates the need for physical cash, card swiping, or manual bank details entry, thereby reducing transaction complexity and improving efficiency. A key feature of the proposed system is the integration of Machine Learning-based fraud detection mechanisms. The ML model continuously analyzes transaction patterns, user behavior, device information, and payment history to identify unusual or suspicious activities. By using classification and anomaly detection techniques, the system can detect potential fraud in real time and prevent unauthorized transactions before they are completed. This enhances the overall trust and reliability of the payment platform. The system also includes essential modules such as secure user authentication, dynamic QR code generation, transaction processing, payment history tracking, and notification services. Each transaction is securely encrypted and stored in a centralized database to ensure data integrity and confidentiality. The platform is designed using modern web technologies to ensure scalability, responsiveness, and compatibility across multiple devices. From a functional perspective, the system supports both users and merchants, enabling seamless peer-to-merchant and peer to peer payments. Merchants can generate unique QR codes linked to their accounts, while users can scan and complete payments instantly. The inclusion of real-time alerts and dashboards helps users track their financial activities efficiently.

DOI: https://doi.org/10.5281/zenodo.20036097

Published by: vikaspatanker

Authors: Sony V Hovale, Manu K C, Naresh Patel, Pavithra B, Shradha G Vernekar

Abstract: Early detection and classification of oral lesions are essential for the prevention of oral cancers, and yet, manual diagnosis is still a challenge due to variations in the appearance of lesions, quality of images, and limited clinical datasets. This research explores the use of diffusion models, a recent class of generative models renowned for their stable training and high-fidelity reconstruction, to improve the automatic classification of oral lesion images. The proposed system includes dataset collection from open-source platform kaggle, preprocessing of dataset, a diffusion- based denoising and feature extraction pipeline, and finally, a classification stage to categorize the normal, precancerous, and cancerous lesions. By leveraging the forward and reverse process of diffusion, the model improves the clarity of the images and effectively extracts discriminative features, mitigating problems of noise, imbalance, and low-quality clinical images. In a deep learning approach combining CNN-based classification with the concept of enhancement provided by diffusion mechanisms, the generalization performance is boosted. The system will be evaluated based on accuracy, precision, recall, and F1-score, and the results provide promising improvements compared to the state-of-the-art traditional deep learning methods. This paper has found that diffusion models provide a robust, scalable, and clinically valuable pipeline for early oral lesion detection, with strong potential to be deployed in real-world diagnostic pipelines and future research on medical imaging and we obtained a very good accuracy i.e., 96% while training the model. This paper establishes the diffusion model as a promising approach for medical image analysis, particularly in the early detection and classification of oral lesions, paving the way for future research and clinical applications in healthcare.

DOI: http://doi.org/

Published by: vikaspatanker

Authors: S. Ashwin, S. Brittlin, K. Rohini

Abstract: Conventional fixed-time traffic signal systems are structurally incapable of responding to the stochastic variability of urban traffic flow, resulting in prolonged vehicle waiting times, suboptimal intersection throughput, and unnecessary fuel consumption. This paper presents a complete, edge-deployed adaptive traffic signal management system that uses real-time video input from existing CCTV infrastructure and the YOLOv8 deep learning object detection model to continuously estimate lane-wise vehicle density and dynamically compute optimised signal phase durations. The architecture is modular, comprising video acquisition, frame preprocessing, YOLOv8-based vehicle detection and classification, density estimation, decision logic, and signal control modules. The system avoids cloud dependency through localised edge processing, ensuring end-to-end signal update latency below 250 ms. Experimental evaluation across four simulated intersection lanes demonstrates an overall vehicle detection mAP@0.5 of 92.9% at 46 frames per second, a 38.3% reduction in average vehicle waiting time, and a 37.5% improvement in intersection throughput relative to a fixed-time baseline. Comparative benchmarking against Faster R-CNN, SSD, and YOLOv3-based approaches confirms the superiority of the proposed implementation on both detection accuracy and real-time responsiveness. The system is deployable without additional roadside hardware investment, making it a cost-effective and scalable solution for smart urban traffic management.

