Musyimi Samuel Muthama, Dr. Kennedy Hadullo, Dr. Mvurya Mgala

Abstract

E-Learning is a transformative shift from traditional physical learning, yet it faces challenges in accommodating learners with diverse capabilities. While technology, particularly deep learning, has demonstrated innovative potential across sectors, the education field seeks adaptive e-learning as a learner-centered solution. This study will gather student learning behavior data during e-Learning for a period of one academic year from public universities at the Coast region in Kenya. This will be followed by the modelling process using selected common Deep learning algorithms such as neural networks. This study addresses these challenges by gathering and analyzing student learning behavior data over an academic year from public universities in the Kenyan Coast region. The data undergoes preprocessing and rigorous analysis, followed by modeling using prevalent deep learning algorithms, including neural networks. The study’s outcome is the development of an Adaptive E-learning model tailored for Higher Learning Institutions in Kenya. This model enhances students’ learning capabilities, leading to improved academic performance, personalized learning experiences, and a cycle of continuous education improvement.

Key words: Deep Learning, Adaptive learning, e-learning, algorithms