School of Computing and Informatics Technology (CIT)

Permanent URI for this community

http://10.29.1.53:4000/handle/10570/37

Browse

Browsing School of Computing and Informatics Technology (CIT) by Title

  • Item
    A computer vision approach towards glare mitigation and image quality enhancement in license plate recognition
    (Makerere University, 2025) Masaba, Jeremiah
    License Plate Recognition (LPR) systems play a crucial role in Intelligent Transportation Systems (ITS), facilitating automated vehicle identification for applications such as traffic monitoring, law enforcement, and toll collection. However, these systems often suffer from glare-induced distortions caused by intense light sources such as sunlight, vehicle headlights, and reflections. These distortions obscure license plate details, leading to reduced Optical Character Recognition (OCR) accuracy and compromised system reliability. This research addresses this critical challenge by developing a unified computer vision framework that integrates Autoencoders (AE) and Noise2Clean Generative Adversarial Networks (N2C-GAN) to mitigate glare and improve image quality. The study aimed to achieve four key objectives: access and utilize an existing dataset of glare-induced license plate images, image pre-processing, model implementation, and rigorous model evaluation. The proposed model demonstrated significant advances in glare mitigation, achieving a Peak Signal-to-Noise Ratio (PSNR) of 38.8 dB, a Structural Similarity Index Measure (SSIM) of 0.987, and a Visual Information Fidelity (VIF) of 0.8896. Furthermore, the model improved the accuracy of OCR to 99.9% using Google Cloud Vision OCR, underscoring its effectiveness in restoring license plate readability under glare conditions. Computational efficiency was a key focus, with a compact model size of 298 kB and a runtime of 0.7263 s, making it scalable for real-world deployment. Despite encountering limitations such as dataset bias and computational constraints, this research provides valuable insights and lays the groundwork for future advances in glare mitigation, image processing, and machine learning-based LPR enhancements. The findings have broad implications for transportation management, public safety, and automated enforcement, offering a robust solution to improve the performance and reliability of LPR systems in diverse real-world applications.
  • Item
    A digital enabled care coordination framework for patients with diabetes in Uganda
    (Makerere University, 2025) Male, Lincoln
    This study aimed to design a Digital Enabled Care Coordination Framework (DECCF) to improve diabetes management in Ugandan hospitals through the use of ICTs. It was motivated by the persistent challenge of fragmented care, through which there is limited coordination among healthcare workers and this affects the quality of diabetic care. The objective was to develop a framework that digitally links care teams and supports patients in managing their condition. Using a Design Science approach, data was collected from healthcare workers involved in diabetic care through purposive sampling. The study involved St. Francis Nsambya Hospital, Kisenyi Health Centre IV, Mengo Hospital, Nakasero Hospital, and Nkozi Hospital. Data was collated using structured questionnaires and analysed descriptively using Microsoft Excel 21. Findings showed a strong need for a unified digital platform to integrate information from ubiquitous sources such as health records, telehealth consultations, patient portals and decision support tools. The study concluded that the DECCF can improve diabetic care by improving coordination and patient engagement. The study also recommended piloting the framework in real hospital settings, improving ICT infrastructure, and training healthcare teams in digital tool usage.
  • Item
    A digital finance model for financial inclusion of women in Makindye Division
    (Makerere University, 2025) Yahaya, Saidi
    Financial inclusion is a key driver of economic growth, particularly in developing countries where large portions of the population, especially women, remain unbanked and underserved by formal financial institutions. In Uganda, over 54% of financially excluded adults are women, who face significant barriers to accessing digital financial services, including affordability, lack of digital literacy, and socio-cultural restrictions. These challenges limit their ability to save, access credit, and participate fully in the digital economy. Despite various initiatives, a significant gap remains in addressing the specific challenges women face in accessing and utilizing digital financial services. The purpose of this study was to develop a digital finance model aimed at enhancing the financial inclusion of women in Makindye Division, Uganda. The study sought to identify requirements for the digital finance model for financial inclusion of women, design a digital finance model for financial inclusion of women in Makindye division and test the effectiveness of the designed digital finance model. A mixed-method approach was employed, combining both quantitative and qualitative data collection. Survey questionnaires were administered to 362 women while in-depth interviews were conducted with 10 mobile money/banking agents within Makindye Division. The quantitative data was analyzed using IBM-SPSS for descriptive and inferential statistics, including correlation and regression analysis, to test the relationships between digital finance and financial inclusion. The results revealed significant positive correlations between digital finance and financial inclusion, with digital infrastructure access, digital literacy, affordability of digital financial services, perceived risk and privacy concerns being critical factors. The study found that women face several barriers, including limited access to digital devices, poor network quality, high costs of internet services, and lack of formal training. The developed digital finance model was tested as an effective tool for enhancing financial inclusion among women in Makindye division. The study has important implications for policymakers and financial service providers. It offers a practical model that can be adopted to address the financial inclusion gap among women, particularly by promoting digital literacy, expanding digital infrastructure, and reducing the cost of digital financial services. This research provides valuable insights for fostering a more inclusive financial ecosystem in Uganda and other similar developing context
