This research investigates the effectiveness of various virtual learning platforms; Zoom, Class Dojo, Google Classroom, and VICBHE (Virtual Interactive Classroom for Bilingual Higher Education), in delivering Core Curriculum and Minimum Academic Standards (CCMAS)-aligned content. The study evaluates platform features such as multimedia support, interactivity, student engagement, ease of assignment distribution, real-time feedback, CCMAS curriculum alignment, ease of use for teachers, and content delivery. This study reveals the platforms ' strengths and weaknesses in facilitating learning outcomes through a combination of regression analysis and experimental data from multiple educational settings. The findings indicate that student engagement and curriculum alignment have the most significant impact on educational success, with Google Classroom emerging as the most effective platform overall. VICBHE, designed to deliver region-specific content, excels in curriculum alignment but faces challenges in interactivity and real-time feedback, limiting its effectiveness in dynamic learning environments. The research concludes with recommendations for platform improvements and strategies for optimizing virtual learning in diverse educational contexts.

Predicting student performance in higher education is challenging when data distributions differ across cohorts or programs. This paper proposes an adaptive transfer learning framework to improve prediction accuracy on a student dataset with simulated domain shifts. The dataset contains demographic, academic, and macroeconomic features for university students, with the target outcome indicating whether a student graduated, dropped out, or is still enrolled. We partition the data into distinct domains by academic program to emulate distributional differences. An Artificial Neural Network (ANN) model is first trained on a source domain and then fine-tuned on a target domain with a subset of layer weights frozen. We evaluate model performance using Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and coefficient of determination (R^2), comparing the proposed transfer learning approach against a baseline without transfer. The results show that transfer learning significantly improves prediction accuracy: RMSE and MAE are reduced while R^2 increases on the target domain, indicating better generalization. The findings demonstrate that an ANN-based transfer learning method can effectively mitigate domain shift in student performance prediction. This study presents the benefits of transfer learning in an educational context by using attribute-based domain separation, offering a practical approach for academic institutions to predict student outcomes across different programs or semesters.

This study investigates the performance of students enrolled in programming courses offered under the Sandwich Educational System (SES) in Ghanaian universities and colleges. SES is a unique educational approach that combines academic studies with practical work experience. This study examines various teaching models employed within the SES for programming education to identify any significant relationship between teaching methods and student academic performance. The target population for this study comprised students enrolled in computing education-related programs within the SES, with a specific focus on those undertaking programming courses. A single study group of students pursuing the Bachelor of Education programme in Information Technology (B.Ed. IT) under the sandwich mode at University X was selected to ensure efficient research management in this study. Employing a mixed-methods research design, quantitative and qualitative data were collected and analysed using descriptive and inferential statistics. A survey was administered to 218 of the 357 students in the study group during the designated survey period. Additionally, a seven-year longitudinal quasi-experiment involving five different year groups in the B.Ed IT sandwich programme at University X was conducted to examine the relationship between student performance and teaching methods within SES. The findings of this study do not demonstrate a significant difference in academic performance among students taught using different teaching methods in SES. However, it is crucial to acknowledge the study's limitations, which necessitate considering the findings as insightful observations rather than as conclusive results. This study recommends enhancing students' prior exposure to programming and adopting innovative teaching methods to improve their academic performance. Future research should address the limitations of this study by utilising a more rigorous experimental design, such as a randomised controlled trial, and exploring additional factors that may influence student performance within the SES. Such endeavours would enable more robust causal inferences to be drawn.

The increasing affordability of smartphones and the rapid development of internet connections have significantly shifted consumer shopping patterns from traditional offline methods to online platforms. This transformation has been further accelerated by the COVID-19 pandemic, which forced many businesses and consumers to adapt to digital transactions. However, organic farmers in East Kalimantan continue to face challenges in marketing their products due to limited market access, lack of digital literacy, and logistical barriers. This research presents the development of an Android-based marketplace application aimed at improving the marketing of organic agricultural products by local farmers. The system increases accessibility, enhances efficiency, and supports sustainable agricultural practices. The development process involves observation and analysis, utilizing UML for system modeling. The marketplace was developed using Android Studio, MySQL for database management, and API integration to facilitate secure digital payments and location-based map services. Key features of the system include product management, real-time inventory tracking, digital payment gateways, and logistics support tailored to local needs. Initial implementation results demonstrate that this system effectively expands market reach, enhances marketing efficiency, and supports the sustainability of organic farming. Additionally, it contributes to building a robust digital ecosystem for the agricultural sector in Indonesia.

This study investigates the incorporation of artificial intelligence (AI)-driven technologies, in facilitating automation, intelligent decision-making, predictive analytics, and responsive urban management, as essentials to the change inherent in developing smart cities. This need for efficiency, sustainability, and improved quality of life has led to a radical change in contemporary urban planning as urban areas are gradually developing into smart cities. Through networked systems and real-time data analysis, smart cities use cutting-edge technologies to optimize governance, infrastructure, and services. Smart energy grids, waste optimization, adaptive traffic control, and customized citizen services are all made possible by these technologies. However, an agile and iterative approach to technology implementation is necessary due to the dynamic and complex nature of urban systems. This study examines Agile methodology as a strategic framework for the creation and application of AI-driven tools in smart city settings. Agile's fundamental principles, namely collaborative development, incremental delivery, and responsiveness to change, align well with the demands of adjusting to changing user needs, technological advancements, and sociopolitical factors. This study examines how Agile practices support stakeholder coordination, iterative prototyping, and quick adaptation in AI-based urban solutions through a mixed-methods research design that includes case studies from a few chosen smart city initiatives. The results show that the proposed Nigeria Agile Integration for Smart City Transformation (NAI-SMART) framework showed that Abuja, Enugu, and Ibadan are more technology-compliant at the time of this study than a few other cities used in this research. NAI-SMART was able to achieve this via AI-based technologies namely GRU time series model, Reinforcement learning, XGBoost, and Scikit-learn that were employed during NAI-SMART Urban Intelligence Engine (NAI-SMART UIE) model creation. This research therefore, contributes to both theory and practice by proposing a step-by-step framework for AI-powered smart city development using Agile principles. Ultimately, the study underscores the synergistic potential of AI and Agile in actualizing the vision of inclusive, data-driven, and adaptive smart cities in Nigeria.