DOI: https://doi.org/10.5281/zenodo.20035179

Published by: vikaspatanker

Authors: V. Irfan Ahamed, J. Lokeshwar, Dr. K. Rohini

Abstract: Gas leakage accidents involving liquefied petroleum gas (LPG), methane, and related hydrocarbons represent a significant and persistent safety hazard in both residential and small-scale industrial settings. Conventional reliance on human olfactory detection is inherently unreliable, particularly under conditions of poor ventilation, occupant absence, or odorant threshold variability. This paper presents the design, hardware implementation, and systematic performance evaluation of a low-cost, embedded gas leakage detection system built around an Arduino Uno microcontroller (ATmega328P) and a Figaro MQ-2 semiconductor gas sensor. The sensing element operates on the principle of surface resistance modulation upon exposure to combustible gases, with the resulting analogue voltage mapped to a 10-bit ADC value for threshold-based decision logic. Alert output is delivered through a dual mechanism comprising an 85 dB piezoelectric buzzer and a visual LED indicator, ensuring notification under varied ambient conditions. Over 40 controlled trials spanning four gas concentration levels, the system achieved an overall detection accuracy of 92.5%, with a sub-1.2 second response time at high exposure levels and an alert latency of 180–210 ms. The false-positive and false-negative rates were 5.0% and 2.5%, respectively. Environmental characterisation identified ambient temperature and relative humidity as the primary factors influencing baseline drift and sensitivity attenuation. The results confirm that the proposed system provides a technically sound, cost-effective safety solution, with a clear upgrade pathway toward IoT-enabled remote monitoring.

DOI: https://doi.org/10.5281/zenodo.20035126

Published by: vikaspatanker

Dr.Alugolu Avinash
Affiliation	Associate Professor,Pragati Engineering College (A) ,Surampalem,Andhra Pradesh , India.
Email-Id:	agoyal514@gmail.com
Publication: Patents: Enhancing Cyber Threat Detection Through Integrated Endpoint Detection And Response With Network-Based Anomaly Analysis- 2024. SmartPaperWeightwithProductivityTracking, 2021. Implementationofvariousresourcesinsupplychainnetworkon competitive moves, 2022. Books: Fundamentals Of Machine Learning’ in Scicraft hub International Publication  2024. Publications: Novel Preprocessing Techniques For Numerical Data Analysis in Journal of Emerging Technologies and Innovative Research – 2024. A Dynamic Load Balancing Strategy for Optimizing Resource Utilization in Cloud Data-Centres in  International Journal for Modern Trends in Science and Technology (IJMTST) – 2023. Heart Disease Prediction with Novel Machine Learning Technique in Indian Journal of Computer Science and Technology (INDJCST) -2023. Analyzing the User Comments from Youtube Videos Using NLP and ML” in International Journal of Information Technology and Computer Engineering , 2022. Comparison of Ebola Virus Disease (EVD) and Covid-19 bydata visualization techniques of Machine Learning 2020.

Published by: vikaspatanker

Authors: Mr. D. Harsha, N. Soumya, G. Nandavardhan Reddy, K. Sai Sreesh

Abstract: The rapid growth of electric vehicles (EVs) has increased the demand for efficient and intelligent charging systems capable of supporting modern power grids. This paper presents the design and simulation of a bidirectional battery charger that enables Grid-to-Vehicle (G2V), Vehicle-to-Grid (V2G), and active filter operations within a single integrated system. The proposed configuration consists of a bidirectional AC–DC converter connected to the grid and a bidirectional DC–DC converter interfaced with the battery through a regulated DC link. An LCL filter is employed to reduce harmonic distortion and ensure high-quality grid current. A control strategy based on pulse width modulation (PWM) and reference current polarity is implemented to achieve smooth transition between operating modes. In G2V mode, the system provides controlled battery charging with near unity power factor, while in V2G mode, stored energy is effectively supplied back to the grid. Additionally, the system operates as an active filter to compensate for harmonics caused by non-linear loads. Simulation results demonstrate stable DC link voltage, reliable bidirectional power flow, and improved power quality. A hardware prototype with microcontroller-based control and Bluetooth communication further validates the practical feasibility of the proposed system.

DOI: https://doi.org/10.5281/zenodo.20033587

Published by: vikaspatanker