  • Item
    A framework for detecting and transcribing multilingual speech in low resource languages
    (Makerere University, 2025) Abigaba, Wilson
    This dissertation presents the development and evaluation of a novel multilingual automatic speech recognition (ASR) framework specifically designed for low-resource Ugandan languages, with focus on Luganda and Runyankole-Rukiga. The research addresses a critical gap in language technology by creating the first deep learning-based ASR system capable of transcribing speech in these Bantu languages, which collectively serve over 8 million speakers in Uganda but have historically been underrepresented in speech recognition technologies. The study employed transfer learning techniques by fine-tuning OpenAI's Whisper model on a custom-curated dataset of 2,000 speech samples comprising approximately 12 hours of audio data. The developed framework achieved a Word Error Rate (WER) of 50% for Luganda and 60% for Runyankole-Rukiga, with corresponding Character Error Rates (CER) of 22% and 28% respectively. These results represent significant improvements over baseline models, demonstrating WER reductions of up to 45% compared to non-fine-tuned systems. The framework incorporates a language detection module capable of identifying language switches with 78% accuracy, enabling real-time multilingual transcription scenarios common in Uganda's multilingual contexts. A comprehensive evaluation involving both technical benchmarks and user studies with 20 participants validated the framework's effectiveness, efficiency, and usability. The system achieved a System Usability Scale (SUS) score of 76.5, indicating above-average usability, with users rating transcription quality at 4.1 out of 5 stars. Performance analysis revealed that the model handles various acoustic conditions, speaker demographics, and speech rates with reasonable accuracy of 78.5%, though challenges remain with highly code-switched utterances and low-frequency vocabulary. The research makes several key contributions to the field of low-resource language processing: (1) creation of the first Whisper-based ASR system for Luganda and Runyankole-Rukiga; (2) demonstration of effective transfer learning strategies for Bantu languages; and (3) validation of practical deployment approaches for resource-constrained environments. The framework is designed with scalability in mind, providing a foundation for expansion to additional Ugandan languages and similar low-resource contexts across Africa. This work has significant implications for linguistic preservation, digital inclusion, and practical applications in healthcare, education, and government services within Uganda. By enabling speech-based interfaces in local languages, the framework contributes to bridging the digital divide and preserving cultural identity in an increasingly AI-driven world. Future work will focus on expanding the dataset, incorporating more speakers and dialects, implementing full code-switching detection capabilities, and deploying the system in real-world applications. Keywords: Automatic Speech Recognition, Low-Resource Languages, Multilingual ASR, Luganda, Runyankole-Rukiga, Transfer Learning, Whisper, Bantu Languages, Language Technology, Uganda
  • Item
    A framework for mitigating fairness and ethical challenges of large language models in Africa
    (Makerere University, 2025) Namuwaya, Hajarah Ali
    The exponential growth of Large Language Models (LLMs), such as GPT-4, LLama2, BARD, and Falcon, underscores the urgency for robust frameworks to address fairness and ethical concerns in their deployment, particularly in the African context. This thesis proposed an innovative framework tailored to mitigate fairness and ethical challenges associated with LLMs in Africa. Drawing upon diverse methodologies and metrics, our framework offers a comprehensive approach to assess and address biases, promote transparency, and ensure equitable outcomes. By emphasizing the importance of representative training data and stakeholder collaboration, our framework seeks to foster responsible development and deployment of LLMs in Africa, balancing technological innovation with ethical considerations. The methodology employed involved a multi-dimensional approach, drawing upon insights from diverse stakeholders, literature review, and empirical analysis. Extensive research was primarily conducted to identify existing frameworks, ethical guidelines, and best practices in AI governance followed by a series of consultations with experts in AI ethics, linguistics, and African studies to tailor the framework to the unique socio-cultural context of Africa. The input from these consultations informed the selection of key dimensions for assessment, such as data diversity, transparency, and community engagement. This study employs Design Science Research methodology to develop and validate a framework for mitigating fairness and ethical challenges of Large Language Models in Africa, informed by African contextual factors including linguistic diversity, cultural values, resource constraints, and data availability. Pilot studies were conducted using sample datasets to validate the efficacy of the framework in identifying and mitigating biases in LLMs and the preliminary results indicated promising outcomes, with the framework demonstrating its ability to enhance fairness and ethical accountability in LLM deployment and this developed framework serves as a guiding resource for policymakers, researchers, and practitioners, facilitating informed decision-making and ethical governance of LLMs in the African context.
