School of Computing and Informatics Technology (CIT) Collection
Permanent URI for this collection
Browse
Recent Submissions
1 - 5 of 559
-
ItemContextualisation of syntactic interoperability data standards : a case for health information exchange in Uganda’s healthcare system(Makerere University, 2025)Syntactic interoperability data standards are vital for the seamless exchange and effective utilisation of healthcare information within contemporary health systems. This study focuses on contextualising these standards to advance digital healthcare in Uganda, aligning with the World Health Organisation’s (WHO) strategic framework for 2020-2025. This framework aims to overcome gaps across six building blocks to achieve the Sustainable Development Goal of good health and well-being by enhancing health information systems for improved patient care continuity. Contextualised syntactic interoperability standards are essential for ensuring that patient data is consistently collected, processed, shared, and stored in compatible formats, thereby facilitating interoperability across diverse healthcare environments. Uganda’s healthcare system faces unique challenges that impede effective utilisation of health data, including the absence of standardised data formats, inadequate technical infrastructure, and insufficient data governance policies. Additional barriers include a shortage of skilled personnel, a weak data use culture, limited resources, poor data quality, complacency, limited political will, and inadequate leadership. Existing data interoperability standards, which are predominantly designed for developed countries, often fail to address Uganda’s specific needs due to differing levels of health information management maturity. This study addresses a critical literature gap by presenting a pragmatic approach to contextualising syntactic interoperability data standards specifically for Uganda, contrasting with successful contextualisation in other countries. A systematic three-phase methodology was employed: First, a descriptive cross-sectional survey identified essential Health Information Exchange (HIE) standards using Design Science Research (DSR) methodologies, including brainstorming, systems review, and literature review. Second, standards were developed based on these requirements, covering areas such as patient identification, health information exchange registries, medical imaging management, system digitisation, security, privacy, and capacity building. The contextualized standards were validated by Uganda’s Ministry of Health experts and reviewed by digital health stakeholders using the HIIRETWG tool. Aligned with global frameworks, they aim to enhance data use, improve patient care, foster innovation, and strengthen efficiency and interoperability within Uganda’s healthcare system.
-
ItemAn Integrated Model for Implementing Digitalization in Ugandan Technical and Vocational Education and Training Institutions(Makerere University, 2025-10-29)Digitalization projects in Technical, Vocational Education and Training institutions have experienced high failure rates, exceeding 70%. These failures are attributed to a combination of technical, managerial, and strategic challenges, including inadequate infrastructure, poor oversight, weak regulatory frameworks, and limited stakeholder alignment. This study aimed to develop a model to guide the successful implementation of digitalization projects in Ugandan TVET institutions. The model tested in the study was informed by three theories. These were the Agency Theory as the foundational lens, and further strengthened by the DeLone and McLean Information Systems Success Model, and the Dynamic Capabilities Framework. These theories when integrated to address issues of governance, system effectiveness, and institutional adaptability, which are critical for long-term success in digitalization initiatives. The study adopted a pragmatic research philosophy, an abductive approach, and a design science methodology, the study involved participants from selected Technical and Vocational Education and Training institutions across various districts in Uganda. A purposive and stratified sampling approach was used to ensure representation across administrators, instructors, and other key stakeholders involved in digitalization efforts. The analysis of data from the field study was conducted using Structural Equation modeling (SEM), with tools such as SPSS and SmartPLS. The results revealed that process quality significantly improves communication (β = 0.593, p < 0.001), which in turn enhances project outcomes (β = 0.411, p < 0.001). Monitoring emerged as a key mediating factor (β = 0.382, p <0.01), while goal conflict was found to inversely relate to digitalization success (β = - 0.326, p < 0.05). Outcome-based contracts, however, did not show a significant effect (β = 0.107, p = 0.152). Reliability analysis showed strong internal consistency across key constructs, with Cronbach‘s alpha values exceeding 0.7 (e.g., Power = 0.831; Politics = 0.872; Counterproductive Multitasking = 0.920; User Satisfaction = 0.839). The study contributes to theory by extending Agency Theory in the context of public sector digitalization, integrating insights from systems success and dynamic capability literature. Practically, it offers a structured model for improving digitalization outcomes through enhanced monitoring, stakeholder communication, and attention to governance and institutional responsiveness, which are factors particularly relevant in developing country contexts like Uganda.
