Faculty of Engineering, Design and Technology

Permanent URI for this communityhttps://hdl.handle.net/20.500.11951/793

Browse

Now showing 1 - 20 of 31

A Data-Driven NLP Skills Gap Analysis of Uganda’s TVET Curriculum and its Effects on Graduate Employability
(Uganda Christian University, 2025-09-23) Patrick Atuhe
This thesis evaluates the outcomes of the revisions to Uganda’s Technical and Vocational Education and Training (TVET) curriculum, focusing on graduate employability. The study applies data science methodologies, particularly Natural Language Processing (NLP), to assess how well the current curriculum aligns with industry needs. Data was collected from 350 TVET graduates, feedback from 50 employers who assessed over 1,250 graduates, and 30 stakeholders analyzed the curriculum. An NLP-based recommendation system was developed using TF-IDF and cosine similarity to quantify alignment between skills taught and those required in the workforce. Findings reveal significant gaps in digital skills, technical preparedness, and alignment with evolving industry expectations. Employers reported a 68% deficiency in digital competencies, with a mean curriculum-employer similarity score of 0.42. The NLP system achieved an F1-score of 0.87, outperforming manual reviews in skill-gap identification. The study provides actionable recommendations for curriculum reform, including the integration of digital tools, periodic review mechanisms, and the use of real-time feedback loops from the industry. These insights contribute to national development goals such as Uganda Vision 2040 by enhancing TVET effectiveness and workforce readiness.
A Framework for Improving Document Submission in Digital Institutional Repositories: A Case Study of Uganda Christian University
(Uganda Christian University, 2025-05-26) Drake Tamale
Digital institutional repositories (DIRs) serve as critical platforms for the preservation and dissemination of academic and research outputs. However, the document submission process in these repositories is often fraught with challenges such as manual data entry, system inefficiencies, and limited user training. This study aims to develop a comprehensive framework to enhance the document submission process in DIRs, addressing these challenges and improving overall user experience and system effectiveness. The primary objective of this study is to develop a framework for improving the document submission process in digital institutional repositories. Specific objectives include assessing the current state of document submission processes, determining the factors for improvement, and developing a framework based on these requirements. The study employed quantitative data collection techniques. A total of 158 questionnaires were distributed to participants, with a response rate of 94.9%. The demographic analysis revealed a diverse participant pool, with a majority holding bachelor's degrees (49%) and having some level of experience with DIRs. The assessment of the current submission process highlighted significant time spent on submissions, guided primarily by institutional policy (62%). System quality and information quality were identified as critical areas for improvement, with participants indicating the need for enhanced metadata workflows and effective error handling mechanisms. User satisfaction and individual impact metrics underscored the importance of training and system updates to improve performance and save time. The findings suggest that improving system quality, information quality, and user satisfaction can significantly enhance the document submission process in DIRs. The designed framework incorporates components such as metadata management, security and privacy measures, automated data entry, and error handling. These improvements are expected to streamline the submission process, reduce errors, and increase user efficiency and satisfaction. This study provides a comprehensive framework for improving document submission in digital institutional repositories. By addressing system inefficiencies and enhancing user experience, the proposed framework aims to facilitate more effective and efficient document management.
A Framework for Integrating Blockchain Technology into Copyright Theft Prevention Systems: A Case Study of the Uganda National Musicians Federation
(Uganda Christian University, 2025-07-22) Ahmed Kasole
Uganda's vibrant creative economy, particularly its music industry, faces significant challenges from widespread copyright infringement and substantial revenue loss. This is primarily due to unauthorized digital distribution and the limitations of traditional enforcement methods in the digital age. Artists often find their work used without proper compensation, which stifles innovation and threatens the economic viability of creative professionals. This study aims to address these issues by conceptualizing and developing a blockchain-based framework to prevent copyright theft and enhance revenue tracking for artists under the Uganda National Musicians Federation. The framework is designed to revolutionize ownership verification and automate royalty distribution with unprecedented transparency, thereby restoring financial control to creators. To achieve this, a qualitative case study was conducted at the Uganda National Musicians Federation (UNMF). The methodology involved in-depth interviews with musicians, producers, and