EEG Emotion Classification Using an Enhanced Transformer-CNN-BiLSTM Architecture with Dual Attention Mechanisms
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912884042235904 |
|---|---|
| author | Karim, S M Rakib UI Lu, Wenyi Bala, Diponkor Rasul, Rownak Ara Goggins, Sean |
| author_facet | Karim, S M Rakib UI Lu, Wenyi Bala, Diponkor Rasul, Rownak Ara Goggins, Sean |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_06411 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | EEG Emotion Classification Using an Enhanced Transformer-CNN-BiLSTM Architecture with Dual Attention Mechanisms Karim, S M Rakib UI Lu, Wenyi Bala, Diponkor Rasul, Rownak Ara Goggins, Sean Machine Learning 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. |
| title | EEG Emotion Classification Using an Enhanced Transformer-CNN-BiLSTM Architecture with Dual Attention Mechanisms |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2602.06411 |