Mobile Based GPS Attendance System

Abstract

Mobile Based GPS Attendance System is by combining GPS geo-fencing, BLE beacon detection, and face verification to guarantee precise, impenetrable student authentication, the Mobile-Based GPS Attendance System overcomes the drawbacks of conventional attendance techniques. The system automatically records attendance when a student enters the classroom, verifies their position, and recognizes classroom beacons. It is designed with distinct interfaces for students and instructors. After that, attendance information is sent to a backend server for safe reporting and logging. In order to maintain integrity and transparency, the system also keeps an eye on app activity and instantly notifies users if a kid changes to a different app while taking attendance. This system improves dependability, lowers proxy attendance, and simplifies classroom administration for educational institutions by fusing mobile sensing technologies with automated backend processing.

Introduction

Traditional attendance systems, including manual signatures, ID card swipes, or basic digital check-ins, are prone to errors, proxy attendance, and scalability issues. To address these challenges, the proposed Mobile-Based GPS Attendance System integrates multi-layer authentication using GPS geo-fencing, Bluetooth Low Energy (BLE) beacons, facial recognition, and app usage monitoring to ensure secure, accurate, and automated attendance tracking.

The system works as follows:

1. GPS Geo-Fencing: Verifies the student is within a predefined classroom or academic area, preventing attendance marking from outside.

2. BLE Beacon Detection: Confirms indoor proximity to the classroom by detecting beacon signals for precise localization.

3. Facial Recognition: Uses live selfies and deep learning embeddings with liveness checks to authenticate the student’s identity.

4. Behavior Monitoring: Tracks app activity to detect suspicious behavior, such as switching apps during attendance marking.

The frontend Android app handles GPS, camera, and Bluetooth sensors, providing a user-friendly interface for students and real-time logs for faculty. The backend, implemented using FastAPI, processes GPS, BLE, and facial data, manages verification workflows, and securely records attendance with timestamps and metadata.

Conclusion

In academic settings, the suggested Mobile-Based GPS Attendance System offers a safe, automated, multi-factor solution for precise student attendance verification. Only approved students who are physically present in the classroom can mark attendance thanks to the system\'s integration of GPS geo-fencing, BLE beacon proximity validation, and biometric facial recognition. By identifying efforts to switch apps and stopping abuse, behaviour tracking further improves integrity. The system greatly reduces proxy attempts and human effort compared to traditional attendance systems, which benefits both educational institutions and students, according to experimental evaluation. It also achieves excellent reliability and closely correlates with humanly checked attendance records

References

REFERENCES [1] A. Zandbergen, \"GPS-Based Location Tracking Technologies,\" Journal of Spatial Science, vol. 55, no. 2, pp. 103–117, 2010. [2] \"The Horus WLAN Location Determination System,\" International Conference on Mobile Systems, M. A. Youssef and A. Agrawala, pp. 205–218, 2005. [3] M. A. Alsheikh, S. Lin, D. Niyato, and H. Tan, \"Indoor Localization Using Smartphones: A Survey,\" IEEE Communications Surveys & Tutorials, vol. 19, no. 2, pp. 1347–1370, 2017. [4] \"Location Fingerprinting With Bluetooth Low Energy Beacons,\" S. Faragher and R. Harle, IEEE Journal on Selected Areas in Communications, vol. 33, no. 11, pp. 2418–2428, 2015. [5] Deep Learning, I. Goodfellow, Y. Bengio, and A. Courville, MIT Press, 2016. [6] C Cortes and V. Vapnik, “Support Vector Networks,” Machine Learning, vol. 20, pp. 273–297, 1995. [6] \"Face-Net: A Unified Embedding for Face Recognition,\" F. Schroff, D. Kalenichenko, and J. Philbin, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015. [7] \"Rapid Object Detection Using a Boosted Cascade of Simple Features,\" CVPR, 2001, P. Viola and M. Jones. [8] \"Android Location Services Documentation,\" Google Developers, 2024. [Online]. https://developer.android.com is accessible. [9] \"Bluetooth Low Energy Specifications,\" Bluetooth SIG, 2023. [Online]. Accessible: https://www.bluetooth.com [10] \"Fast-API: High-Performance Web Framework,\" Fast-API Documentation, 2023. [11] \"MySQL Reference Manual,\" MySQL Developers, Oracle, 2023. [12] React Team, “React Documentation,” Meta, 2023. [Online]. Available: https://reactjs.org [12] OpenCV Team, \"OpenCV Documentation,\" 2023. [Online]. Accessible: https://opencv.org [13] \"Retrofit REST Client for Android,\" Retrofit Developers, 2023. [14] \"The Cricket Indoor Location System,\" N. Priyantha, A. Chakraborty, and H. Balakrishnan, Mobile Computing and Networking, pp. 32–43, 2000.

Copyright

Copyright © 2025 Madhu B G, Harshitha K M, Mallika G U, Vaibhavi B Dandin, Vibha J. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.