federation staff to understand their lived experiences of copyright abuse and the challenges in licensing. This empirical data was supported by a comprehensive literature review on copyright enforcement and blockchain integration in the creative industries. To demonstrate feasibility, a simulation model was built using Hyperledger Fabric, which was tested in realistic content distribution scenarios to show how smart contracts could seamlessly register content, automate agreements, and ensure timely royalty payments directly to creators. The findings confirm that blockchain technology can effectively secure content ownership with cryptographic certainty, track usage in real-time, and reduce dependency on intermediaries. Based on these insights, the study proposes a comprehensive Blockchain Copyright Compliance Framework (BCCF) customized for Uganda. This framework outlines processes for decentralized content registration, smart contract-based licensing, and inter-agency collaboration. The study concludes that while blockchain offers immense potential for copyright governance and revenue protection, its successful implementation will require a multi-faceted approach involving legal reform, stakeholder buy-in, and technical capacity-building initiatives
A Framework for Managing the Functionality of Hand Pump Rural Water Supply Systems in Bumbaire Sub-county, Bushenyi District
(Uganda Christian University, 2025-04-10) Titus Nuwamanya
Water is a basic need and a human right. When communities access potable water, their livelihoods improve. Groundwater is the most commonly used source of water. Communities access water from this source through hand pumps, among others. The water is accessed when they are functional. Against this backdrop, the purpose of the study was to develop a framework for managing the functionality of hand pump rural water systems in Uganda. The study was contextualized on Bumbaire Sub County in Bushenyi District. The study set out to establish the causes of hand pump nonfunctionality, to design a framework for improving the maintenance of hand pumps; and to validate the designed framework and recommend it for deployment. Primary and secondary data were collected to answer objective 1 while Design Science Research was adopted to design and evaluate the framework to answer objectives 2 and 3. Water users, District Water Officials and Sub County Community Development Officer participated in the study. In total, 158 participants were involved. Questionnaires, FGD, Interviews, Experiments and Sanitary Inspection tool were used for primary data collection. Findings revealed that social, financial, technical and institutional factors were responsible for nonfunctionality of the hand pumps. A framework for closing the social, financial, technical and institutional management gaps was designed and evaluated. The evaluated framework was recommended for deployment. The study concluded that when the prescriptions of the evaluated framework are duly implemented, the maintenance of hand pumps will improve. Correspondingly, the magnitude of break-down and nonfunctionality will be minimized. The study recommends need for continuous awareness creation and active engagement of the water users, among others.
A Framework for the Adoption of Intelligent Farm Advisory Systems for the Coffee Sector: A Case of Western Uganda
(Uganda Christian University, 2024-05) Benson Mworozi Byaruhanga
Coffee farming is a critical sector in Uganda, supporting livelihoods and contributing to the economy. However, coffee farmers face numerous challenges, including weather uncertainties, market fluctuations, and pest outbreaks. Intelligent Farm Advisory Systems (IFAS) technology offers a potential solution to address these challenges and improve farming practices. Therefore, this study aimed to explore coffee farmers' perceptions and attitudes towards IFAS technology adoption in Western Uganda. Using questionnaires, data were collected from 384 coffee farmers in Western Uganda. The data collection method involved administering structured questionnaires to participants, focusing on variables related to perceived usefulness, relevance, trust, environmental sustainability, ease of use, training access, and interface usability, attitude towards use, behavioral intention, and actual usage of IFAS technology. The findings revealed that coffee farmers perceive IFAS technology as beneficial in enhancing task efficiency, mitigating risks, addressing market challenges, improving productivity, and supporting sustainable farming practices. Despite positive perceptions and intentions towards IFAS adoption, actual usage remains limited, indicating barriers to adoption and implementation. The study highlights the importance of addressing contextual factors, technological infrastructure, ethical considerations, and environmental implications in promoting IFAS technology adoption and sustainability in coffee farming communities. Stakeholders, policymakers, and researchers are encouraged to collaborate in developing tailored interventions, capacity-building initiatives, and policy frameworks to facilitate the effective adoption, utilization, and integration of IFAS technology into coffee farming practices. Overall, the study underscores the potential of IFAS technology to transform agricultural systems, improve food security, and contribute to sustainable development goals in Uganda and beyond.
A Machine Learning Approach for Accurate Valuation of Imports in Uganda
(Uganda Christian University, 2025-09-30) Sentongo Paul
Accurate customs valuation is central to revenue mobilization, trade compliance, and economic stability in Uganda, where import duties contribute nearly one-third of domestic tax revenue. Yet persistent inefficiencies in conventional valuation methods such as reliance on importer-declared invoice values, outdated price databases, and manual adjudication have resulted in systemic undervaluation, mis invoicing, and annual revenue losses exceeding USD 200 million. This thesis investigates the potential of machine learning (ML) to transform customs valuation by developing and deploying predictive models trained on more than 70,000 import declaration records from Uganda Revenue Authority’s ASYCUDA system (2020–2024). Three supervised ML algorithms; Random Forest, Extreme Gradient Boosting (XGBoost), and Artificial Neural Networks (ANN) were implemented following a rigorous pipeline that included exploratory data analysis, feature engineering, and model optimization. All models demonstrated strong predictive performance (R² >0.93), with Random Forest achieving near-perfect accuracy(R² = 0.997, MAE = UGX 560.35, RMSE = UGX 1,868.23). Compared to Uganda’s current average based approach (MAE = UGX124,797.76), this represents a 99.55% reduction in error, underscoring the transformative capacity of ML for valuation precision. Beyond model benchmarking, the study contributes technically by operationalizing the Random Forest model into a Streamlit based prototype web application, offering real-time decision support for customs officers. Empirically, it provides the first quantified evidence of ML’s potential to address valuation fraud and inefficiencies in Uganda. Practically, it establishes a replicable frame work for low-resource settings, integrating ML with existing trade platforms such as ASYCUDA. The findings have significant policy implications: adopting ML-driven valuation can curtail revenue leakages, enhance compliance with WTO Customs Valuation Agreements, and support Uganda’s Vision 2040 and National Development Plan III goals for domestic revenue mobilization. Limitations such as reliance on secondary data, exclusion of informal trade, and simulation based deployment highlight opportunities for future research. These include incorporating regional datasets, exploring explainable AI techniques (e.g., SHAP, LIME) to improve transparency, and piloting ML integration within operational customs systems. This thesis thus advances the discourse on AI in public sector modernization, demonstrating that machine learning is not merely a technical innovation but a strategic enabler for fiscal sustainability, trade integrity, and digital transformation in Uganda’s customs administration.
A Text-based Poultry Health System: An Interactive Disease Detection and Prescription Recommendations
(Uganda Christian University, 2025-09-23) Ritah Nakimuli
Poultry farming is vital to Uganda’s economy, providing income for many rural households. However, broiler chicken farmers struggle with early disease detection and management, leading to significant flock losses and financial hardship. Although advanced diagnostic tools exist, they are often too expensive and complicated for small-scale farmers in rural areas to access. This research presents a multilingual, symptom-based poultry disease prediction system, a lightweight, mobile-friendly machine learning solution that addresses the limitations of existing diagnostic tools. By allowing farmers to input observable symptoms like bird behavior, droppings, and flock age through a simple text-based interface, it eliminates the need for costly equipment, lab tests, or other traditional methods. Several machine learning algorithms were tested to identify the best method for disease prediction, including SVM, Random Forest, XGBoost, and KNN. KNN and SVM performed best, each achieving 96% accuracy and 97% precision, with Random Forest close behind. XGBoost performed poorly, with only 11% accuracy. Although SVM matched KNN in accuracy, it struggled with real-world probability calibration. KNN, on the other hand, provided reliable and interpretable confidence scores, making it the preferred choice for deployment. The final application is deployed using the Streamlit framework, enabling seamless access across desktop and mobile browsers. It provides real-time disease predictions, along with tailored prescriptions and prevention strategies. Additional features include a QR code for easy sharing, which enhances both the user experience and accessibility. This project bridges the gap between advanced AI and the practical realities of low-resource agricultural settings.
Adoption of Block Chain Technology to Enhance Patient Records Management- a Case of Mulago National Referral Hospital
(Uganda Christian University, 2024-03-09) Ronald Sseggujja
Block chain technology holds immense potential for transforming patient records management in healthcare settings. However, its adoption faces numerous challenges, particularly in resource-constrained environments such as Mulago National Referral Hospital. In this study, we aimed to investigate the factors influencing the adoption of block chain technology to enhance patient records management at Mulago Hospital. Using a quantitative methods approach, data was collected from healthcare professionals at Mulago Hospital through a structured questionnaire survey. Participants were selected based on their involvement in patient record management processes. Data collection involved administering the questionnaire to key stakeholders. The collected data were analyzed using descriptive statistics. The findings reveal several key insights into the factors affecting the adoption of block chain technology at Mulago Hospital. Organizational support, regulatory compliance, and training programs emerged as critical determinants of perceived usefulness and ease of use of block chain technology. The study also identified concerns regarding data security and interoperability as significant barriers to adoption. Despite these challenges, there is a consensus among healthcare professionals about the potential benefits of block chain technology in improving patient record management practices. The implications of these findings underscore the importance of addressing organizational and technical challenges to facilitate the successful adoption of block chain technology in healthcare settings. By providing insights into the perceptions and attitudes of healthcare professionals, this study contributes to the growing body of literature on technology adoption in healthcare. Ultimately, the successful implementation of block chain technology at Mulago Hospital could serve as a model for similar healthcare facilities facing similar challenges worldwide.
