Master of Computer Science

Permanent URI for this collection

https://testir.kiu.ac.ug/handle/20.500.12306/3607

Browse

Recent Submissions

Now showing 1 - 5 of 15
  • Thumbnail Image
    Item
    Structural Equation Model Analysis of Sex Education, Hiv/Aids Knowledge and Attitude, among University Students at Kampala International University, Kampala, Uganda
    (2024) Womunga Emmanuel
    This study explores the impact of sex education on HIV/AIDS knowledge and attitudes among students at Kampala International University, addressing ongoing challenges in effectively curbing HIV/AIDS through education. The primary objectives were to examine the relationship between sex education and HIV/AIDS knowledge, assess the correlation between knowledge and attitudes, and construct a structural equation model (SEM) illustrating these interactions. A cross-sectional design was employed, collecting data from 425 students through a stratified sampling technique. Data analysis was conducted using SPSS, Python, and Smart PLS, utilizing logistic regression and SEM for model construction. The results revealed that sex education accounts for 13.6% of the variability in HIV/AIDS knowledge, indicating a moderate influence. Furthermore, 34.9% of the knowledge gained influences students' attitudes toward HIV/AIDS, suggesting a significant correlation. The SEM analysis demonstrated positive and significant relationships between sex education, HIV knowledge, and attitudes. The study concludes that comprehensive sex education significantly enhances students' understanding of HIV/AIDS, which in turn positively influences their attitudes toward the disease. Recommendations include integrating sex education into the university curriculum to bolster HIV/AIDS prevention efforts.
  • Thumbnail Image
    Item
    A Framework Design for Handling Technical Factors Affecting Deployment of Mobile Networks in Uganda
    (2024) Tuhame William
    Telecommunications service quality and coverage are major concerns globally, especially in the mobile communications sector. In Uganda, the deployment of mobile networks faces various technical, operational, and business challenges (UCC report, 2022). This study aimed to design a mobile network framework that addresses these technological issues to ensure widespread coverage and high-quality services (QoS) nationwide. Using a mixed-methods approach, the research gathered quantitative data from 109 stakeholders, including mobile telecom companies, infrastructure providers, and the Uganda Communications Commission (UCC), alongside qualitative insights. Findings revealed that mobile network deployment in Uganda is moderately high, with emerging technologies impacting deployment at a moderate level. Key factors facilitating deployment included spectrum availability and regulatory support. To enhance network coverage and reliability, the study recommended increasing the number of deployed endpoints, utilizing unlicensed spectrum, and establishing more ad hoc networks in remote areas. It proposed using the Communication and Computing Energy Cost model for rural regions and wireless mesh networks for broader coverage. The designed framework simulated using Packet Tracer, effectively addressed key technical factors, enhancing security, optimizing spectrum usage, and improving infrastructure performance. Recommendations for improving deployment quality and coverage included increasing mobile tower numbers, reducing costs through innovative backhaul technologies and low-cost base stations, and ensuring affordable power supplies. The study also emphasized the need for revised spectrum management policies, collaborative strategies among stakeholders, and increased investment in ICT infrastructure.
  • Thumbnail Image
    Item
    Statistical Modelling of the Effect of Government Investments on Poverty Alleviation in Mogadishu, Somalia
    (2024) Sakerie Saed Mouse
    This study examines the effect of government investments on poverty alleviation in Mogadishu, Somalia, focusing on key sectors such as agriculture, manufacturing, and small and medium enterprises (SMEs). Data were collected through surveys and official government reports. By employing advanced statistical methods, including Granger-causality tests, Johansen co-integration tests, Lasso regression, and Ridge regression, the research analyzes both short-term and long-term impacts on poverty reduction indicators like household income, access to clean water, food, and shelter. The findings reveal that investments in SMEs have the most significant positive effect, driving improvements in living standards and contributing to sustainable economic growth. In contrast, investments in agriculture show a less consistent impact, suggesting the need for more targeted strategies to enhance their effectiveness. The manufacturing sector also contributes to poverty alleviation, though its effects are less pronounced compared to SMEs. This study underscores the importance of sector-specific investment strategies, particularly focusing on SMEs, to achieve meaningful poverty reduction in conflict-affected regions. Additionally, it is recommended that policy makers prioritize resource allocation towards sectors demonstrating the highest returns on investment for poverty alleviation. The findings contribute to the broader discourse on development economics, highlighting key areas for continued research and policy refinement.
  • Thumbnail Image
    Item
    Statistical Analysis of Agricultural Production and Income Per Capita Growth Rate in Uganda 1988-2022
    (2024) Sakariye Abdullahi Abdi
    The relationship between Uganda's agricultural output and income per capita growth rate between 1988 and 2022 is examined using Statistical analysis. Multiple linear regression is used in the study to examine the data gathered during the designated time frame. The results show that agricultural output has been trending downward over time, but per capita income has been steadily rising. Table 4.2 in the analysis shows that agricultural production has a moderate impact on Uganda's income per capita growth rate, despite the country's diminishing agricultural output. These results are consistent with earlier studies, demonstrating the critical role that agriculture plays in the economic growth of countries, especially those with lower per capita incomes. Furthermore, the study shows a causal relationship—albeit one with a limited effect on total economic growth—between agricultural productivity and income per capita growth rate. These variables have statistically significant short- and long-term correlations, highlighting the long-lasting impact of agricultural activities on income levels throughout time. The study concludes by highlighting the significance of policies targeted at improving agricultural production, assisting the agricultural industry, and controlling variables like labor availability and interest rates to guarantee sustained income development and the decrease of poverty in Uganda. These findings offer insightful information for stakeholders, researchers, and politicians looking to advance the well-being and economic growth of agricultural economies
  • Thumbnail Image
    Item
    A Machine Learning-Based Model for Predicting Credit Facility Defaulters in Uganda
    (2024) Muddu George
    Predicting credit facility defaulters in Uganda poses a significant challenge, particularly for individuals lacking formal banking histories. This study aims to address this gap by leveraging machine learning techniques on a diverse set of financial data, including mobile money transactions, FinTech services, and traditional banking records. By developing a more inclusive creditworthiness assessment tool, we seek to enhance financial inclusion for underserved populations. Several machine learning algorithms to predict loan defaults were evaluated, including Logistic Regression, Support Vector Machines (SVM), and Extreme Gradient Boosting (XGBoost). The XGBoost model emerged as the most effective, achieving an accuracy of 95.23%, a recall of 73.32%, a precision of 94.11%, and an AUC of 0.8119. In contrast, the Logistic Regression model attained an accuracy of 89.53%, with a significantly lower recall of 43.24% and precision of 66.59%. The SVM model performed moderately, with an accuracy of 93.21% and a recall of 62.80%, but it still fell short compared to XGBoost. The findings highlight the potential of advanced machine learning models like XGBoost to significantly improve credit scoring systems. By providing a more accurate and inclusive tool for credit evaluation, financial institutions and policymakers can better identify potential defaulters, mitigate loan defaults, and foster economic growth among underserved communities