EEG Slope Entropy and Affective Self-Report Fusion for Cognitive Workload Classification: A Multi-Stage Pipeline with Explainable AI Evaluation

Classifying cognitive workload (CWL) from neurophysiological signals remains a central challenge in affective computing. We present a multi-stage pipeline fusing EEG Slope Entropy (SlpEn; M=3, δ=0.001, γ=1.0, 1-s window) on the DEAP corpus, evaluating five affective dimensions (Valence, Arousal, Dominance, Liking, Familiarity) individually and across all ten pairwise combinations. Random Forest (RF) and XGBoost classifiers were assessed with 5-fold stratified cross-validation on a binary HIGH/LOW CWL task derived from a disjunctive threshold rule over Arousal and Dominance. Results are, therefore, reported separately for rule-constituentand non-constituent features. Arousal (RF: 81.48%, AUC: 0.896) and Dominance (71.64%, AUC: 0.811) attain the highest apparent accuracies but largely reconstruct the labelling rule. Among non-constituent dimensions, Valence is the strongest legitimate predictor (RF: 64.14%, AUC: 0.684), followed by Liking (58.75%) and Familiarity (57.93%). Slope entropy adds 3.6–4.1 pp over the strongest affective baselines and up to 23.4 pp over the SlpEn-alone baseline, with complete insensitivity to blend weighting. The Arousal + Dominance pair (RF: 99.84%, AUC: 1.000) fully reconstructs the rule and is excluded from substantive interpretation. Valence + Arousal reaches 87.27% but remains partially rule-inflated. All results are reported as mean with 95%.