  • Item
    A framework for supporting information sharing and reuse in e-government service delivery in Uganda
    (Makerere University, 2025) Ajuna, Newton Brian
    Uganda’s public sector continues to face significant challenges in information sharing and reuse among Ministries, Departments, and Agencies (MDAs), despite notable investments in ICT infrastructure and e-government systems. Fragmented data ecosystems, limited interoperability, and redundant data management processes hinder effective service delivery. This study addresses these challenges by proposing a context-specific framework for supporting secure and scalable information sharing and reuse across MDAs. Grounded in a thorough literature review and a comprehensive analysis of Uganda’s institutional context, the study adopts the Design Science Research (DSR) methodology. Through iterative design, evaluation, and refinement cycles, the study integrates findings from document reviews and empirical data collected via a national survey targeting ICT professionals and data managers. Key challenges and requirements were categorized using the PESTEL (Political, Economic, Social, Technological, Environmental, and Legal) framework. The resulting framework SIRAM (Supporting Information Reuse Among MDAs) is an adapted version of Estonia’s X-Road framework, extended to suit Uganda’s unique governance and operational environment. SIRAM incorporates components such as policy harmonization, metadata standards, legal alignment, stakeholder trust-building, and capacity development. Visual modeling was conducted using Visual Paradigm. To evaluate the framework, structured walkthroughs were conducted with 15 experts from URA and peer MDAs. Evaluation results confirmed the framework’s conceptual relevance, usability, and institutional applicability. The study concludes by emphasizing the need for coordinated legal reform, investment in capacity-building, and centralized governance structures to unlock the full benefits of e-government interoperability in Uganda. Future studies may extend the framework by testing its scalability across MDAs, integrating with UGHUB, and examining policy adoption challenges. Future work will pilot SIRAM across additional MDAs and refine governance, legal, and technical guidelines by sector. It will also evaluate capacity needs and the costs and benefits of nationwide adoption.
  • Item
    A framework for supporting the accessibility of e-learning platforms for students with visual impairements in higher education institutes in Uganda: a case study of Kyambogo University
    (Makerere University, 2025) Omagoro, Ivan
    E-learning is a rapidly growing trend in education, but it is not fully accessible to people with visual impairments, despite their increased enrolment in higher education. It has the potential of reaching of reaching out many students in an accessible way, including those with disabilities if it designed with the needs of learners with disabilities in mind; which is not the case for Ugandan Universities. This study set out to develop a framework for supporting the accessibility of e-learning platforms for This study was defined by the following main objective; To design a framework for supporting the accessibility of e-learning platforms for students with visual impairments in HEIs in Uganda and to achieve this the following specific objectives were formulated; To determine the requirements for a framework for supporting accessibility in e-learning platforms for students with visual impairment, to design a framework that supports the accessibility of e-learning platforms for students with visual impairment and to evaluate the designed framework for environmental utility using. This study adopted an abductive approach and used a design science research methodology to guide the research. Adobe Illustrator CC was used for to visualize the framework proposed by this study. The key findings were that necessary guidelines, best practices and assistive technologies to enhance the accessibility of e-learning platforms are available. However, the e-learning administrators responsible for implementing these learning systems possess insufficient expertise in this domain. The developed framework was evaluated in terms of its environmental utility and accessibility. The evaluation aimed to assess the framework's usefulness within the given context and its alignment with the established accessibility guidelines and company best practices pertinent to visually impaired learners. The scholarly contribution of this study was threefold: providing insights into addressing the issue of limited accessibility in e-learning, documenting a framework to support accessibility of e learning for students with visual impairments, and sharing the experiences from problem definition to artifact evaluation.
  • Item
    A framework for the adoption of social media in crime investigations: case of Uganda Police in Kampala Metropolitan Area
    (Makerere University, 2025) Adupa, Bob Bruno
    The exponential rise of social media platforms presents unique opportunities for enhancing crime investigation efforts within law enforcement agencies. This study investigates the integration of social media into crime investigation processes within the Uganda Police Force (UPF), focusing on the Kampala Metropolitan Area. Despite technological advancements and increased smartphone usage, the UPF has faced significant challenges in leveraging digital tools for timely evidence gathering, suspect identification, and digital forensics. This research aimed to develop a practical framework to guide the adoption and use of social media in crime investigations. Using a Design Science Research (DSR) methodology complemented by an abductive research approach, the study collected primary data through structured questionnaires distributed to police personnel and analysed it using statistical tools. It further reviewed existing global frameworks and theoretical models such as the Technology Acceptance Model (TAM), Unified Theory of Acceptance and Use of Technology (UTAUT), and Crime Pattern Theory to inform framework development. Findings indicated that perceived usefulness, ease of use, organizational support, training, and investigative protocols significantly affect social media adoption for crime investigations. The final framework was structured in three phases: pre-adoption, adoption, and post-adoption, each addressing specific functional, organizational, and technical requirements for digital investigation. The framework was validated through expert reviews and statistical analysis, demonstrating its potential to improve digital evidence collection, suspect identification, witness location, and investigative efficiency. The study contributes to both academic research and practical implementation by offering a structured, context-specific model that can be adapted by law enforcement agencies across similar settings.
  • Item
    A framework to support water leakage reporting at water supply networks through crowdsourcing: a case study of National Water and Sewerage Corporation, Uganda
    (Makerere University, 2025) Akiror, Elizabeth
    Water leakage remains a critical challenge in urban water distribution networks in developing countries; however, beyond physical infrastructure failures, ineffective water leakage reporting mechanisms significantly limit timely detection and response. In many utilities, leakage reporting is constrained by low public participation, unclear or inaccessible reporting channels, language barriers, and limited trust in institutional responsiveness, resulting in delayed interventions and increased non-revenue water. To address this reporting gap, this study proposes a crowdsourcingbased framework to support effective water leakage reporting, using the National Water and Sewerage Corporation (NWSC) in Uganda as a case study. Guided by the Design Science Research (DSR) methodology, the study integrates theoretical insights with empirical data collected from NWSC staff and community members to design and refine the framework. The research process comprised three stages: problem identification and analysis, framework design and development, and expert evaluation. The resulting framework addresses key reporting-related challenges by strengthening citizen engagement, clarifying reporting procedures, enabling multilingual support, enhancing data validation, and promoting responsive institutional action within appropriate legal and ethical safeguards. Expert evaluation findings indicate that the framework has strong potential to improve the timeliness, accuracy, and scalability of water leakage reporting, thereby supporting more effective operational response and sustainable water service delivery. Overall, the study contributes a practical, ICT-enabled crowdsourcing solution and extends theoretical understanding of participatory approaches to water governance in developing country contexts.
  • Item
    A hybrid deep learning model for detection and mitigation of distributed denial of service attacks in software-defined networks
    (Makerere University, 2026) Emukuny, Martin
    The increasing adoption of Software-Defined Networking (SDN) has introduced flexibility and programmability in modern networks but has also exposed the SDN controller to Distributed Denial of Service (DDoS) attacks that exploit its centralized architecture. Existing intrusion detection approaches largely focus on detection without providing effective mitigation, and many rely on outdated or non-SDN datasets, limiting their real-world applicability. Furthermore, models based on single deep learning architectures often fail to capture both the spatial and temporal characteristics of DDoS traffic, leading to high false positive and false negative rates. This study proposes a hybrid deep learning model that integrates Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks for the detection and mitigation of DDoS attacks in SDN environments. The CNN component extracts spatial correlations among flow features, while the LSTM component captures temporal dependencies, thereby enhancing spatio-temporal learning. The model was trained and evaluated using the LR-HR DDoS 2024 dataset, an SDN specific dataset containing both low-rate and high-rate attacks. Data preprocessing included exploratory analysis, feature normalization, and class balancing using Synthetic Minority Oversampling Technique (SMOTE). The model was implemented in TensorFlow and deployed in a simulated SDN environment using Mininet and the OpenDaylight controller, where detected attacks were mitigated through dynamic flow rule enforcement. Experimental results show that the hybrid CNN–LSTM model achieved an accuracy of 98.7%, a precision of 0.987, a recall of 0.987, and an F1-score of 0.987, outperforming standalone CNN and LSTM models. The model further attained ROC-AUC and PR-AUC values of 0.995 and 0.993 respectively, with confusion matrix analysis confirming reduced misclassification rates. Although the hybrid model required slightly higher computational resources, 3.2 million parameters, an average training time of 47 minutes per epoch, and an inference latency of 3.1 milliseconds, it remained practical for real-time SDN deployment. Limitations include reliance on a single dataset, evaluation within a simulated testbed, and the exclusion of additional contextual features such as topology data. Future work should focus on validating the model with multiple real-world datasets, integrating attention mechanisms or transformer architectures, optimizing for lightweight deployment, and testing resilience against adversarial attack strategies.
