Brain2Vec: A Deep Learning Framework for EEG-Based Stress Detection Using CNN-LSTM-Attention

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mynoddin, Md, Dev, Troyee, Chakma, Rishita
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912427329716224
author Mynoddin, Md
Dev, Troyee
Chakma, Rishita
author_facet Mynoddin, Md
Dev, Troyee
Chakma, Rishita
contents Mental stress has become a pervasive factor affecting cognitive health and overall well-being, necessitating the development of robust, non-invasive diagnostic tools. Electroencephalogram (EEG) signals provide a direct window into neural activity, yet their non-stationary and high-dimensional nature poses significant modeling challenges. Here we introduce Brain2Vec, a new deep learning tool that classifies stress states from raw EEG recordings using a hybrid architecture of convolutional, recurrent, and attention mechanisms. The model begins with a series of convolutional layers to capture localized spatial dependencies, followed by an LSTM layer to model sequential temporal patterns, and concludes with an attention mechanism to emphasize informative temporal regions. We evaluate Brain2Vec on the DEAP dataset, applying bandpass filtering, z-score normalization, and epoch segmentation as part of a comprehensive preprocessing pipeline. Compared to traditional CNN-LSTM baselines, our proposed model achieves an AUC score of 0.68 and a validation accuracy of 81.25%. These findings demonstrate Brain2Vec's potential for integration into wearable stress monitoring platforms and personalized healthcare systems.
format Preprint
id arxiv_https___arxiv_org_abs_2506_11179
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Brain2Vec: A Deep Learning Framework for EEG-Based Stress Detection Using CNN-LSTM-Attention
Mynoddin, Md
Dev, Troyee
Chakma, Rishita
Signal Processing
Artificial Intelligence
Human-Computer Interaction
Neural and Evolutionary Computing
Neurons and Cognition
Mental stress has become a pervasive factor affecting cognitive health and overall well-being, necessitating the development of robust, non-invasive diagnostic tools. Electroencephalogram (EEG) signals provide a direct window into neural activity, yet their non-stationary and high-dimensional nature poses significant modeling challenges. Here we introduce Brain2Vec, a new deep learning tool that classifies stress states from raw EEG recordings using a hybrid architecture of convolutional, recurrent, and attention mechanisms. The model begins with a series of convolutional layers to capture localized spatial dependencies, followed by an LSTM layer to model sequential temporal patterns, and concludes with an attention mechanism to emphasize informative temporal regions. We evaluate Brain2Vec on the DEAP dataset, applying bandpass filtering, z-score normalization, and epoch segmentation as part of a comprehensive preprocessing pipeline. Compared to traditional CNN-LSTM baselines, our proposed model achieves an AUC score of 0.68 and a validation accuracy of 81.25%. These findings demonstrate Brain2Vec's potential for integration into wearable stress monitoring platforms and personalized healthcare systems.
title Brain2Vec: A Deep Learning Framework for EEG-Based Stress Detection Using CNN-LSTM-Attention
topic Signal Processing
Artificial Intelligence
Human-Computer Interaction
Neural and Evolutionary Computing
Neurons and Cognition
url https://arxiv.org/abs/2506.11179