Adoption of Climate Smart Agriculture Technologies by Smallholder Maize Farmers in Manafwa District, Eastern Uganda
(Uganda Christian University, 2025-04-04) Robert Hamfrey Mafumo
Globally, climate change is becoming a major threat to food security systems and sustainable development. This study aimed to assess the effects of Climate-Smart Agriculture (CSA) practices adopted by smallholder farmers on maize yields in Butiru sub-county, Manafwa district. It focused on identifying the existing CSA practices, determined factors influencing their adoption, and evaluated their effects on maize yield. The study hypothesized that CSA practices have no significant effect on maize yield. A cross-sectional design was employed; simple random sampling to select 298 maize farmers and semi-structured questionnaires were used to collect primary data. Data analysis was conducted using descriptive statistics and a Binary probity with STATA software. The results revealed that, the common CSA practices included: intercropping maize with legumes, use of improved maize varieties, and application of organic fertilizers implementation of crop barriers, terracing and agroforestry. Among these, intercropping maize crop with legumes ranked 1st and agroforestry ranked the least among the CSA practices used. Majority of farmers (55.37%) were male, mean age of respondents was 43.61 years. On average, farmers’ households comprised six (6) members, the mean maize average was 2.297 acres and an average number of extension visits was 0.439 per month. The average size of farmer groups was 10 members. The Binary probit revealed that factors such as gender, age, participation in CSA training sessions, extension visits, household labor availability, education level, and access to credit significantly (p>0.1) influenced the adoption of CSA practices among smallholder farmers. Furthermore, CSA practices like intercropping (P>0.03), planted better quality maize seeds (P> 0.04), and use of decomposed manure (p = 0.01) had a significant effect on maize yield. In conclusion, the adoption of the improved maize planning technologies is influenced by factors such as sex, age, education, and extension visits. Training has helped in promoting the use of different improved technologies, with significant effects on maize yield seen in practices like intercropping, use of biological mature and the use of better-quality seeds. To enhance the adoption of improved technologies and improve crop productivity, it is recommended to develop farmer education programs that increase adoption, promote gender empowerment and youth involvement and improve access to financial credit for small-scale farmers.
An Architectural Design for Aggregated Healthcare Reporting From Electronic Medical Record Systems to the National Electronic Healthcare Reporting System. A Case Study of Uganda Ministry of Health
(Uganda Christian University, 2025-06-23) Emmanuel Ogwang
In Uganda, there has been notable adoption of Information and Communication Technology (ICT), especially Electronic Medical Record (EMR) systems. Pilot studies have paved the way for the implementation of UgandaEMR, primarily used by government healthcare providers for disease surveillance and electronic reporting to DHIS2, the national electronic healthcare reporting system. Despite strong endorsement by the Ministry of Health (MoH), private healthcare providers have been slow to adopt UgandaEMR, citing diverse requirements, notably advanced financial capabilities. A major challenge with alternative EMR systems is their inability to directly exchange routine aggregate healthcare data with DHIS2, a functionality already achieved by UgandaEMR. This gap leads to reporting delays to the MoH, negatively impacting disease surveillance and resource allocation. This study addressed three key objectives: understanding challenges in aggregated data reporting from diverse EMR systems to DHIS2 and identifying architectural needs, designing an application architecture for data exchange between alternative EMR systems and DHIS2, and implementing this design for proof-of-concept. Through an inductive approach, a survey of 20 purposively selected healthcare providers was conducted using questionnaires, with descriptive statistics used for analysis. The analysis revealed numerous challenges in report aggregation, including spending more than three hours consolidating reports, duplicate entries, data incompleteness and inaccuracy, and reliance on unreliable data sources such as simultaneous paper and EMR system usage. To enhance EMR system capabilities, several strategies were identified, including developing an auto-synchronization service for report automation, integrating MoH report formats into EMR systems, and adopting interoperability standards for seamless data exchange. A prototype was developed to demonstrate these strategies' effectiveness, showing that enhancing alternative EMR systems' capabilities enabled timely submission of aggregate healthcare data to the MoH, thereby improving disease surveillance and resource allocation efficiency.
