EEG Emotion Classification Using an Enhanced Transformer-CNN-BiLSTM Architecture with Dual Attention Mechanisms

TL;DR

This paper presents an enhanced hybrid deep learning model combining CNN, BiLSTM, and attention mechanisms for EEG-based emotion classification, achieving state-of-the-art accuracy and robustness in recognizing emotional states.

Contribution

The study introduces a novel hybrid architecture with dual attention mechanisms and regularization, significantly improving EEG emotion recognition performance over existing methods.

Findings

Achieved state-of-the-art classification accuracy on EEG emotion dataset.

Demonstrated robustness of the model through statistical cross-validation.

Identified covariance-based features as most influential for emotion discrimination.

Abstract

Electroencephalography (EEG)-based emotion recognition plays a critical role in affective computing and emerging decision-support systems, yet remains challenging due to high-dimensional, noisy, and subject-dependent signals. This study investigates whether hybrid deep learning architectures that integrate convolutional, recurrent, and attention-based components can improve emotion classification performance and robustness in EEG data. We propose an enhanced hybrid model that combines convolutional feature extraction, bidirectional temporal modeling, and self-attention mechanisms with regularization strategies to mitigate overfitting. Experiments conducted on a publicly available EEG dataset spanning three emotional states (neutral, positive, and negative) demonstrate that the proposed approach achieves state-of-the-art classification performance, significantly outperforming classical machine learning and neural baselines. Statistical tests confirm the robustness of these performance gains under cross-validation. Feature-level analyses further reveal that covariance-based EEG features contribute most strongly to emotion discrimination, highlighting the importance of inter-channel relationships in affective modeling. These findings suggest that carefully designed hybrid architectures can effectively balance predictive accuracy, robustness, and interpretability in EEG-based emotion recognition, with implications for applied affective computing and human-centered intelligent systems.