EEG-Driven Machine Learning Framework for Student Cognitive Load Classification

Understanding differences in learning abilities is essential for improving education. This paper presents a framework to differentiate between learners using EEG data. The framework identifies critical factors that influence learning experiences by applying data-driven approaches and statistical methods. It includes analyses such as band power, entropy calculation, and coherence measurement across EEG channels. The extracted features are used to train a classifier and to identify cognitive behavior patterns. The framework's accuracy is verified using cross-validation, classification reports, and confusion matrices. The experimental analysis shows major improvements in cognitive pattern understanding and identification. This framework provides educators with actionable insights to design personalized learning strategies. By enhancing the understanding of individual learning dynamics, the framework has the potential to optimize educational outcomes across diverse learner profiles.