  • Item
    A knowledge management portal to support the sharing of best practices in community-based obesity prevention and advocacy in Uganda
    (Makerere University, 2025) Kamukama, Diana
    Obesity has gradually become a silent epidemic in Uganda, contributing to rising rates of diet-related non-communicable diseases (NCDs) such as hypertension, type 2 diabetes, cardiovascular disease, and certain cancers leading to increased mortality. This alarming trend has placed considerable strain on Uganda’s health system and highlights critical gaps in community-level knowledge about effective practices for preventing and managing obesity. With limited focus by the government on actions that specifically target the prevention and management of obesity, there is a growing need for increased advocacy, particularly through knowledge sharing to engage communities in physical activity and promote diet modifications for healthier lifestyles. Knowledge Management (KM) has been proven to be a valuable approach to addressing health knowledge gaps by enabling access to, sharing of, and application of evidence-based practices within communities. However, the effective implementation of KM in the obesity care continuum remains largely untapped in Uganda. This study addresses that gap by developing a Knowledge management portal for Obesity Prevention and Advocacy (KOPA), a digital platform intended to serve as a single point of access to evidence-based best practices for obesity prevention and advocacy, targeting both healthcare professionals and community members. Using an Action Research approach, this study identified key challenges and user requirements that informed the portal’s design and implementation. KOPA combines a searchable library of best practices on healthy eating and physical activity, collaboration tools, content for different user groups, simple obesity-tracking, and clear Uganda-specific guidance on healthy lifestyle change. Evaluation with healthcare professionals and community members found it relevant, easy to use, and helpful for finding, organising, and sharing practical information that supports behaviour change. KOPA shows how a centralized, knowledge-driven platform can strengthen obesity prevention and advocacy in resource-constrained settings. Future work includes expanding multilingual content, introducing lightweight mobile access, connecting with Ministry of Health resources, and running a multi-site evaluation to confirm gains in knowledge, activity, and diet quality.
  • Item
    A knowledge management portal to support the sharing of best practices in community-based obesity prevention and advocacy in Uganda
    (Makerere University, 2025) Kamukama, Diana
    Obesity has gradually become a silent epidemic in Uganda, contributing to rising rates of diet-related non-communicable diseases (NCDs) such as hypertension, type 2 diabetes, cardiovascular disease, and certain cancers leading to increased mortality. This alarming trend has placed considerable strain on Uganda‘s health system and highlights critical gaps in community-level knowledge about effective practices for preventing and managing obesity. With limited focus by the government on actions that specifically target the prevention and management of obesity, there is a growing need for increased advocacy, particularly through knowledge sharing to engage communities in physical activity and promote diet modifications for healthier lifestyles. Knowledge Management (KM) has been proven to be a valuable approach to addressing health knowledge gaps by enabling access to, sharing of, and application of evidence-based practices within communities. However, the effective implementation of KM in the obesity care continuum remains largely untapped in Uganda. This study addresses that gap by developing a Knowledge management portal for Obesity Prevention and Advocacy (KOPA), a digital platform intended to serve as a single point of access to evidence-based best practices for obesity prevention and advocacy, targeting both healthcare professionals and community members. Using an Action Research approach, this study identified key challenges and user requirements that informed the portal‘s design and implementation. KOPA combines a searchable library of best practices on healthy eating and physical activity, collaboration tools, content for different user groups, simple obesity-tracking, and clear Uganda-specific guidance on healthy lifestyle change. Evaluation with healthcare professionals and community members found it relevant, easy to use, and helpful for finding, organising, and sharing practical information that supports behaviour change. KOPA shows how a centralized, knowledge-driven platform can strengthen obesity prevention and advocacy in resource-constrained settings. Future work includes expanding multilingual content, introducing lightweight mobile access, connecting with Ministry of Health resources, and running a multi-site evaluation to confirm gains in knowledge, activity, and diet quality.
