Kirinyaga University is a public university situated in Kutus Kerugoya in Kirinyaga County, Kenya.
Background: The rapid expansion of digital technologies has reshaped higher education, with digital libraries significantly increasing access to scholarly resources. Despite these advances, students with disabilities (SWDs) continue to face barriers that restrict effective participation in digital library environments across many universities.Purpose: This study examined the experiences of SWDs in accessing and using digital library resources in six Kenyan public universities, with particular focus on institutional infrastructure, policy frameworks, and staff engagement.Research Design: A qualitative descriptive and exploratory research design was adopted to gain in-depth understanding of accessibility conditions and user experiences in digital library contexts.Study Sample: The study involved 54 SWDs, including 33 visually impaired and 21 hearing impaired students, alongside library staff and disability coordinators from six public universities in Kenya.Data Collection and/or Analysis: Data were collected through semi-structured interviews, document review, and field observations. Thematic analysis was conducted using NVivo 14 to identify recurring patterns and key factors influencing digital inclusion.Results: Findings showed significant differences in accessibility and usability across institutions. Universities with integrated assistive technologies, trained and supportive staff, and structured support programs promoted autonomy and active engagement among SWDs. In contrast, outdated technologies, inaccessible platforms, and weak policy implementation limited participation. Barriers were technological, environmental, institutional, and individual, while facilitators included proactive staff support, peer networks, orientation programs, and basic adaptive tools.Conclusions: Sustainable digital inclusion requires coordinated institutional action combining assistive technologies, universal design principles, continuous staff training, and strong governance frameworks. Enforceable accessibility policies, inclusive platform design, and national standardization frameworks are recommended to improve equitable access to digital library resources for SWDs in Kenyan public universities.
The loan prediction models are ever-changing due to changes in technology, whereby financial institutions are adopting various technologies to automate the loan process. The surge of loan applicants with diverse attributes has accelerated the need for machine learning models which can incorporate different applicant attributes and improve accuracy in determining loan eligibility. While the use of individual machine learning models was more robust and accurate, these models have some limitations that may hinder the achievement of optimal results when establishing loan eligibility. Thus, the need to combine two or more individual models and leverage their strengths to improve accuracy and robustness. This study aimed to develop an eXtreme Gradient Boosting (XGBoost)-Support Vector Machine (SVM) hybrid model to determine loan eligibility in the banking sector. This work utilized secondary financial dataset from Google Kaggle. The dataset was preprocessed, transformed and used to train and test the models. Evaluation metrics, namely accuracy, precision, F1-score, recall and Receiver Operating Characteristics-Area Under Curve (ROC-AUC), were used to evaluate the performance and reliability of the XGBoost, SVM and the XGBoost-SVM hybrid model. The XGBoost-SVM hybrid model posted strong performance metrics results with accuracy of 0.78, precision of 0.27, a balanced recall of 0.49, F1-Score of 0.34 and AUC-ROC curve of 0.74. It was therefore evident that the hybrid model was able to leverage the standalone model's strength for better performance in determining loan eligibility.
Sustainable Development Goal 6 on clean water and sanitation is threatened by Escherichia coli (E. coli) contamination in wastewater, which poses grave dangers to the environment and public health. Microbial and chemical contaminants are present in wastewater from various sources, and treatment difficulties are growing due to urbanization. While biofilm formation, disinfectant resistance, and particle attachment increase bacterial survival, pathogenic E. coli strains can cause serious illness. To explain the dynamics of E. coli in wastewater systems, this study develops a deterministic mathematical model. MATLAB solvers and uncertainty and sensitivity techniques based on Latin hypercube sampling and partial rank correlation coefficients are used to analyze the model. The findings promote more effective wastewater treatment and microbial risk management by identifying key drivers of persistence.
