eng Oriental Scientific Publishing Company Biomedical and Pharmacology Journal 0974-6242 2026-10-29 19 4 73815 article Sudhakar Tukkaram 1 Hari Krishnan Gurumurthy 2 Bethanney Janney J 1 Mohadass Ganapathy 3 Sindu Divakaran 1 Vinod Srinivasan 4 Department of Biomedical Engineering, Sathyabama Institute of Science and Technology, Chennai, India. Department of Electrical and Electronics Engineering, School of Engineering, Mohan Babu University, Tirupati, India Department of Biomedical Engineering, Saveetha School of Engineering, Saveetha Institute of Medical and Technical Sciences, Saveetha University, Chennai, India Department of Electrical and Electronics Engineering, Jerusalem College of Engineering, Chennai, India We investigated EEG-based assessment of cognitive workload during task-based learning aligned with a simplified, three-level Bloom framework (lower, intermediate, higher). EEG was recorded using a three-electrode montage during level-specific problem blocks, interleaved with rest periods. Signals were preprocessed (band-pass filtered 1–40 Hz, notch filtered as required, and baseline corrected), segmented by task level, and summarised using alpha-band (8–13 Hz) and time-domain features.Forty healthy adults (mean age 21.4 ± 2.1 years; 22 male, 18 female) were recruited from an academic institution. Four supervised classifiers were trained and evaluated (Logistic Regression, SVM-RBF, Random Forest, and shallow MLP) to discriminate the three Bloom levels using a strict subject-wise data partition (TRAIN/VALIDATION/TEST = 28/6/6 subjects) to prevent information leakage; all feature-scaling transforms were fit on the training split only. Performance was evaluated with stratified cross-validation and a held-out test set and summarised by accuracy, macro-F1, ROC-AUC, and confusion matrices. Classifiers achieved robust discrimination across levels on internal validation and held-out testing, with the aggregate model attaining 96.30% test accuracy and 99.76% AUC. Alpha-band power exhibited a systematic increase from Lower to Higher Bloom levels, consistent with inhibitory gating and internally-directed processing mechanisms. The complex and context-dependent nature of alpha oscillations, including the well-known event-related desynchronisation under externally-driven cognitive load, is acknowledged and discussed. Limitations include reduced spatial specificity inherent to the three-electrode montage, modest sample size, absence of concurrent behavioural performance validation, and internal-only validation; future work should incorporate higher-density EEG, paired behavioural metrics, and preregistered external replication. https://biomedpharmajournal.org/vol19no4/neurophysiological-assessment-of-cognitive-load-using-eeg-during-task-based-learning-categorized-by-blooms-taxonomy/ Alpha band Bloom’s taxonomy Cognitive workload EEG Task-based learning