Key result
Deep learning EEG model predicts mental stress with ~98% accuracy.
Why the study?
Traditional deep learning techniques for EEG-based mental stress prediction face limitations such as temporal dynamics and feature extraction issues.
Population
Physiological parameters extracted from the EEG Psychiatric Disorders Dataset
Comparison
Proposed deep learning and combined transform model vs existing algorithms
Design
Simulated research study
Authors
Loading...
Hypothesis-generating for EEG-based stress detection; prospective validation required before cardiovascular applications.
A novel deep learning approach combining advanced transform-based feature extraction and ParNeXt v1-DB achieved high accuracy in predicting mental stress from EEG signals.
Agarwal et al. (2025) studied Mental stress. Deep learning-based classification model (ParNeXt v1-DB) with AFAWT and STFT-RT vs. Existing algorithms was evaluated on Accuracy of mental stress prediction. The proposed deep learning-based classification model using EEG signals achieved an accuracy of 97.8% in Dataset 1 and 96.3% in Dataset 2 for predicting mental stress.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: