School of Computing and Informatics Technology Collection

Browse

Recent Submissions

Now showing 1 - 5 of 639
  • Item
    Semi-autonomous fire-fighting robot system
    (Makerere University, 2026) Galiwango, Ananda ; Naggayi, Daphne Pearl ; Nannozi, Racheal ; Nalunkuma Ketra
    Main Objective: The main objective of this project is to design and implement a semi-autonomous fire-fighting robot capable of detecting, localizing, navigating to, and extinguishing fires using a low-cost embedded system. Specific Objectives: 1. To assemble and develop an integrated fire response system capable of detecting fire, estimating its location, providing real-time monitoring and control through a user interface, and suppressing the fire using a water pump mechanism. 2. To implement the A* path planning algorithm for efficient and optimal navigation of the robot towards the fire location while avoiding obstacles. 3. To design and implement an ultrasonic-based obstacle detection and avoidance system to ensure safe navigation in dynamic indoor environments. 4. To evaluate the overall system performance based on key metrics such as fire detection accuracy, response time, navigation success rate, obstacle avoidance efficiency, and fire suppression effectiveness in a controlled environment. Final Remarks: The developed system demonstrates the potential of combining embedded systems, robotics and wireless communication for real-world fire safety applications. With further enhancements, the system can be adapted for deployment in larger and more complex environments such as industrial buildings and warehouses.
  • Item
    IOT-enabled environmental monitoring in black soldier fly farming
    (Makerere University, 2026) Tashobya, Aronda Darlin; Magala, Hillary Jefferson; Linda, Cherise and Sekamalira, Dauda.
    Black Soldier Fly (BSF) farming is increasingly being adopted as a sustainable approach for organic waste management and production of protein-rich biomass for animal feed. However, successful BSF larvae production depends on maintaining suitable environmental conditions such as temperature, humidity, substrate temperature, light intensity, ammonia concentration, and biomass development. At TASH Farm in Mbarara District, Uganda, environmental monitoring was mainly carried out through manual observation and camera-based supervision, which limited continuous measurement, historical tracking, timely detection of abnormal conditions, and structured reporting. This project aimed to design and implement an IoT-enabled environmental monitoring system for Black Soldier Fly farming. The system was developed using an iterative prototyping approach. Requirements were gathered through observation, interviews, questionnaires, and review of related literature and existing IoT monitoring systems. The developed prototype consists of a web-based dashboard, user authentication, role-based access control, monitoring node management, environmental data visualization, threshold-based alerts, analytics, CSV export, and PDF report generation. The frontend was implemented using React, TypeScript, Vite, and Tailwind CSS, while Supabase PostgreSQL was used for backend services, authentication, and database storage. Firebase Hosting was used to deploy the system online through the project domain. Due to time and procurement constraints affecting full physical sensor integration, the deployed prototype was validated using simulated environmental datasets. The simulated readings were inserted into the Supabase database and used to test dashboard visualization, multi-node monitoring, analytics, alerts, and report generation. The validation produced daily, weekly, and monthly reports, with the daily report showing 463 data points, average temperature of 29.2°C, average humidity of 70.5%, average ammonia of 14.4 ppm, and biomass growth of +3.8%. The weekly and monthly reports each summarized 1,000 data points, confirming that the system could process and report environmental data over different time ranges. The project demonstrates how Information Systems and IoT-ready technologies can support environmental monitoring in BSF farming. Although full live sensor deployment remains future work, the developed prototype provides a functional foundation for real-time sensor integration, improved farm monitoring, alerts, reporting, and future predictive analytics.
  • Item
    Tracking management information system for EEMS
    (Makerere University, 2022) Nahurira, Elizabeth ; Atwongyeirwe, Emmanuel ; Kobuganzi, Penlope ; Amanya, Edwin ; Kantono, Vanessa
    Main Objectives: To develop a Management Information System for EEMIS that will handle tracking of the workers sent abroad by different approved export companies and monitored by the relevant authorities. Specific Objectives: 1. To identify requirements that will be used in the development of the system. 2. To design a web-based system for tracking at EEMIS Uganda. 3. To implement the designed system. 4. To test and validate the implemented system.
  • Item
    An online appointment management system for Mengo Hospital
    (Makerere University, 2023) Makiika, Sarah Mulonge ; Balinonye, Trevor Mark ; Aryet, David ; Munyagwe, Edgar ; Natosha, Sarah
    With the enhancement in technology, so many aspects in different fields are also embracing and advancing in new technology. We managed to work on a system that automates the visitor's appointment management process in hospitals, identifying our case study as Mengo hospital Uganda. This hospital already has a manual system in place which records visitors information manually, and with this kind of operation, of course we expect so many vulnerabilities here and there not forgetting inefficiencies. The purpose of this research proposal is to deliver an online appointment management system for hospitals like Mengo, and this proposed system will enhance building security, improve visitor experience, and effectively monitor, track, and record visitor information. In order to achieve the above objectives, our system is exclusively enhanced with features such as pre-registration, contactless check-in, real-time monitoring and tracking, advanced security features including health screening measures.
  • Item
    Interpretable foot and mouth disease detection
    (Makerere University, 2025) Zirimabagabo, Anslem ; Kawooya, Barry Isaac ; Namuwanga, Aisha
    Foot and Mouth Disease (FMD) is a highly contagious viral infection that hinderslivestock production, resulting in severe economic losses in Uganda[21]. This study investigates an interpretable machine learning approach to FMD detection by using two distinct datasets: a numerical dataset sourced from Uganda for early detection, and an image based dataset collected from the internet for visual diagnosis. Exploratory Data Analysis (EDA) was conducted to assess feature distributions, identify class imbalances, and uncover correlations among epidemiological and environmental factors such as rainfall, temperature, livestock density, and geographic proximity to national parks and borders[5]. A total of six models were developed—four trained on the numerical dataset and two on the image dataset. For early detection, models including Random Forest, Support Vector Machine (SVM), Logistic Regression, and Gradient Boosting were evaluated. The XGBoost model, when combined with the Synthetic Minority Oversampling Technique (SMOTE), achieved the highest accuracy of 82%. However, performance decreased in scenarios involving dynamic or imbalanced data distributions, underscoring the need for adaptive learning strategies.[15] In the image-based classification task, deep learning models comprising a custom Convolutional Neural Network (CNN) and ResNet50 were implemented. Among these, ResNet50 achieved the highest accuracy of 97%, demonstrating strong potential for visual FMD symptom detection. To enhance transparency and model trustworthiness, SHAP was employed to explain feature importance in numerical models, while Grad-CAM was used to generate class activation maps for CNN-based image models[14]. This report emphasizes the value of integrating explainable artificial intelligence (XAI) and adaptive machine learning in livestock disease diagnostics. The proposed approach provides a foundation for developing robust, data-driven decision support systems to strengthen early warning and surveillance mechanisms for FMD in Uganda.