An Assessment of Causal Factors of Accidents and Injuries in Powerline Construction Projects in Uganda. A Case Study in Luuka, Kaliro, Iganga And Bugweri Districts
(Uganda Christian University, 0012-09-23) Brian Muhimbura
ABSTRACT Although, the construction industry contributes to national economic growth, it has been associated with unsafe working environments due to the exposure of workers occupational hazards and injuries. This study assessed the types, prevalence and causal factors of accidents amongst powerline construction workers in Eastern Uganda. A mixed research approach was employed and data collected using both structured and unstructured interviews Descriptive statistics approaches including Chi-square tests and multiple regression model were employed to analyze quantitative data and qualitative data analyzed using thematic analysis. Occupational accidents at worksites included electrocutions, slip, falls from height, overhead power contacts, struck by, struck against and car accident. Injuries included skin pierces, skin peel-offs, swellings and skin cuts. Fatal cases originated from struck-by accidents in (76.4%) and car accidents (23.6).Overhead power contacts (25.2%), struck-by accidents (23.2%) and electric shock (16.4%) accounted for most non-fatal accidents. Only 52% of workers had ever sustained an occupational accident while 69% of them workers had ever sustained an injury. Struck-by accidents (26.5%), struck against (25.7%) and slip accidents (18.6%) were more prevalent accidents while Skin pierce (26.5), skin peel offs (22.8%) and swellings (21.9%) formed the prevalent injuries. Low experience and expertise of workers (68.9%), poor weather conditions (33%), poor conditions & usability of equipment (20.4%), poor communication amongst the workers (25.2%) formed the originating, shaping and immediate influence on accidents. The Duration of work at the powerline construction worksite significantly influenced occupational accidents (P= 0.014). Monthly income (P=0.015), site location (P=0.049), electrician job (P=0.048) and mate electrician job (P=0.034) significantly influenced work-related injuries amongst workers. Investing in work place safeguards and promoting safety behaviour amongst employees should be prioritized by employers.
Assessing the Effectiveness of On-Site Fecal Sludge Emptying Technologies in Delivering Safely Managed Sanitation Services in Kampala
(Uganda Christian University, 2025) Caroline Namale
The research study investigated the effectiveness of on-site fecal sludge emptying technologies in delivering safely managed sanitation services in Kampala. The study focused on cesspool and gulper technology operations in Kampala with a sample space of 68 operators both companies and sole proprietors. The study identified the technological, human and environmental health gaps in the technologies that hinder their effectiveness in delivering safely managed sanitation services using survey questionnaires and laboratory analysis. The study identified improvements that can be adopted by the technologies to operate effectively across the sanitation service chain. These included modification of gulper technology by introducing a simple fuel-powered motor with a potable pump end that can suck the fecal sludge with minimal energy requirement from the operator. The research study discovered that both cesspool and gulper technologies do not fully empty the clients containments, considering septic tanks, ventilated improved pit latrines, and traditional pit latrines. The gulper technology takes more than one hour to empty containments, which is not the case for cesspool technology. The research identified gulper technology to be associated with more environmental and public health risks compared to the cesspool technology. The study recommended the installation of GPS equipment on all cesspool vacuum trucks and gulper technology operators' tricycles to track movement and ensure that the fecal sludge is only disposed of at the fecal sludge treatment plant to curb environmental and public health risks identified by the research study.
Assessment of Causes of Occupational Accidents Among Workers at Storeyed Commercial Building Construction Sites in Wakiso District, Uganda
(Uganda Christian University, 2024-03-19) Doreen Birungi
Occupational Hazards Accidents on commercial storeyed construction sites
Assessment of Effectiveness of Chlorination and Free Residual Chlorine Decay at Point of Use in Refugee Settlements in Uganda: The Case of West Nile
(Uganda Chrisitian University, 2025-04-07) Dithan Mukiibi
Uganda is famous for hosting refugees in Africa and world over. Despite this prominence, providing for the needs of the refugees has come with challenges, water, sanitation and hygiene (WASH) inclusive. Against this backdrop, the purpose of this study was to assess the effectiveness of the chlorination programmes implemented in refugee settlements in Uganda. The intent was on establishing the factors that influence free residual chlorine decay at point of use in the refugee settlements in Uganda. The study was contextualized on West Nile. Three refugee settlements were involved namely Omugo, Imvepi 1 and Pagirinya. Specifically, the study examined physicochemical quality and bacteriological load of drinking water in the three refugee settlements; assessed the efficacy of different types of chlorine disinfection programs used in the refugee settlements; sought to establish the relationship between storage conditions at point of use on residual chlorine and bacteriological load water in refugee settlements in West Nile; and sought to propose strategies for better management of quality of treated water at household level in refugee settlements. Water quality measurements, Questionnaires and interviews were used to collect data. The study objectives were duly achieved and the major findings were; most of the physico-chemical and biological parameters of water at the source points lay within the permissible ranges of local and international thresholds except E-coli, EC, chlorides and total alkalinity. Therefore, chlorination was necessary to improve the potability of water before consumption by refugee households. The study also established that centralized chlorination system was applied in all the selected settlements. This occurred at the points of distribution before water was drawn for home use. The Free Residual Chlorine at points of distribution in the three settlements was 0.5mg/L. However, the free residual chlorine deteriorated at point of use leading to recontamination of the water. The predisposing factors for the rapid decay of the free residual chlorine and the eventual recontamination of the water were related to poor storage conditions including the cleanliness of storage devices or vessels and use of dipping system to draw water from the storage vessels including use of dirty utensils. Besides, poor personal hygiene of the refugees such as long finger nails equally affected the quality of the stored water, as well as the long storage time beyond recommended 24 hours, among others. However, the refugees were optimistic that rigorous awareness creation, increasing the distribution of standpipes (POD) and donating water collection and storage devices would remedy the situation. This study concluded that water recontamination at household level was a big problem facing the refugees in settlements in West Nile. This has increased vulnerability to waterborne diseases. The study recommended need for active engagement of the refugees for requisite behavioural and attitude changes, among others.
