Category Archives: Uncategorized

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

Authors: Vaibhav Aggarwal, Laxmi, Yashraj Sharma

Abstract: The rapid advancement of information technology has transformed the traditional education system into a more flexible and accessible digital learning environment. This research paper presents the design and implementation of an Online Course Management System (OCMS) developed using Django web framework with Python as the backend programming language and SQLite as the database management system. The proposed system provides a comprehensive platform for educational institutions to manage courses, track student progress, handle enrollments, and generate completion certificates automatically. The system implements a role-based access control mechanism supporting three distinct user roles: Administrator, Instructor, and Student. Each role has specific permissions and functionalities tailored to their requirements. The frontend is developed using HTML5, CSS3, and Bootstrap 5 framework, ensuring responsive design across various devices. The research demonstrates how modern web technologies can be leveraged to create an efficient, scalable, and user-friendly learning management system.

Published by: vikaspatanker

Authors: Dimple Khatri, Garima, Rajat Takkar

Abstract: Large Language Models (LLMs) have emerged as a major breakthrough in artificial intelligence, significantly improving how machines process and generate human language. These models, built on transformer architectures, are capable of performing a wide range of tasks such as text summarization, translation, question answering, and code generation. In this paper, we analyze the applications and limitations of LLMs in real-world systems through a qualitative study based on literature review and conceptual experimentation. Our findings suggest that while LLMs provide high accuracy and flexibility across domains like healthcare, education, and customer service, they still face critical challenges such as hallucination, bias, high computational cost, and lack of interpretability. The study highlights the importance of integrating validation mechanisms and ethical AI practices to ensure reliable deployment. We conclude that although LLMs are powerful tools, their practical adoption requires careful optimization and responsible usage strategies.

DOI:

Published by: vikaspatanker

Authors: Dr. Rajul Misra, Mr. Saurabh Saxena, Ritik Saini, Waseem, Shuaib Ali

Abstract: The Single Phase Induction Motor Protection and Control System using IoT is designed to improve the safety, reliability and performance of single phase induction motors by continuously monitoring important electrical parameters and controlling the motor through internet-based technology. Single phase induction motors are widely used in household appliances, agricultural pumps, fans, compressors and small industrial machines due to their simple construction and low cost. However, these motors are highly sensitive to abnormal operating conditions such as overload, overcurrent, overheating, voltage fluctuation, phase failure and short circuit. These faults can reduce motor efficiency, increase maintenance cost and sometimes permanently damage the motor. In traditional systems, protection devices such as fuse, MCB or overload relay provide limited safety and do not allow remote monitoring of motor condition. To overcome this problem, Internet of Things (IoT) technology is used in this project to create a smart monitoring and protection system. The proposed system uses sensors such as current sensor, voltage sensor and temperature sensor to continuously measure motor parameters. These sensors are connected to a microcontroller such as Arduino, which processes the data and compares it with predefined safe operating limits. When the motor operates under normal conditions, the system continuously sends real time data to an IoT cloud platform such as Blynk or ThingSpeak through Wi-Fi module. The user can monitor motor parameters such as current, voltage and temperature using a mobile phone, tablet or computer from any location. If any abnormal condition such as overload, overheating or high current occurs, the microcontroller automatically activates the relay module to disconnect power supply to the motor and prevent damage. The system also provides remote control facility, allowing the user to turn the motor ON or OFF using IoT mobile application. This feature is especially useful in agricultural applications such as water pumping systems where motor needs to be controlled from distant locations. The system helps in early fault detection, reduces maintenance cost and increases operational safety. Overall, the IoT based motor protection system is an efficient, low cost and reliable solution for improving motor life and reducing failure risk. The system can be further enhanced by adding features such as SMS alert, mobile notification, automatic fault diagnosis and data logging for performance analysis. This project demonstrates how IoT technology can be effectively used in electrical engineering applications to develop smart and intelligent protection systems.

DOI: https://doi.org/10.5281/zenodo.20024088

Published by: vikaspatanker

Authors: Mrs.W. Asha Princy, Pooja K.P., Pooja Shree S, Prathisha A, Shahira Banu S

Abstract: The rapid advancement of artificial intelligence (AI) in healthcare has created unprecedented opportunities for improving diagnosis, treatment planning, and clinical decision-making. This paper presents DonorSync — an AI-powered Digital Twin system designed to assist physicians in liver and kidney donor-recipient matching using machine learning and medical image analysis. The proposed system combines Logistic Regression-based clinical parameter analysis (age, bilirubin, albumin, creatinine, urea) with a ResNet-50-driven ultrasound image evaluation module to generate ranked donor compatibility scores and transplant success probabilities in real time. Built on a FastAPI backend with MongoDB data storage and an HTML/CSS/JavaScript frontend, the platform provides secure, scalable, and efficient access to donor matching services. Experimental evaluation confirms that the integrated dual-modality approach substantially reduces donor selection time and enhances prediction reliability compared to conventional manual processes. The system aligns with UN Sustainable Development Goal 3 (Good Health and Well-Being) and Goal 9 (Industry, Innovation and Infrastructure).

Published by: vikaspatanker

Authors: Jag Pratap Singh Yadav

Abstract: Systems in reality are characterized by uncertainties. There are uncertainties associated with nature, economics, communications, healthcare delivery, production systems, and social systems, among others, which cannot be modeled using deterministic equations. Stochastic processes facilitate the formulation of mathematical models of systems whose behavior is affected by some random elements. They help in assessing risks, optimizing resource allocations, forecasting future behaviors, and enhancing system robustness. The paper centers on stochastic processes as techniques for dealing with uncertainty in systems. First, the concept of stochastic processes will be defined. Major types of stochastic processes, including Markov chains, Poisson processes, Brownian motion, random walks, and queueing models, will be discussed. Then, applications of stochastic models in various areas, such as financial modeling, engineering, health care, climate studies, operations management, telecommunications, and machine learning, will be explored. Additionally, this paper will examine advantages and disadvantages associated with stochastic modeling. In particular, problems associated with assumptions used in building stochastic models and computational complexities of such models will be analyzed. It will be concluded that stochastic processes represent powerful tools for studying and managing uncertain systems because they enable turning randomness from an issue into a quantifiable phenomenon.

DOI: https://doi.org/10.5281/zenodo.20021901

Published by: vikaspatanker

Authors: Prof. Pushpa T, Dheeraj P Aradhya, K Prajwal, Pramod Hegde, Kiran MR

Abstract: The global surge in non-communicable diseases (NCDs) necessitates a transition from episodic clinical care to continuous, data-driven personal health management. This paper details the development of the Smart Health and Fitness Tracker (SHFT), a scalable ecosystem built on the MERN stack. Unlike localized tracking applications, SHFT employs a centralized NoSQL architecture to provide longitudinal health data analysis. The system integrates real-time telemetry tracking—including caloric balance, hydration, and sleep hygiene—with automated BMI and BMR computation. By utilizing a React-based interactive dashboard and Node.js middleware, the platform achieves high data integrity and low-latency feedback. Experimental results demonstrate that the system enhances user engagement and supports informed decision-making for long-term wellness.

Published by: vikaspatanker