Publications

IC3 2024: Sixteenth International Conference on Contemporary Computing

Safeguarding Personally Identifiable Information (PII) in an increasingly interconnected world presents intimidating challenges, particularly in low-resource languages like Luganda where computational resources for Natural Language Processing (NLP) are scarce. By directing models to key linguistic features and integrating Explainable AI (XAI) techniques, the study aims to improve both performance and transparency. Three distinct models were implemented i.e. luganda-ner-v6, DeBERTa-v3-Base, and afroxlmr-large-ner-masakhaner. Evaluation results demonstrate promising precision, recall, and F1 scores, while all models perform well, afroxlmr-large-ner- masakhaner consistently excels than the other models on all metrics. The afroxlmr-large-ner-masakhaner model has the highest accuracy with 96.3%, followed closely by luganda-ner-v6 at 95.1%, and deberta-v3-base at 93.9%.

International Journal on Economics, Finance and Sustainable Development

Like many developing countries, Uganda’s engagement in international research collaboration has been on the increase. However, lacks alignment with national and global goals e.g. and SDGs. hence, the study analyzes projects, using text mining to guide policy with insights from patterns uncovered. 2017 saw a surge in collaborative research. Text mining reveals key focus areas and shifts over time. Findings emphasize collaboration for effective SDG and national development goal achievement

American Journal of Social and Humanitarian Research

The intersection of gender and development has gained prominence in international development, with gender justice reshaping contemporary debates. This study explores the impact of gender on international research collaboration using Feature Analysis and binary logistic regression. Employing gradient boosting, text-mining, and natural language processing, the research focuses on projects registered at Uganda National Council of Science and Technology. Results reveal that the researcher's role (38.1%), lead researcher's gender (23.5%), estimated budget (7.7%), Ugandan nationality (7.1%), and age (5.3%) significantly influence the gender composition of research teams.

School of Statistics and Planning (SSP) Collection

Charcoal is a prime source of energy for heating functions in Uganda, and most especially in urban and peri urban areas. Surprisingly, policy makers pay little attention to the ways in which charcoal is produced and consumed. Developing an application tool to estimate the equivalent grid power and number of trees that would replace a given percentage of heating functions done by charcoal based on the energy balance concept and the forest conversion factors.

Traffic monitoring plays an important role in modern urban infrastructure management and public safety. In this study, an ensemble-based traffic monitoring model is developed utilizing traditional machine learning techniques. The ensemble model integrates K-Nearest Support Vector Machine (SVM), Decision Trees, and Random Forest algorithms to classify and identify vehicles (trucks and motorcycles) within a traffic video. The approach involved the conversion of traffic video into images, manual annotation of vehicles in images, feature extraction, and the training of machine learning models. Performance of these models was evaluated using the metrics of Area Under the Curve (AUC), Precision, Recall, and F1 score. Furthermore, an ensemble model from the 3 top-performing algorithms was constructed and its efficacy compared against individual models. Experimental results demonstrated the effectiveness of the ensemble approach, with the ensemble model showcasing superior performance compared to individual models.

🚀 The comprehensive guide on R programming is a resource for learning R, maily for beginner building a strong foundation or an experienced programmer refining skills. This guide explores R programming in depth, featuring exercises and quizzes at the end of each section to reinforce learning. Covering a broad range of topics—including getting started with R, operators, data structures, workin with data, data visualization, statistical modeling, interactive reporting with R Shiny, R Markdown. Created using R, RStudio, and key packages like RMarkdown and Blogdown. As a dynamic work in progress, it is continuously updated with fresh R content, ensuring it remains a valuable resource.