EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

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

R S Soundariya, P Thangaraj

Frontiers in Computational Neuroscience · 09.06.2026 · 20

DOI: 10.3389/fncom.2026.1775449 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Computational Neuroscience, online erschienen am 09.06.2026. Verfasst von R S Soundariya und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science and Engineering, Bannari Amman Institute of Technology, Sathyamangalam, Tamil Nadu, India. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

Stichwörter der Autor:innen

affective computingdeep learningelectroencephalography (EEG)emotion recognitionmultiscale neural dynamicsspatio-temporal modellingtransformer networkswavelet transform

Autor:innen und Institutionen

  • Department of Computer Science and Engineering, Bannari Amman Institute of Technology, Sathyamangalam, Tamil Nadu, India.
  • Department of Computer Science and Engineering, Kangeyam Institute of Technology, Kangeyam, Tamil Nadu, India.

Zitieren

APA

Soundariya, R. S., & Thangaraj, P. (2026). Modeling multiscale neural dynamics for EEG-based emotion recognition using an attentive wavelet–transformer framework. Frontiers in Computational Neuroscience, 20. https://doi.org/10.3389/fncom.2026.1775449

Vancouver

Soundariya RS, Thangaraj P. Modeling multiscale neural dynamics for EEG-based emotion recognition using an attentive wavelet–transformer framework. Frontiers in Computational Neuroscience. 2026;20. doi:10.3389/fncom.2026.1775449

BibTeX
@article{Soundariya2026,
  author = {Soundariya, R S and Thangaraj, P},
  title = {Modeling multiscale neural dynamics for EEG-based emotion recognition using an attentive wavelet–transformer framework},
  journal = {Frontiers in Computational Neuroscience},
  year = {2026},
  volume = {20},
  doi = {10.3389/fncom.2026.1775449}
}
Kostenlos starten →