What question did this study set out to answer?

This research aims to improve emotion recognition accuracy using EEG by addressing common challenges like noise and class imbalance with a new framework.

June 13, 2026Open Access

Modeling multiscale neural dynamics for EEG-based emotion recognition using an attentive wavelet–transformer framework

Key Points

This research aims to improve emotion recognition accuracy using EEG by addressing common challenges like noise and class imbalance with a new framework.
Introduced the Attentive Wavelet-Transformer Network (AWT-Net) to integrate various advanced signal processing techniques.
Evaluated AWT-Net on a custom EEG dataset (2,132 samples, 14 channels, 28 subjects) and the DEAP dataset (1,280 trials, 40 channels, 32 subjects).
Compared AWT-Net's performance against baseline models such as LSTM and CNN-LSTM under subject-dependent and independent protocols.
AWT-Net achieved a window-level accuracy of 99.61% on DEAP and 99.34% on the custom EEG dataset.
Under stricter evaluation, trial-wise accuracy was 99.30% and subject-independent was 97.23% on DEAP.
Error rates reduced to 0.70% for EEG and 0.39% for DEAP, significantly lower than baseline models showing effect sizes of Cohen’s d: 1.82–2.14.

Abstract

Electroencephalography (EEG)-based emotion recognition faces challenges such as signal noise, non-stationarity, inter-subject variability, and class imbalance, limiting its practical application in affective computing and clinical diagnostics. This study introduces the Attentive Wavelet-Transformer Network (AWT-Net), a novel framework integrating Hierarchical Wavelet Packet Decomposition (HWPD), Empirical Wavelet Transform with Kalman filtering (EWT-Kalman), Multi-Head Self-Attention (MHSA), and a Hybrid Spatio-Temporal Transformer (HSTT) to address these issues. The proposed work is evaluated on a custom EEG dataset (2,132 samples, 14 channels, 28 subjects) and the DEAP dataset (1,280 trials, 40 channels, 32 subjects), AWT-Net achieves window-level, subject-dependent accuracy of 99.61% on DEAP and 99.34% on custom EEG. Under stricter evaluation protocols, accuracy is 99.30% (trial-wise grouped) and 97.23% (subject-independent LOSO) on DEAP, demonstrating robust generalization across varying validation conditions. Comparisons with baseline models (LSTM: 89.42%, CNN-LSTM: 91.75%) are provided under equivalent subject-dependent protocols, while LOSO comparisons (Elrefaiy et al.: 97.00%, Bagherzadeh et al.: ~77.75%) highlight cross-subject performance. Error rates are significantly reduced to 0.70% (EEG) and 0.39% (DEAP), compared to 6.69–10.58% for baselines, with statistical validation confirming large effect sizes (Cohen’s d: 1.82–2.14). AWT-Net’s adaptive focal loss mitigates class imbalance, while HWPD and EWT-Kalman enhance noise robustness. These results demonstrate AWT-Net’s potential for real-time emotion recognition, advancing applications in healthcare and human-computer interaction.

Ask AI

Helpful

Bookmark

View Full Paper