Type 2 diabetes mellitus (T2DM) is an escalating public health burden in sub-Saharan Africa, where over half of affected individuals remain undiagnosed at clinical presentation. In Kenya, early risk identification is constrained by limited population-level screening infrastructure and the underutilization of data-driven predictive tools. This study applied a Random Forest (RF) machine learning classifier to the nationally representative 2022 Kenya Demographic and Health Survey (KDHS 2022) dataset to develop and evaluate a predictive model for T2DM risk among Kenyan adults aged 15–54 years. The analytical sample comprised 31,354 respondents drawn from all 47 counties of Kenya, of whom 272 (0.87%) were classified as diabetic, reflecting a severe class imbalance ratio of 114.3:1. Data preprocessing encompassed median imputation for missing values, min-max normalisation of continuous predictors, one-hot encoding of categorical variables, and Recursive Feature Elimination with Cross-Validation (RFECV) for feature selection. The Synthetic Minority Over-sampling Technique (SMOTE) was applied exclusively to the training partition to address class imbalance without contaminating test-set evaluation. The RF model was optimised via exhaustive grid search with five-fold stratified cross-validation, yielding a cross-validation Area Under the Receiver Operating Characteristic Curve (AUC-ROC) of 0.9895 (standard deviation (SD = 0.0004). At a calibrated classification threshold of 0.20, the model achieved a test-set sensitivity of 62.96%, specificity of 69.81%, balanced accuracy of 66.40%, and Matthews Correlation Coefficient (MCC) of 0.0659, correctly identifying 34 of 54 diabetic cases in the held-out test set. SHAP (SHapley Additive exPlanations) analysis identified age, wealth index, hypertension, employment status, and Body Mass Index (BMI) as the dominant predictors of T2DM risk. These findings establish a reproducible, nationally representative RF-based screening framework with direct implications for targeted public health intervention and early detection policy in Kenya.
As the world grows more connected and turns into a global village, technologically based practices become more embedded into the social fabric of society enabling greater interaction among individuals and groups. This increased role of technology has led scholars to seek to understand the role it can play in education (Churchill 2009; Ducate & Lomicka 2008; Goldman, Cohen & Sheahan 2008). Various technological practices have thus been used to enhance instructional strategies at all levels of learning. One such technological practice is personal web publishing which has emerged as a popular tool of journaling. Web publishing is increasingly becoming an integral part of supporting learning in many higher education settings (Andergassen, Behringer, Finlay, Gorra & Moore, 2009). In particular, the weblog is steadily gaining acceptance as a viable tool in the learning process. It is used in various ways including as a forum for reflection where students articulate ideas, analyze and make judgments about aspects of their learning, post commentaries and express opinions on a web page. Due to this important role, scholars have used diverse theoretical models to explore the impact of blogging on the learning process (Sakovic & McNaught, 2013). Notwithstanding the theoretical model used, the outcome has shown evidence of the usefulness of blogging especially from a teaching perspective. Sakovic and McNaught (2013) however point out that what is missing from the academic discourse on this topic is the learner experiences and perspective of its usefulness. In agreement, Xie and Sharma (2005) reveal that there is very little reported exploration into learners’ individual experiences and perceptions with the use of Weblogs for reflection. Indeed, I have not come across studies of this nature focusing on the context of my study. This means that while researchers increasingly become convinced of the usefulness of blogging, it is not clear whether the learners share in this conviction. It is therefore extremely important to understand the students’ feelings towards using Weblogs so as to make adjustments towards more appropriate uses to support individual reflection and group discourse. This study offers insights to researchers and instructors about learner experiences and perceptions of the use of weblogs for reflection particularly in the context of the study and lead to suggestions for its use. It has the potential to influence how weblogs are used in similar contexts. The study serves as a springboard for subsequent studies with learners of different educational levels, economic background and cultures as these are some of the factors that lead to disparity in perceptions and experiences. Since literature on individual perceptions and experiences with the use of Weblog is limited (Xie &Sharma, 2005; Sakovic & McNaught ,2013)), the findings also contribute to this body of knowledge. It is in light of this that I examine graduate students’ lived experiences and perceptions of the practice of course-specific reflection on weblogs