http://dlib.iit.ac.lk/xmlui/handle/123456789/2154 2026-04-08T18:29:09Z 2026-04-08T18:29:09Z Samarage, Hiruni http://dlib.iit.ac.lk/xmlui/handle/123456789/2998 2026-03-17T07:20:17Z 2025-01-01T00:00:00Z

Development of an AI-Based Semantic Chatbot for Tertiary Education Institutes Samarage, Hiruni This project presents the design, development, testing, and evaluation of an AI-based semantic chatbot system tailored for tertiary education institutions in Sri Lanka. The primary objective was to enhance student engagement and support by enabling real-time, context-aware, and personalized responses to academic and administrative inquiries through natural language interaction. The chatbot system was developed using a modular architecture comprising: • A web-based user interface built with HTML, CSS, and JavaScript, • A Flask-based backend server for managing user sessions and API communication, • Integration with OpenAI’s GPT-4o model for natural language understanding and generation, • A FAISS vector search engine to perform semantic information retrieval from an institutional knowledge base, • An SQLite database for persistent user data, chat history, and feedback storage. The system was designed to operate across all major web browsers and device types, ensuring compatibility with Windows, macOS, Android, and iOS operating systems. Through comprehensive black box, white box, integration, usability, and exploratory testing, the chatbot demonstrated strong performance in delivering accurate, contextually relevant answers and a smooth, user-centric interaction experience. Key features included multilingual support (informal Singlish handling), chat history retrieval, feedback collection, voice output via the Web Speech API, and dynamic UI enhancements. Stakeholder evaluations validated the system’s effectiveness, highlighting its potential for broader deployment within educational institutions. The project successfully showcases how AI-driven semantic chatbots can be integrated into higher education environments to improve information access, communication efficiency, and user satisfaction.

2025-01-01T00:00:00Z Magdon Ismail, Noor Nisma http://dlib.iit.ac.lk/xmlui/handle/123456789/2997 2026-03-17T07:17:21Z 2025-01-01T00:00:00Z

PlanitGreen: A Gamified Tour Booking Platform to Promote Sustainable Travel Choices Magdon Ismail, Noor Nisma The tourism industry plays a significant role in the global economy but also contributes significantly to climate change through carbon emissions from transportation, accommodation, and other travel activities. As environmental concerns grow, eco-friendly tourism is gaining traction among pro-environmentalists. However, many travellers still lack awareness of the environmental impact of their choices and are often unmotivated to choose sustainable options, as they don't experience immediate benefits. To address this issue, PlanitGreen introduces a gamified tour booking platform that makes sustainable travel easier, attractive, more rewarding, and engaging. It incentivizes eco-friendly choices through a points-based reward system, allowing travellers to earn and redeem Eco Points for booking environmentally responsible tours and unlock sustainability badges for achieving key milestones. The platform enhances transparency with sustainability metrics and enables direct contributions to climate action, through tree planting game elements. By incorporating ecogamification, this system enhances traveller engagement and motivation to make greener travel decisions. PlanitGreen is built using ASP.NET Core MVC in a three-tier client-server architecture, ensuring scalability and maintainability. The backend is developed with C# .NET 8 and Entity Framework Core 8.0.0, interacting with a SQL Server database for efficient data management. The frontend leverages HTML, CSS, and JavaScript. By embedding sustainability features into a conventional booking app, PlanitGreen addresses a key limitation of existing standalone eco-gamified platforms, which tend to appeal primarily to users who are already invested in environmental causes. This integration enables broader engagement by presenting sustainable options within a context that users are likely to engage with regardless of their environmental priorities. Thus, the project demonstrates how thoughtful software design can drive real-world change through simple, user-focused innovation.

2025-01-01T00:00:00Z Thennakoon, Tharindu http://dlib.iit.ac.lk/xmlui/handle/123456789/2996 2026-03-17T07:12:47Z 2025-01-01T00:00:00Z

Requirement Based Academic Matchmaking Platform for Academic Institutes Thennakoon, Tharindu This project focuses on designing, developing, and evaluating Lecture Link, a web-based platform intended to connect Sri Lankan academic institutions with qualified visiting lecturers. Targeting the higher education sector, the system addresses the challenges of lecturer recruitment by implementing a requirement-driven matchmaking mechanism based on lecturer expertise, subject compatibility, and institutional standards. The main purpose of the software is to streamline lecturer selection processes, reduce full time staff workload, and enhance teaching quality through a responsive, scalable, and secure platform. It enables institutions to register, post subject requirements, and match with suitable visiting lecturers, while lecturers can manage profiles and express interest in academic opportunities. The backend of the application is built using Java Spring Boot, leveraging technologies such as Hibernate ORM, MySQL database, Firebase Storage for file management, Spring Security for authentication, and JavaMailSender for notifications. Machine learning functionalities, including lecturer prediction, are powered by a separate Python Flask API using Scikit-learn, Pandas, NumPy, and Joblib. Communication between the backend and the AI API is achieved via RESTful services. The frontend is developed using React with TypeScript and styled using Tailwind CSS, ensuring a user-friendly and mobile-responsive interface. API interactions on the frontend are managed via Axios. The application is aimed at cross-platform compatibility, being accessible through all major web browsers on Windows, macOS, and Linux systems. This project combines modern web development practices, cloud integration, AI-assisted matching, and secure data management to create a sustainable solution for academic resource optimization in Sri Lanka.

2025-01-01T00:00:00Z Munasinghe, Isuru http://dlib.iit.ac.lk/xmlui/handle/123456789/2995 2026-03-17T07:09:44Z 2025-01-01T00:00:00Z

EventEase Event Management System Munasinghe, Isuru EventEase is a web application that specializes in event planning and management. It ensures an easy experience for event organizers and attendees. The project is built around the simplification of event management through creating, editing, registration, and tracking features. System also consist of vendor suggestion feature which suggests suitable vendors for organizers based on budget limitations and service type, making the event planning more convenient. The application has a three-layered structure with HTML, CSS, and JavaScript on the frontend, a PHP based backend, and MySQL database. The system also uses SendGrid API for to send emails when an attendee registers for an event. The system allows functional requirements such as user login, event creation and management, vendor suggestion, and dynamic dashboards. The non-functional requirements are based on security, scalability, and simplicity. The app is designed to protect against CSRF, XSS, and SQL injection attacks, so the data remain secure and the users safe. This project has utilized concepts borrowed from similar systems in order to offer an end-user-centric experience with a tilt towards simplicity of use, security, and efficient event management. The result is a well-built system catering to event organizers, attendees, and system administrators. The app on the whole shows how technology can make event planning easier as well as enhance user experience.

2025-01-01T00:00:00Z