  • Item
    A knowledge sharing framework for secondary schools in Uganda
    (Makerere University, 2025) Agaba, Silver
    This study developed a knowledge-sharing framework for secondary schools in Uganda, aimed at addressing the challenges of poor collaboration and communication among teachers and students. The research identified a lack of efficient knowledge- sharing systems as a critical issue contributing to inequalities in educational outcomes. The framework was designed to leverage ICT tools and infrastructure to facilitate the sharing, storage, and retrieval of educational resources, foster collaboration, and improve teaching and learning outcomes. A mixed-methods approach was employed, including literature reviews, data collection from three schools across two regions, and an evaluation of the framework by teachers, students, and school administrators. The evaluation used a 5-point Likert scale to assess key factors such as ICT components, resource management, school culture, collaboration, and innovation. The findings revealed strong support for the framework, with respondents highlighting its effectiveness in promoting knowledge sharing, improving teaching quality, enhancing student engagement, and fostering a collaborative culture. The study recommends the integration of continuous ICT training programs, active management involvement, and cultural initiatives to encourage knowledge sharing. Limitations of the study include a narrow geographical scope and limited student participation, suggesting the need for broader implementation and longitudinal assessments. This framework presents a scalable solution to bridge the knowledge- sharing gap, ensuring equitable access to educational resources and fostering innovation in Ugandan secondary schools.
  • Item
    A model driven serious game generator : a case of Android quiz game
    (Makerere University, 2025) Afema, Deogracious
    Computer games are used in several areas encompassing fun and serious contexts. Game development however is a complex technical undertaking with resulting financial costs exploding into millions of dollars for the most complex games. As a result , Model Driven Development (MDD) has been used in several studies to simplify software development and develop domain specific artefacts. This study explored the use of Model Driven Development (MDD) in serious game development with a focus on quiz games. Quiz games are a simple game domain that can easily be modelled. Corresponding graphical and other tooling can also be developed to ease game development. With existing evidence of the effectiveness of games in effecting positive learning outcomes and policy shifts allowing learners to have digital devices in schools, serious games hold great potential to shape positive learning outcomes. This study identified serious game features, identified the features missing from the existing quiz game modelling languages, modelled select features missing from the existing languages and developed a model editor to facilitate a no code approach. The study found out that while there were existing modelling languages for quiz games, they did not incorporate several serious games features despite the applicability of the said features to the quiz game domain. With the new features added to the existing modelling language AskMe, five games were prototyped to reflect the applicability of the features to quiz games. A formal verification tool (Microsoft z3) was also used to check the generated models for correctness covering both positive and negative outcomes. Finally this study developed a model editor for the extended language. Through analysis of quiz game requirements specified in existing serious quiz games, this study found out that the extended language covered the specified requirements in a more robust manner. The major contributions of this study include the extension of the quiz game modelling language AskMe to make it more suitable for serious game applications. This study introduced progress tracking, level based game challenges among others that were missing from AskMe. This study also introduced a graphical model editor as an additional tool to enable creation of quiz game models with little to no programming skills.
  • Item
    A model for enhancing career selection systems: a case of Ugandan secondary school students
    (Makerere University, 2025) Tuhame, Moses Kamondo
    Career selection in developing countries is often guided by traditional methods such as teacher- led sessions and examination results yet these approaches fail to account for the complex and multi-dimensional factors influencing career choices. As a result, many students make decisions based on guesswork, peer pressure or parental influence, leading to career mismatches and wasted potential. Although ICT-based career selection tools have been of help, they remain generic and overlook Uganda’s socio-economic and cultural realities. Recent advancements in Artificial Intelligence (AI) and Machine Learning (ML) have strengthened predictive capabilities in career selection systems; however, these technologies rely on limited variables and are largely designed for developed contexts. This study therefore aimed to develop a model that enhances the performance of the existing Career Selection Systems for secondary school students in Uganda. Guided by Social Cognitive Career Theory (SCCT) and Holland’s Vocational theory, the model integrates socio-behavioural and contextual variables to enhance the variables of the existing career selection systems to reflect the realities of Uganda. The study adopted pragmatism research paradigm and employed Design Science Research strategy with both quantitative and qualitative data collected from secondary school and university students and career guidance stakeholders. Data were analysed using SPSS, NVivo, and PLS- SEM. Eight key SCCT variables were identified for the model: Contextual Influences, Contextual Affordances, Learning Experiences, Career Goals, Outcome Expectations, Self- Efficacy Expectations, Personality, and Career Decision-Making. The model demonstrated good statistical fit, with 3.2% of variance in enhancing career selection. Additional qualitative insights highlighted five additional factors for model improvement. Model evaluation showed strong support, with expert walkthroughs yielding a 79.3% satisfaction rate and prototype testing with 51 users recording an 80% satisfaction rate. These results demonstrate that the model is both robust and adaptable, making it suitable for integration into technology-supported career selection systems, including AI- and ML-based platforms in Uganda and similar contexts. Future work should include a longitudinal study to assess the long-term impact of the model on students’ career trajectories from school to employment, alongside the development of a mobile version of the prototype to enhance accessibility and usability. Additionally, integrating the model into existing career selection systems, particularly AI- and ML-based platforms, is recommended to improve system performance and support wider adoption.
