Developing a Memetic Algorithm for Personalized Learning in Intelligent E-Learning Systems

Personalized learning in intelligent E-learning systems is a pivotal area of research, aiming to enhance educational outcomes by tailoring learning experiences to individual needs. The paper presents a comprehensive framework for personalized learning in intelligent E-learning systems, emphasizing the development of a Memetic Algorithm optimized for educational outcomes. Leveraging a dataset from the Kaggle repository, the proposed methodology integrates Min-Max Normalization for preprocessing. Feature selection employs Recursive Feature Elimination (RFE) to systematically identify relevant attributes. The Memetic Algorithm design combines genetic operators with local search strategies, achieving a balance between exploration and exploitation. Results showcase the proposed method's significant superiority, achieving 98% accuracy, surpassing existing approaches such as KNN, DT and RF by 10.5%. The implementation, carried out in Python, underscores the algorithm's practical applicability. This research contributes a robust personalized learning framework, showcasing the efficacy of the proposed Memetic Algorithm in advancing educational outcomes.