ULK Scientific Journal

Leveraging Data Exchange and Random Forest Regression Model for Precision Farming: Predicting Soil pH to Enhance Agricultural Efficiency

Jean Bosco Musabe — 2025-02-14

Precision farming is revolutionizing agriculture by incorporating advanced technologies and data-driven methods to improve crop production. However, a gap persists in the practical use of machine learning (ML) models and real-time data exchange for optimizing soil conditions to enhance crop yields, reduce resource waste, and limit environmental impact. This study aims to bridge this gap by leveraging ML, particularly focusing on soil pH prediction to ensure optimal nutrient absorption for plant health. Data was collected from Kigali Independent University ULK in Gasabo District, Kigali City, Rwanda, using seven soil sensors measuring soil moisture, temperature, humidity, NPK levels, and pH. The study applied a Random Forest regression model to predict soil pH, achieving an impressive accuracy of 99.9%, surpassing several contemporary models. The results highlight the effectiveness of ML in offering valuable insights to farmers, promoting sustainable and profitable agricultural practices. The research emphasizes the importance of continuous technological innovation and collaboration to push the boundaries of modern agriculture.

Understanding Root causes of Low Academic Engagement among University Students and Strategies for Improvement: A case of Rwanda

Cyprien Sikubwabo — 2025-02-14

This study investigated the root causes of low academic engagement among university students in Rwanda and identifies strategies to improve their involvement in academic activities. A mixed- methods approach was used, with a sample of 394 students and 198 lecturers from five universities. Stratified random sampling was used for students, while simple random sampling was used for lecturers. The sample size was determined using Slovin’s formula. Data were collected through structured questionnaires, focus group discussion and classroom observations. Quantitative data were analyzed using descriptive statistics (frequencies, percentages, means, and standard deviations), while qualitative data were analyzed using thematic analysis. The findings revealed that students exhibit low levels of engagement in key academic behaviors, such as attending classes regularly, participating in discussions, and utilizing academic support services. Contributing factors include a perceived lack of value in higher education, limited job prospects after graduation, excessive use of social media, and insufficient enforcement of university policies. Students also reported low levels of enthusiasm and academic curiosity, further aggravating the issue. The study identified several important strategies to address these challenges: the implementation of mentorship programs, career counseling, academic advising, and digital literacy workshops. Additionally, stricter enforcement of attendance and academic regulations, along with the adoption of innovative teaching methods and active learning strategies, are proposed to create a more engaging academic environment. The study stresses the need for universities to align their offerings with students' career expectations and to foster a supportive, interactive learning environment to enhance student engagement and academic success.

e Effect of Generational Diversity on Workforce Performance in the Rwandan Banking Sector

Jean De Dieu Mfitiryayo — 2025-02-14

The research explored the influence of generational diversity on employee performance in the Rwandan banking sector, focusing on the Central Bank of Rwanda. The study aimed to assess the impact of generational differences on workplace dynamics, communication, and employee effectiveness, addressing three key objectives: examining communication styles, the role of ethics in motivation, and the effect of learning and development on work quality. The study involved a sample of 108 employees across six departments. Findings revealed significant generational differences in communication preferences, with 24.1% favoring digital methods and 20.4% traditional approaches. A strong correlation (R = 0.787) linked communication styles to teamwork, highlighting the need for tailored strategies to improve generational collaboration. On ethics, 89.8% trusted the bank’s leadership, and ethical behavior strongly influenced motivation, particularly among Millennials and Generation Z, with a correlation (R = 0.753) indicating that ethics impacted motivation. Regarding Learning and Development, 38% of employees engaged infrequently, while 47.2% participated occasionally, with Millennials being the most involved. A significant correlation (R = 0.791) showed that Learning and Development participation improved work quality. The study emphasized aligning organizational ethics with generational values and personalizing Learning and Development programs for diverse needs. Recommendations included offering communication training, adopting hybrid communication methods, and fostering intergenerational teamwork. Strengthening ethical leadership, creating inclusive ethical frameworks, and implementing recognition programs were suggested to enhance motivation. In Learning and Development, expanding program accessibility, customizing initiatives for Millennials, encouraging intergenerational learning and regularly assessing outcomes were recommended to better align with employee and organizational goals.

