School of Computing and Informatics Technology Collection
Permanent URI for this collection
Browse
Recent Submissions
1 - 5 of 632
-
ItemCarbon dioxide emission monitoring and information dissemination system (CEMIDS)( 2024)This project addresses the critical issue of monitoring Carbon dioxide emissions to combat climate change. The specific objectives included reviewing literature and conducting field studies to identify system requirements, designing a system based on these requirements, and implementing a web-based platform. The developed Carbon dioxide Emission Monitoring and Information Dissemination System (CEMIDS) utilizes an ESP32 microcontroller and MH-Z19 Carbon dioxide sensor to collect real-time data, which is then processed by a Django-based backend and visualized through a React.js web application. Integrations with Firebase, Twilio, and ThingSpeak enhance the system's functionality by ensuring secure authentication, real-time alerts, and robust data logging. Comprehensive testing validated the system's performance, usability, and security. Despite limitations such as budget constraints, the project effectively meets its objectives, providing valuable data for policymakers, raising community awareness, and promoting sustainable industrial practices. Future work will expand sensor coverage, enhance analytics, and improve user engagement features, demonstrating the system's potential to contribute significantly to climate action efforts.
-
ItemSquint eye detection system(Makerere University, 2023)This book begins by showing the Github repository and the blog used by the team to develop the system. It describes the software Design Document (SDD) for our project that guided us to implement the system. These are the sections included in the SDD, Introduction to the project purpose and scope, system overview, system architecture, Data design, component design, Human interface design and requirements matrix for the system. It also describes the report of our system after the implementation. Which includes, introduction, system specifications, Design output, inspection and testing, installation and system acceptance, performance, servicing, maintenance and phase out, conclusions and recommendations. This book also contains the user manual guide, which will help users of the system (Squint Eye Detection System) on how to interact with it.
-
ItemAI therapist App - your personal mental health companion(Makerere University, 2025)Mental health challenges affect millions globally, yet access to quality care remains limited due to cost, stigma, and scarcity of trained professionals. This research addresses this gap by developing an AI Therapist Web app using Retrieval Augmented Generation (RAG) models trained on validated medical literature. The system provides accessible, evidence-based mental health support while emphasizing responsible AI implementation. Our methodology combined software development using Ruby on Rails, machine learning techniques, and user-centered design principles. We leveraged Google’s Gemini 2.0 as our foundation model for the RAG implementation, enhancing its capabilities with domain specific knowledge retrieval. This research contributes to the growing field of AI in healthcare while addressing critical accessibility challenges in mental health support. The developed system serves as a complementary tool to traditional therapy, potentially reducing barriers to care for underserved populations.
-
ItemCheptoyek, B., Lema, A., Bazziwe, M., Nkinzi, K. (2025). A crowdsourced local news platform for Uganda. (Unpublished research project). Kampala, Makerere University.(Makerere University, 2025)This report presents the design, development, and implementation strategy for a crowdsourced local news platform specifically tailored for Uganda. The main goal is to fill the gap in reliable news, especially in rural areas where access is often limited. Our platform aims to give communities more say in what gets reported, while making sure the news is accurate and trustworthy by blending Artificial Intelligence (AI) with blockchain technology. Core Features and Strategy At the core of it all is a strong verification system. AI tools help us fact-check stories and confirm that the content is genuine. Meanwhile, blockchain keeps a transparent, unchangeable record of all approved news, building confidence across users. Customized for Uganda: • Multimedia Support: Support for various media (text, photos). • Gamification: Features that motivate community members to contribute high-quality content. • Localized Filtering: Users can filter news feeds based on where they are and what interests them. Overcoming Challenges The verification process is automated and optimized, combining machine learning with community input for quick, reliable results. We also dive into some of the biggest obstacles, such as: • The need for local data to train AI models effectively. • Ensuring verification works well even with poor internet connections. • Keeping users engaged over time. This project marks a major leap forward in giving Ugandan communities the tools to access and share trustworthy local news, laying the groundwork for grassroots journalism. The tech and strategies we're developing could be a model for other regions around the world facing similar challenges around getting reliable information. News Classification The news will be classified into three critical types: • Verified: Content verified as factual and accurate. • Fake: Content containing false or misleading information. • Propaganda: Content designed to influence opinions or behaviors through biased or misleading reporting
-
ItemAI-based exam question generation system for UBTEB(Makerere University, 2026)The increasing demand for scalable and efficient examination systems in technical and vocational education has highlighted the limitations of traditional manual question-setting processes. This project presents the design and development of an AI-Based Exam Question Generation System tailored for the Uganda Business and Technical Examinations Board (UBTEB). The system leverages Natural Language Processing (NLP) techniques using the T5 Valhalla transformer model and incorporates a lightweight Retrieval method. It enables automated generation of high-quality, curriculum-aligned examination questions from both structured (curriculum documents) and unstructured (examiner input) content. The system is designed with offline capability to ensure security and usability in resource-constrained environments. Evaluation results demonstrated that the system produced syntactically correct, semantically relevant, and non-repetitive questions across various subjects, achieving a BLEU score of 0.371 and high approval ratings from domain experts. The project contributes a practical, scalable, and secure solution for modernizing assessment in Uganda’s technical education sector and sets a foundation for broader applications in educational tools.