-
ItemDeep learning based models for yield estimation using drone imagery(Makerere Universtity, 2025)Agriculture plays a crucial role in the economies of developing countries, contributing 37% to gross domestic product (GDP), nearly 60% to export earnings, and providing employment for over 76% of the population. Accurate crop yield estimation is essential for optimizing agricultural practices, ensuring food security, and enhancing economic stability. Traditional yield estimation methods, such as actual fruit counts, can exceed optimal numbers by 10 to 20 fold. Modern agricultural techniques, like deep learning, are required to manage yield components more effectively. This study developed deep learning models for yield estimation using the collected highresolution drone imagery. The research involved systematically collecting and annotating the drone image dataset for coffee, cashew and cocoa, developing advanced image classification and object detection models, and integrating these models into a robust yield estimation pipeline. The dataset collection was a collaborative effort involving the Makerere Artificial Intelligence Lab, Marconi Research and Innovation Lab, National Coffee Research Institute (NaCORI), and KaraAgroAI. We used different machine learning approaches, including traditional methods, deep learning, transfer learning, and foundation models, to find the best image classification model. The custom deep learning model emerged as the best, with an overall accuracy of 99% in classifying various crop types. For the object detection model, state-of-the-art YOLO (You Only Look Once) models and transformer models were customer-trained on our dataset, and YOLOv9 had better precision in identifying and locating the crops, with mean Average Precision (mAP) scores of 0.832 for cocoa, 0.546 for coffee, and 0.543 for cashew. We then used a Python package called Supervision to count the detected crops as the yield estimation system in the image. The image classification and object detection models were then used to develop a yield estimation pipeline in this study, which has proven to be accurate, providing a practical solution for real-time yield prediction. However, the study also encountered limitations, including constraints in data collection and a focus on a limited number of crops (only three were considered for yield estimation), high-resolution requirements, and significant computational resource needs. To address these limitations, we recommend expanding data collection efforts, utilizing more accessible technology, improving computational efficiency, and creating automated annotation tools. Furthermore, future research should explore multispectral and hyperspectral imaging, real-time monitoring systems (including using these models on video, not just images), and longitudinal studies to enhance yield estimation accuracy and applicability.
-
ItemAn electronic recruitment monitoring information system for external labour agencies in Uganda(Makerere University, 2023)This study covers a system designed for monitoring and keeping track of migrant workers by Ministry of Gender Labour and Social Development and external recruitment agencies from Uganda. To achieve this goal, a research study was carried out using interviews and questionnaires, as well as an analysis of the existing monitoring systems. Relevant documentation was also undertaken as a contribution to the knowledge base. Working from the literature review, questionnaires, and interviews; limited, inadequate, immigrant workers information was the main challenge faced by Ministry of Gender and Social Development in monitoring their safety at destination countries resulting into poor coordination among stake holders. The other reasons included unlicensed external recruitment companies that smuggle out migrant with attempt of dodging taxes, high charges levied on external laborer’s, ignorance /lack of pre-departure training of migrant workers about their destinations and emergency contacts which has resulted into poor monitoring and coordination among stake holders. It is from those challenges that this study was conducted to identify and collect requirements using Interviews and Questionnaires. Unified Modelling (UML) was used to document the system development process, producing artifacts like Use Case, activity diagrams, etc. The system was implemented using native Java for Android. With a firebase database which is a backend-as-a-service and also supports other environments like JavaScript/html5 frameworks. It offers real-time databases, different Application Programming Interfaces, multiple authentication types, and hosting platforms. The system also fetches real-time data using a NoSQL serverless Backend as a service also known as Baas service with a firebase database to store data. The Interfaces were implemented using Java and XML. The final product was a system that merges different stake holders of labour export in one centralized location for easy monitoring and coordination. The developed system enables migrant workers to make real time emergency alerts and also randomly check inn at their destinations enabling MGLSD, labour agencies and next of keen to keep track of them, making it very easy to plan for their trips since they will have all the relevant and required information.
-
ItemA security framework for preventing man in the middle attacks in mobile banking applications: a case of mobile banking services in Uganda(Makerere University, 2023)The surge in mobile banking applications in developing nations, like Uganda, has transformed financial inclusion. However, it has exposed these services to man-in-the-middle (MitM) attacks. This study focused on MitM challenges in Uganda's mobile banking and aimed to create a tailored security framework. Leveraging the UTAUT2 model, we proposed a comprehensive framework, including performance and effort expectancy, social influence, facilitating conditions, price value, and hedonic motivation. Security aspects like perceived system security, security risk, and MitM risk were also integral. A survey of 230 respondents in Kampala, Uganda, analyzed via PLSSEM, revealed insights into MitM impacts and strategies to mitigate risks. Our research contributes a context-specific security framework to fortify mobile banking in Uganda, addressing unique challenges, fortifying confidentiality, and maintaining trust. The results underscore proactive measures to secure mobile banking from MitM threats, providing practical implications for stakeholders and policymakers. Ultimately, our research aims to cultivate a safer mobile banking environment in Uganda, supporting financial inclusion with secure and reliable services.