Assessment of Heavy Metal Concentrations in Water, Sediment and Water Hyacinth of the Inner Murchison Bay, Lake Victoria
(Uganda Christian University, 2023-09-08) Rosette Zawadi Lokuni
This study assessed heavy metal pollution in the Inner Murchison Bay within Lake Victoria region. The assessment was based on determination of concentrations of heavy metals in water, sediment and water hyacinth (Eichhornia crassipes). The Bay is the abstraction point of water supplied in Kampala City and metropolitan areas. It is also the recipient of partially treated and untreated wastewater from the City. There is a potential for continuous deterioration of the Bay’s water quality due to anthropogenic activities carried out in its catchment. Twelve sampling locations that are representative of the Bay were used to gather samples of water, sediment, and water hyacinth based on cross-sectional study. Atomic Absorption Spectrophotometer (AAS) analysis was performed on the samples to ascertain their lead (Pb), cadmium (Cd), and mercury (Hg) concentrations. Results showed that the concentration of Pb and Cd in water was above the permissible limits set by WHO and NEMA (Pb:0.01ppm and Cd:0.003) at all sites. In sediment, Pb was below the LEL (31.0) while Cd exceeded both the LEL (0.60) and TEL (0.99) signifying that the values of Pb and Cd were permissible as per the sediment assessment guidelines Contamination Factor and Pollution Load Index indicated moderate pollution of the sediment with Pb and Cd (CF>1, PLI>1). The values of Bio-concentration factor for water hyacinths were above 1 indicating that the plants were able to take up Pb and Cd from water. Mercury (Hg) was below the detectable levels in all the samples. Pb and Cd are from agricultural fertilizers, industrial effluent, urban runoff, wastewater effluent, navigation and recreational activities carried out in the catchment of the Bay. Evidence of concentration of heavy metals in water, sediment and water hyacinth indicates pollution of the Bay by heavy metals thus continuous monitoring of the Bay’s state is crucial. Key words: Inner Murchison Bay, Heavy Metals, Contamination Factor, Pollution Load Index, Water hyacinth, Bio-concentration Factor, Lowest Element Level (LEL), Threshold Element Level (TEL), Probable Effect Concentration (PEC) and Severe Effect Level (SEL)
ASSESSMENT OF THE EFFECTIVENESS OF USING BLACK SOLDIER FLY LARVAE IN TREATMENT OF MUNICIPAL SOLID WASTE
(Uganda Christian University, 2025-09-02) Mukasa Mugambwa Richard
The study intended to find the potential of Black Soldier Fly (BSF) larvae as a sustainable solution for managing municipal solid waste (MSW) in Uganda, a country grappling with significant waste management challenges. Kampala generates an alarming 2,000 to 2,500 tons of waste daily, yet only a fraction is effectively collected and processed, rendering traditional disposal methods inadequate. The research primarily focused on analyzing the composition of MSW, assessing the weight reduction over a nine-day composting period, and examining the influence of moisture and temperature on waste processing efficiency. The study's methodology combined both quantitative and qualitative approaches. Waste was collected from Nakawa Market, sorted into organic, inorganic, and recyclable components, and processed into uniform 1-2 cm particles. Simultaneously, BSF larvae were reared and monitored, with experiments conducted using five-day-old larvae. The findings revealed that the waste largely consisted of jackfruit and onion residues, which exhibited a moisture content of 79% and a pH of 6.7. A preliminary fermentation process resulted in 275 kg of material at a measured temperature of 24.95°C. Over the nine-day trial, weight reduction was consistently monitored across 22 samples (12.5 kg each), following the addition of 0.003 kg of BSF larvae. The experiment resulted in an average weight decline from 12.5 kg to 9.7 kg, demonstrating statistically significant differences through ANOVA analysis (p < 0.05). Notably, temperature variations were significant throughout the study, with an initial decrease followed by a peak of 37.5°C for one sample, highlighting the dynamic nature of microbial activity. A notable strong negative correlation (r = -0.967) was identified, suggesting that as waste weight diminished, temperature elevated. The relationship between moisture content and waste reduction index (WRI) was also significant: moisture levels at or below 55% maintained a WRI below 1.5, while levels between 60% and 80% peaked at a WRI of 2.5. Conversely, moisture content above 80% led to a decrease in WRI. Waste reduction efficiency was found to be optimal between 60-80% moisture, with temperature playing a pivotal role in the composting process optimal at 30°C for enhanced decomposition rates. Recommendations for effective MSW reduction include routine monitoring of environmental conditions, implementing preliminary fermentation, and promoting aerobic conditions to enhance microbial activity and waste management strategies in Uganda. DECLARATION
