GOFINDIT: A SMART LOST AND FOUND MANAGEMENT SYSTEM FOR GODFREY OKOYE UNIVERSITY
Abstract
ABSTRACT
This research presents the design and development of GoFindit, a web-based Lost and Found Management System that has been developed using the current software engineering best practices to streamline the reporting, tracking, and recovering of lost and found items at Godfrey Okoye University. The system addresses the inefficiencies of traditional manual methods by integrating core components of web development, user authentication, data persistence, and artificial intelligence. The application was developed using the Django web framework and HTML, CSS, and JavaScript on the frontend side; it includes role-based access control, item categorization, an admin moderation panel, and a real-time chat engine between users and the admin. One of the most significant changes to the system is an AI-based item-matching engine that automatically provides possible matches of lost items that have been found based on semantic comparison using Sentence-BERT embeddings and cosine similarity. It was designed in an object-oriented approach, and the models represented are users, items, claims, and messages. The results, guided by design principles, showed that the system significantly improved user experience by reducing search time and the need for manual intervention. Through the combination of natural language processing and machine learning, it effectively addresses everyday problems like item loss, thereby showing how smart systems that can grow and handle more work are useful in real life. The new system, GoFindit, will stand out as a practical and intelligent solution to campus-wide item misplacement. With its strong backend architecture, automated processes, and user-friendly user interface, it exemplifies the new trend of smart web applications in the field of computer science.
Full-Text Access Notice
In accordance with the NERD Policy on promoting peer-reviewed publication, public access to the full text of a project, thesis or dissertation is restricted for three years, allowing the author and supervisors sufficient time to pursue peer-reviewed publication.
During this period, researchers with legitimate academic or research purposes may request authorisation directly from the author to enable NERD to release the indexed full texts of the work using the form below.