AI-Powered Lost and Found Portal for College Campus
Angad Singh
Scholar, Department of Computer Science & Engineering, (AI&ML), KIPM College of Engineering and Technology, U.P., India
Sumit Kumar Verma
Scholar, Department of Computer Science & Engineering, (AI&ML), KIPM College of Engineering and Technology, U.P., India
Abhay Sahu
Scholar, Department of Computer Science & Engineering, (AI&ML), KIPM College of Engineering and Technology, U.P., India
Pankaj Kumar Gupta
Assistant Professor, Department of Computer Science and Engineering, (AI&ML), KIPM College of Engineering and Technology, U.P., India
📌 DOI: https://doi.org/10.63920/tjths.52032
🔑 Keywords: Lost and found system, AI item matching, convolutional neural networks, real-time notifications, QR code, geolocation
📅 Publication Date: 26 April 2026
📜 License:
This work is licensed under a Creative Commons Attribution 4.0 International License
- Share — Copy and Redistribute the material
- Adapt — Remix, Transform, and build upon the material
- The licensor cannot revoke these freedoms as long as you follow the license terms.
Abstract:
Every year, countless students, faculty, and staff across college campuses lose personal belongings — and most of them never get those items back. Traditional lost-and-found systems, whether physical registers, notice boards, or informal WhatsApp groups, simply were not built for the pace and scale of modern campus life. They are slow, hard to search, and offer no intelligent way to connect lost items with found ones. This paper introduces Lost and Found — a full-stack, AI-powered web portal designed to completely rethink how institutions handle lost and found items. Built on the MERN stack (MongoDB, Express.js, React.js, and Node.js), the platform uses a TensorFlow.js convolutional neural network (CNN) to automatically match photos of lost items with found ones, achieving an 87.3% matching accuracy in real-world trials. Beyond AI matching, the system includes QR code tagging for physical items, GPS-based location tracking, role-based access for different types of users, real-time push notifications via WebSockets, and a live analytics dashboard for administrators. During a 60-day pilot at the Institute of Technology, Lucknow with 200 participants, the portal reduced average item recovery time by 74% compared to the paper-based system, and earned a System Usability Scale (SUS) score of 82.4 — placing it firmly in the "Excellent" category
Download Full PDF Paper
📖 How to Cite
Sumit Kumar V., Angad S., Abhay s., Asmit Kumar R., Pankaj Kumar G. (2026). AI-Powered Lost and Found Portal for College Campus. TEJAS J. Technol. Humanit. Sci.,, Vol. 05, Issue 02. https://doi.org/10.63920/tjths.52032
📊 Article Metrics
References
[1] D. Paudel, H. Boogaard, A. de Wit, M. van der Velde, M. Claverie, L. Nisini, S. Janssen, S. Osinga, and I. N. Athanasiadis, “Machine learning for regional crop yield forecasting in Europe,” Field Crops Research, vol. 276, p. 108377, Feb. 2022.
[2] D. Paudel, H. Boogaard, A. de Wit, S. Janssen, S. Osinga, C. Pylianidis, and I. N. Athanasiadis, “Machine learning for large-scale crop yield forecasting,” Agricultural Systems, vol. 187, p. 103016, Feb. 2021.
[3] T. Ben Hassen and H. El Bilali, “Impacts of the Russia-Ukraine War on Global Food Security: Towards More Sustainable and Resilient Food Systems?,” Foods, vol. 11, p. 2301, 2022.
[4] World Health Organization, “World hunger is still not going down after three years and obesity is still growing—UN report,” 2019. [Online]. Available: WHO Report
[5] Y. Perwej and F. Parwej, “A Neuroplasticity (Brain Plasticity) Approach to Use in Artificial Neural Network,” International Journal of Scientific & Engineering Research (IJSER), vol. 3, no. 6, pp. 1–9, 2012, doi: 10.13140/2.1.1693.2808.
[6] V. K. S. Maddala, S. Shahi, Y. Perwej, and H. G. R. Reddy, “Machine learning based IoT application to improve the quality and precision in agricultural system,” European Chemical Bulletin, vol. 12, special issue 6, pp. 1711–1722, May 2023, doi: 10.31838/ecb/2023.12.si6.157.
[7] K. D. V. Prasad, Y. Perwej, E. N. Rao, and H. B. Patel, “IoT devices for agriculture to improve food and farming technology,” Journal of Survey in Fisheries Sciences, vol. 10, no. 1S, pp. 4054–4069, Mar. 2023.
[8] M. Fathi, R. Shah-Hosseini, and A. Moghimi, “3D-ResNet-BiLSTM model: A deep learning model for county-level soybean yield prediction,” Remote Sensing, vol. 15, no. 23, 2023, doi: 10.3390/rs15235551.
[9] M. Champaneri, D. Chachpara, C. Chandvidkar, and M. Rathod, “Crop yield prediction using machine learning,” International Journal of Scientific Research, vol. 9, 2020.
[10] A. Kaneko, T. Kennedy, L. Mei, C. Sintek, M. Burke, S. Ermon, and D. Lobell, “Deep learning for crop yield prediction in Africa,” in Proc. ICML AI for Social Good Workshop, Long Beach, USA, 2019.
[11] Y. Perwej, S. Ahmad, and N. Akhtar, “Leveraging AI for social impact in environmental sustainability,” International Journal of Scientific Research in Science, Engineering and Technology (IJSRSET), vol. 12, no. 4, pp. 253–266, Aug. 2025, doi: 10.32628/IJSRSET2512506.
[12] S. Shukla, Y. Perwej, S. Singh, and N. Akhtar, “IoT-enabled decision support system for crop recommendation using machine learning algorithms,” Journal of Emerging Technologies and Innovative Research (JETIR), vol. 12, no. 11, pp. 803–809, Nov. 2025, doi: 10.6084/m9.jetir.JETIR2511200.
[13] D. Satterthwaite, G. McGranahan, and C. Tacoli, “Urbanization and its implications for food and farming,” Philosophical Transactions of the Royal Society B, vol. 365, pp. 2809–2820, 2010.
[14] T. Lin et al., “DeepCropNet: A deep spatial-temporal learning framework for county-level corn yield estimation,” Environmental Research Letters, vol. 15, p. 034016, 2020.
[15] T. K. Fegade and B. V. Pawar, “Crop prediction using artificial neural network and support vector machine,” in Data Management, Analytics and Innovation, Springer, 2020, pp. 311–324.
[16] S. Singh, S. Shukla, Y. Perwej, and N. Akhtar, “Optimizing crop yield forecasts through deep neural network architectures using Omdena dataset,” International Journal of Scientific Research in Science, Engineering and Technology (IJSRSET), vol. 12, no. 5, pp. 377–389, Oct. 2025, doi: 10.32628/IJSRSET2513819.
[17] A. Gonzalez-Sanchez, J. Frausto-Solis, and W. Ojeda-Bustamante, “Attribute selection impact on linear and nonlinear regression models for crop yield prediction,” The Scientific World Journal, vol. 2014, Article ID 509429, 2014.