Result Details
An Interpretable Machine Learning Framework for Multilevel EEG-Based Stress Recognition
Amin Hafeez Ullah
Bhatti Mehwish S.
Malik Aamir Saeed, prof., Ph.D., DCSY (FIT)
Stress is a hallmark of the majority mental health disorders, yet objective measures for its quantification remain
limited. Electroencephalography (EEG) provides a scalable
window into brain dynamics, but existing approaches often
reduce this multiscale condition to binary states and rely on
narrow spectral bands. This study presents a subject-specific
framework to classify four stress levels, labeled using the Depression Anxiety Stress Scales (DASS), from the resting-state
EEG without requiring task performance, a key advantage
for clinical applicability. EEG data from 75 subjects were
preprocessed with Independent Component Analysis (ICA)
and AutoReject, followed by segmentation into overlapping
epochs. From these segments, statistical, spectral, entropybased, Hjorth, and fractal features were extracted. Correlation filtering and ANOVA were applied before subject-level
cross-validation with imbalance correction. Models using 3s
epochs achieved 92.8% accuracy and 92.6% macro-F1, outperforming 5s windows and deep learning baselines. SHAP
confirmed physiological relevance, highlighting EEG-based
features as objective neural markers of stress.
EEG, Stress, Machine learning, XGBoost, SHAP,
@proceedings{BUT211662,
editor="Muhammad Asad {Zaheer} and {} and {} and Aamir Saeed {Malik}",
title="An Interpretable Machine Learning Framework for Multilevel EEG-Based Stress Recognition",
year="2026",
pages="5",
publisher="Institute of Electrical and Electronics Engineers",
address="Barcelona",
doi="10.1109/ICASSP55912.2026.11461347",
url="https://ieeexplore.ieee.org/abstract/document/11461347"
}