CONTEXTUALIZING AI ETHICS IN UGANDA’S MICROCREDIT WITH ADAPTIVE SENSITIVE REWEIGHTING
(Uganda Christian University, 2025-08-12) Isabirye Emmanuel
This research tackles the pressing ethical concerns of using Artificial Intelligence (AI) in Uganda’s microcredit sector, namely to develop an Adaptive Sensitive Reweighting (ASR) model to mitigate algorithmic bias and promote equitable access to credit. Traditional credit scoring models - and AI algorithms trained on Western-biased data - discriminate against marginalized groups because they are based on formal financial records, reinforcing structural disadvantages. By iterative engagement with Ugandan policymakers, lenders, borrowers, and AI experts, we identify the most significant ethical concerns and specify context-specific fairness metrics. The ASR approach adaptively adjusts weights for sensitive features like collateral values and transaction history during model training to enhance fairness. Experimental outcomes on a typical credit scoring dataset demonstrate ASR’s success: the inclusion rate of disadvantaged borrowers is enhanced by 15% with predictive accuracy maintained, and significant improvements on key fairness metrics. The research provides actionable policy recommendations on implementing ASR-based AI systems in Uganda’s microfinance sector to drive financial inclusion and sustainable development. This study contributes to emerging Majority World scholarship on AI ethics by demonstrating the necessity of situating ethical frameworks and valuing stakeholder perspectives to develop equitable, inclusive AI systems. Our findings offer valuable insights for policymakers, microfinance institutions, and AI practitioners who aim to implement responsible AI in Uganda’s Microcredit sector.
Data-driven Analysis and Prediction of Human Rights Violations Against Human Rights Defenders: A Case Study of Eastern Africa
(Uganda Christian University, 2025-09-29) Bagombeka Esther Asiimire
Despite the growing availability of big data and machine learning, human rights monitoring in the region remains largely dependent on retrospective reports, eyewitness testimonies, and qualitative assessments, which lack the ability to anticipate future violations. The absence of real- time data processing and predictive analytics limits the ability of policymakers and advocacy groups to implement proactive intervention strategies. As a result, human rights organizations often respond reactively, only after violations occur, rather than deploying preemptive measures to protect HRDs. In this research, a quantitative research design was adopted, utilising a cross-sectional approach to analyse patterns in human rights violations. Data was collected from recognized human rights organisations, human rights databases, and global news agencies. The research employed descriptive analytics to identify trends, K-Means clustering to categorize high-risk regions, and predictive modeling to forecast future violations. Seasonal Autoregressive Integrated Moving Average (SARIMA) was used to model long-term seasonal trends, while Recurrent Neural Networks (RNN) captured short-term fluctuations and nonlinear patterns in the data. The Predictive Human Rights Violations Model (PHRVM) emerged as the most effective, balancing structural seasonality and real-time variations, resulting in higher accuracy and improved forecasting reliability compared to individual models. The findings revealed that human rights violations followed distinct temporal and geo- graphic trends, peaking around election periods, protest seasons, and government crackdowns. While the PHRVM outperformed other forecasting methods during training (MAE : 0.081, RMSE : 0.087), testing revealed a slight increase in prediction error, with MAE rising to 0.684 and RMSE increasing to 1.109. A paired t-test confirmed that the model significantly outperformed a naïve baseline forecast (p < 0.05), validating its predictive capability. This research concluded that human rights violations follow recognizable patterns, making it possible to anticipate high-risk periods and optimize protection efforts for HRDs. This helps policymakers, and advocacy groups to anticipate risks and implement preventive measures before violations escalate. The PHRVM’s success shows the potential of AI-driven forecasting in social science research, offering a more systematic approach to tracking civic space restric- tions. However, for predictive models to be more effective in real-world applications, further refinement is needed, including the integration of real-time data sources such as social media monitoring, remote sensing technologies, and expanded human rights reporting networks. Strengthening these capabilities will enhance model accuracy, responsiveness, and impact, ensuring that human rights organisations can move from reactive responses to preventative protection strategies.