  • Item
    A model for person re-identification using deep learning techniques: a case of Ugandan school candidates
    (Makerere University, 2025) Opio, Henry Joe
    Person Re-Identification (Re-ID) is a critical domain in computer vision, with signifi- cant applications in security and public safety. This thesis addresses the unique and com- plex challenge of Re-ID within the educational sector, specifically focusing on the Uganda National Examinations Board (UNEB) dataset. The core problem is the need for reli- able re-identification of school candidates across a minimum four-year age gap (Primary Leaving Examination - PLE to Uganda Certificate of Education - UCE), which causes se- vere Age-Variant Feature Drift. Existing general-purpose Re-ID models are insufficiently robust to these extreme age-related changes, leading to a high risk of misidentification, spoofing, and impersonation during exam registration. To solve this problem, the research study proposes the Automated Person Re-Identification (APRe-ID) model, a novel deep learning architecture designed to generate age-invariant feature embeddings from facial images. The study utilizes a proprietary UNEB dataset of 299,744 data points of student facial features, captured four years apart, to rigorously test the proposed solution. The methodology involves comprehensive data pre-processing with image augmentation, robust face detection using MTCNN, and a deep learning model incorporating the strengths of Deep Metric Learning (DML) and Attention-Based Ar- chitectures. The specific objectives were to investigate optimal facial feature extractors, design the APRe-ID model, and evaluate its performance against the state-of-the-art. Our empirical results show that APRE-ID achieves Precision of 99%, Recall of 99% and F1-Score of 99% as an ensemble of Random forest, Extreme Gradient Boosting, and Sup- port Vector Machine.
  • Item
    A model for streamlining and systemising the management of data in KCCA Primary Schools
    (Makerere University, 2025) Nabutto, Josephine
    Public primary schools in Kampala face a significant challenge of fragmented and inconsistent data management practices. This challenge undermines effective planning, service delivery, and policy implementation, and limits progress toward achieving the Sustainable Development Goals, particularly inclusive and equitable quality education. The study aimed to develop a data management model to streamline and Systemise planning processes and enhance service delivery in Kampala’s public primary schools. The objective was to address inefficiencies arising from varying data management practices across schools and to propose a coherent system that supports reliable decision-making. A mixed-methods research design was adopted, combining surveys and interviews with teachers, headteachers, and officials from the Ministry of Education and the Kampala Capital City Authority (KCCA). This approach enabled a comprehensive understanding of existing data management practices, challenges, and stakeholder requirements for a model for streamlining and systemizing the management of data. Findings revealed significant barriers to effective data management, including low ICT literacy, inadequate infrastructure, insufficient training, limited financing, and weak policy enforcement at the school level. In response, the study developed a three-tier data management model comprising People, Process, and Technology. The People tier emphasises stakeholder roles, collaboration, and trust; the Process tier introduces a structured workflow for planning, data collection, analysis, sharing, and archiving; and the Technology tier focuses on enabling infrastructure, policy frameworks, and data security. Validation by education stakeholders confirmed the model’s clarity, relevance, and potential impact, while noting challenges related to resources and capacity. Overall, the study demonstrates that streamlined and systemised data management is both necessary and feasible for KCCA primary schools and provides a practical foundation for improving educational planning, policy execution, and outcomes, with potential for replication across Uganda’s education sector.
