IJRCIT- International Journal of Research in Computer & Information Technology

Archives of International Journal of Research in Computer & Information Technology(IJRCIT)

Volume 10 Issue 2 March 2025

1. Design and Implementation of Black-Box for Vehicle Safety

AUTHOR NAME : Aditya Fulzele, Likhit Akhade, Tanishq Kamble, Tushar Nimje, Mansi Zingre, Khushi Akare, Prof. Atul Malode

ABSTRACT : The increasing rate of vehicle thefts and road accidents necessitates a smart, IoT-based vehicle black box system for real-time tracking and emergency response. This system integrates GSM, GPS, and embedded automation to detect crashes, send immediate alerts, and track vehicle locations. Using sensors, wireless communication, and cloud integration, it enhances accident response time while improving vehicle security. The system comprises Arduino Uno, GSM SIM900A, GPS NEO-6M, crash sensors, and an LCD display for real-time monitoring. Upon detecting an accident, the system records vehicle parameters, geo-location, and impact severity, sending alerts to emergency contacts and authorities. Additionally, anti-theft features detect unauthorized movement and notify the vehicle owner. The system achieves high accuracy in crash detection and real-time tracking, with a response time of 5 seconds. Future improvements will focus on AI-driven analytics, predictive accident detection, and cloud-based security enhancements.

Download

2. Development of a Self-Learning Educational Tool for Data Analytics Algorithms

AUTHOR NAME : Divya Ikhar, Sagar Wagare, Snehal Panajwar, Ajay Gandhi, Prof. Dr. A. C. Kailuke

ABSTRACT : The demand for data literacy continues to rise across industries, the need for hands-on, interactive learning tools in education has become increasingly important. This project presents a Data Analytics Self-Learning Educational Tool that bridges the gap between theoretical learning and practical application. The platform is designed for students and aspiring analysts to understand and interact with core data analytics algorithms including classification, clustering, regression, and statistical operations like average, sum, and nearest value. Built using web technologies such as HTML, JavaScript, and ASP.NET, the system supports real-time data processing and visualization. The platform features preloaded examples and allows users to upload their own datasets, providing personalized and scalable learning. It includes step-by-step algorithm demonstrations and graphical outputs that promote critical thinking and experimentation. The backend handles file input, logic processing, and result rendering, while the frontend ensures accessibility and responsiveness across devices. The system has been tested with students and educators to ensure usability, performance, and educational effectiveness. Overall, the tool serves as a dynamic, self-paced environment that fosters algorithmic understanding and data problem-solving skills. The paper elaborates on the design phases, implementation, challenges, and educational impact of the tool.

Download

3. Robotic Mimicry Leveraging Posenet Software for Human-Like Movements

AUTHOR NAME : Pooja Chandewar, Yashika Wanjari, Pooja Raut, Dipanjali Warade, Pratiksha Motghare, Dr. Archana Dehankar

ABSTRACT : This research presents a novel algorithm for accurate pose estimation tailored for human posture mimicry in robotics, optimized for low-cost and resource-constrained embedded systems. Integrating Convolutional Neural Network PoseNet for object detection with stereo correspondences for spatial reconstruction, the algorithm enables precise estimation of human posture. Leveraging ORB features and weighted averaging of stereo-corresponded key points, it achieves superior accuracy while maintaining resource efficiency. Comparative testing against deep learning-based methods demonstrates its efficacy for robotic applications. The algorithm affordability and efficiency make it well-suited for implementing human posture mimicry in robotics, with potential applications in personalized rehabilitation and assistive technology. In conclusion, this research presents a versatile and accessible solution for advancing human-robot interaction through posture mimicry.

Download

4. Smart And Effective Realtime Management System for Street Parking

AUTHOR NAME : Rajnandini Wankhade, Rucha Garad, Achal Khadse, Gunjan Londe, Dr. R. R. Bhure

Download

5. AI-Based Designing of Assistive Portal for Stakeholders in Approval Process

AUTHOR NAME : Prof. S.A. Khan, Aachal Bache, Arya Rode, Komal Kale, Tanvi Gonge

ABSTRACT : AI-Based Designing of Assistive Portal for Stakeholders in Approval Process" aims to simplify and automate the complex procedures involved in obtaining approvals from regulatory bodies like the All-India Council for Technical Education (AICTE). The proposed system is a web-based assistive portal that leverages artificial intelligence and data modeling techniques to guide stakeholders through various stages of the approval process. Key features include a chatbot interface for interactive assistance, document analysis tools, multilingual support, and rule-based validation mechanisms. By integrating these technologies, the portal reduces human error, enhances accessibility, and ensures regulatory compliance, thereby improving efficiency and transparency in the approval workflow. This solution is especially valuable for educational institutions, administrators, and policy implementers navigating the often convoluted and document-heavy approval procedures.

Download