Detection of Banana Fusarium Wilt & Black Sigatoka: A Deep Learning Approach for Smallholder Farms in Central Uganda
(Uganda Christian University, 2025-10-20) Peter Mulindwa
Bananas are a vital food and income source in Central Uganda, yet their cultivation is severely threatened by destructive diseases such as Fusarium Wilt and Black Sigatoka. Smallholder farmers, who form the backbone of Uganda’s agricultural sector, rely heavily on manual disease identification methods, which are time-consuming, error-prone, and largely ineffective for early intervention. This thesis proposes a hybrid deep learning approach that integrates Convolutional Neural Networks (CNNs), Vision Transformers (ViTs), and Gray Level Co-occurrence Matrix (GLCM) texture features to provide accurate, efficient, and scalable detection of banana leaf diseases using image-based classification. A dataset of over 17,000 annotated banana leaf images was sourced from the Lacuna Banana project. Rigorous preprocessing, including resizing, normalisation, and augmentation, was applied to enhance model robustness. Texture features extracted through GLCM were combined with spatial features learned by CNN and ViT models to improve classification sensitivity. Several models were developed and evaluated, including a custom CNN, InceptionV3 with transfer learning, and a ViT-based architecture. Evaluation metrics such as accuracy, precision, recall, and F1-score were used to assess model performance. The Vision Transformer outperformed other individual models with 99% classification accuracy, while the proposed hybrid model achieved a balanced accuracy of 98%, with substantial precision and recall across all disease categories. The integration of GLCM features significantly improved the detection of texture-specific diseases like Black Sigatoka. This research contributes a robust, interpretable, and field-deployable AI-based diagnostic tool that aligns with Uganda’s national goals for data-driven agricultural development and the food security-related Sustainable Development Goals (and sustainable farming.
DETERMINANTS OF HAND PUMP BOREHOLE PERFORMANCE AND EFFICIENCY IN RURAL AREAS OF UGANDA. “A CASE STUDY OF KIBUKU DISTRICT"
(Uganda Christian University, 2025-10-10) SIKYAJULA ELIZABETH
Uganda continues to face substantial challenges in ensuring safe, reliable, and equitable access to water, particularly in rural areas. Kibuku District in eastern Uganda exemplifies these challenges, with access rates ranging from 27% in Kabweri Sub-County to 95% in Kenkebu Sub-County, and an overall average of 58%. Despite significant government and donor investments in hand pump boreholes—the primary source of rural water—performance remains inconsistent due to frequent breakdowns, reduced yields, and compromised water quality. This study was undertaken to determine the technical, socio-economic, and environmental factors influencing the performance of hand pump boreholes and to develop predictive insights for enhancing their reliability and efficiency. The specific objectives were to: (i) assess the effect of technical factors on the performance and efficiency of hand pump boreholes, (ii) examine the relationship between socio-economic factors and borehole functionality, (iii) analyse the effect of environmental factors on borehole water quality, and (iv) develop an evidence-based predictive model for improving borehole reliability in Kibuku District. A cross-sectional research design was adopted, involving a sample of 384 respondents and 110 boreholes distributed across the district. Data on technical factors such as casing material, pump type, siting methods, yield; socio-economic factorssuch as user fees, local government support, spare parts availability, and environmental factors such as salinity, contamination, rainfall patterns were collected and analysed using analysis of variance (ANOVA) and multiple regression techniques. Results indicated that technical factors were the most influential predictors of borehole performance. Casing material emerged as the most significant determinant (β = 0.338, p < .001), followed by borehole siting mechanisms (β = 0.173, p < .001), pump type (β = 0.128, p = .013), and pump yield (β = 0.113, p = .012). Among environmental variables, salinity was the strongest predictor (β = 0.408, p < .001), with lower salinity levels associated with higher performance. Socio-economic analysis revealed that user fees (β = 0.085, p = .048), local government support (β = 0.637, p = .019), and spare parts availability (β = 0.871, p = .003) had significant positive effects on functionality, highlighting the importance of financial contributions, institutional support, and logistical readiness in sustaining rural water infrastructure. The study concludes that the performance and efficiency of hand pump boreholes in Kibuku District are primarily determined by technical standards, complemented by socio-economic governance and environmental suitability. Sustainable functionality requires improvements in casing material quality, hydrogeologically informed siting, appropriate pump selection, and structured maintenance. It is recommended that district water programs implement mandatory technical audits, train local technicians, and enforce standardized construction protocols to ensure the use of durable casing and context-appropriate pumps. Furthermore, policy frameworks should strengthen spare parts supply chains and institutional support systems. Future research should assess the long-term cost-effectiveness of casing materials across different hydrogeological zones and explore pump and groundwater interactions to optimize technology selection.

Browse

Browsing Faculty of Engineering, Design and Technology by Title