  • Item
    A model for user acceptance of digital banking services by the informal sector in Uganda: a case of Kampala Owino market traders
    (Makerere University, 2025) Ashaba, Jacenta
    Despite the high penetration rates of digital banking services in developed countries such as UK with 71% and Finland with 74%, the user acceptance of digital banking services is still low in Uganda. For example, ATM is 1%, debit card usage is 28%, credit card is 14% while POS is 20%. This study aimed at developing a user acceptance model for digital banking services by the informal sector in Uganda, a case of Kampala Owino Market traders. In this study, Design Science was adopted to achieve the goals of the study. Primary data was obtained from 200 Owino market traders in Kampala city using a questionnaire tool. Data analysis involved computation of descriptive statistics, Pearson Correlations and multiple linear regression on user behaviour of digital banking services. Hypotheses testing was conducted on Performance Expectancy (PE), Effort Expectancy (EE), Social Influence (SI), Facilitating conditions (FC), Hedonistic motivation (HM), Price Value (PV) and Behavioural Intention (BI) of Owino market traders who had bank accounts. The model testing and validation was done using a validation questionnaire. The questionnaire was presented to 150 Owino market traders and 14 information system practioners/analysts to capture responses on acceptance levels of digital banking services. Descriptive statistics of the respondents was achieved using SPSS software while model validation was done using Pearson correlation coefficient and multiple linear regressions to test the study hypothesis. The results showed that Performance Expectancy, Effort Expectancy, Hedonistic motivation and Habit had moderate positive significant effect on User acceptance of digital banking services while social influence, facilitating conditions and Behavioural intentions had weak negative insignificant effect on user acceptance of digital banking services. The study recommends that Banks should ensure full time availability of the network for all digital banking services, stakeholders in the banking sector should work hand in hand with system vendors to develop application designs that are user friendly for most customers in the informal sector given their little knowledge on the usage of these applications. In conclusion, the study notes that user acceptance of digital banking services in the informal sector is largely influenced by Performance Expectancy, Effort Expectancy, Social Influence, Facilitating conditions, Hedonistic motivation, and Behavioural Intention.
  • Item
    A model to enhance adherence to tuberculosis medication: A case of Mulago Immune Suppressive Syndrome Clinic
    (Makerere University, 2024) Kakooza, Edward
    The study recognizes the challenges faced in ensuring adherence to Tuberculosis (TB) medication, which is crucial for successful treatment outcomes. It acknowledges the potential of digital technology, particularly Short Message Service (SMS), to address these challenges and improve medication adherence. The study aimed to address the challenges faced in TB treatment adherence and explore the potential of digital technology in improving medication adherence. The study adopted the Design Science research methodology and data was collected through interviews with patients and health workers. This approach helped gather insights from multiple perspectives and provides a comprehensive understanding of the factors influencing medication adherence. The study identified various factors that influence adherence to TB medication. These factors encompassed predisposing factors, information about TB, enabling factors, reinforcing factors/support, and national policy support. Understanding these factors helps in designing effective interventions to improve adherence rates. Based on the findings, a conceptual model was proposed to guide the design of the SMS-based adherence model. The model outlines the decisions and components necessary for implementing the SMS intervention, such as reminders, educational messages, and support mechanisms. The model was validated to assess its effectiveness in improving medication adherence. The validation process aimed to validate the potential impact of the SMS model and its ability to enhance adherence rates among TB patients. The study contributes to the field of medical adherence, particularly in the context of TB treatment. It provides insights into the use of digital technology, specifically SMS, as a means to improve medication adherence. By proposing a novel SMS-based model, the study offers a practical and scalable solution to enhance adherence rates and ultimately improve TB treatment outcomes. Overall, the study presents a comprehensive exploration of adherence to TB medication and proposes an innovative SMS-based model that has the potential to address the challenges and improve medication adherence in the Mulago Immune Suppressive Syndrome (ISS) Clinic and similar Healthcare settings.
  • Item
    A predictive model for estimating students’ final cumulative GPA at graduation a case study of Makerere University
    (Makerere University, 2025) Oluka, Tony
    Accurate prediction of students’ final Cumulative Grade Point Average (CGPA) at graduation is crucial for identifying at-risk students and improving academic outcomes. This study focuses on developing a predictive model for estimating CGPA/Degree Class using machine learning techniques, leveraging a dataset of over 2500 records collected from Makerere University graduates. The dataset encompasses academic performance, demographic details, and socioeconomic factors, mapped to official university records to ensure accuracy and credibility. Multiple machine learning models, including Logistic Regression, Gradient Boosting Classifier, and Random Forest Classifier, Dummy Classifier, Extra Trees Classifier, Neural Network MLPClassifier and Decision Tree Classifier were evaluated across three training-test splits (80/20, 75/25, and 70/30). Gradient Boosting Classifier emerged as the best-performing model, achieving consistent accuracy of approximately 84.7% and demonstrating robustness and interpretability. Feature importance analysis highlighted prior academic performance, students behaviour, and Alevel Year as the most significant predictors of CGPA, aligning with global findings and offering localized insights specific to Makerere University. Despite its contributions, the study faced challenges such as dataset size constraints and limited exploration of interdisciplinary variations. Nonetheless, the results underscore the potential of machine learning in academic performance prediction, providing actionable insights for educational institutions. The findings emphasize the importance of early intervention, targeted support, and data-driven decision-making in improving graduation rates. This research advances predictive analytics in education, offering a scalable framework for institutions. Future work should expand dataset size and include discipline-specific predictors for deeper analysis.