Examining the Influence of Employee Training and Development on Service Delivery in Rwandan Local Government Entities: A Case of Rubavu District, Rwanda

Jean Bosco Tuyishime — 2025-02-14

This study examined the influence of employee training and development on service delivery in local government entities in Rubavu District, Rwanda. The study investigated the influence of four key factors namely: (1) employee training programs, (2) participation in training sessions, (3) access to training resources, and (4) employee feedback and satisfaction with training. A sample of 237 employees from various local government offices, including district, sector, cell offices, and the District Administration Security Support Organ (DASSO), participated in the study. Data was collected using questionnaires and semi- structured interview and it was analyzed using descriptive statistics and correlation analysis. The results indicated that all four factors significantly and positively influenced service delivery, with training programs, participation rates, access to training resources, and employee satisfaction contributing to improved public service performance. Based on these findings, the study recommended that Rubavu District: (1) increase the frequency of training sessions, (2) design more motivating and relevant training programs, (3) enhance access to training resources, and (4) expand feedback mechanisms to evaluate the impact of training on service quality. At a national level, the Government of Rwanda should develop a standardized framework for local government training programs, while the Ministry of Local Government should advocate for increased funding for training and create platforms for knowledge exchange across districts. These recommendations aim to improve the effectiveness and equity of public service delivery in Rubavu District and beyond.

Perceptions of International Students from Non-English Speaking Backgrounds regarding English Intensive Language Course. A Case of Francophone West African Students Studying at Kigali Independent University-ULK (Rwanda)

Jacques Ndahayo — 2025-02-14

Predicting School Dropout Using Machine Learning Models: A Case Study of Nyanza District, Rwanda

Jean Bosco Musabe — 2025-02-14

This study investigates the application of machine learning models to predict school dropouts in Nyanza District, Rwanda, addressing the challenge of early identification of at-risk students. By adopting a classification-based approach, the research analyzes data from parents or guardians, school instructors, and teachers to pinpoint contributing factors such as socioeconomic conditions, academic performance, and family background. The research explores a range of machine learning models, including Logistic Regression, Decision Tree Classifier, Gradient Boosting Regression, Artificial Neural Networks (ANN), K-Nearest Neighbors (KNN), and Naive Bayes. These models are evaluated using metrics like accuracy, recall, precision, F1 score, and ROC-AUC, with an emphasis on balancing recall (identifying at- risk students) and precision. The study reveals that different models offer varying levels of performance. KNN achieves a notable accuracy of 0.72 and an exceptional recall of 0.91, successfully identifying 91% of at-risk students. Naive Bayes, however, is highlighted as the most well rounded model, balancing precision and recall effectively. This research fills the gap in predictive analytics for dropout prevention in Nyanza District and offers actionable insights for educators and policymakers to enhance student retention through targeted interventions.

Organizational Culture Development and Employee Retention in Rwanda’s Public Sector: Analysis of the Central Bank of Rwanda

Mfitiryayo Jean de Dieu — 2025-02-14

This study evaluates the influence of organizational culture development on employee retention at the Central Bank of Rwanda (CBR), focusing on communication style, leadership effectiveness, and diversity and inclusion. A cross-sectional research design combined quantitative and qualitative methods. Data were gathered from 108 respondents using structured questionnaires and interviews, supported by secondary sources from 2018-2023. Quantitative data were analyzed using descriptive and inferential statistics, including Pearson correlation and regression analyses, while qualitative insights explored participant perspectives. Key organizational culture factors examined included structure, leadership, communication, and values, and they were assessed against employee retention indicators such as tenure, engagement, and performance. The study's regression analysis revealed that organizational culture significantly influences employee retention, with an R-squared value of 0.664 and a notable F-value supporting the model's effectiveness. Findings highlight the critical role of communication, value alignment, and collaborative culture in improving retention. The study recommends enhancing communication and engagement, aligning organizational values with operational activities, and leveraging demographic diversity. Promoting supportive culture policies, best retention practices, and targeted training programs are emphasized as strategies to foster employee satisfaction and organizational loyalty. Ultimately, the research underscores the importance of organizational culture development as a vital strategy for improving retention outcomes, highlighting the need for sustained investment in culture enhancement and effective communication.