EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Deep Hybrid CNN–BiLSTM–Attention Model for EEG Classification Using Wavelet Features

Tony Bayan, Daisy Das, Nabamita Deb

Annals of Neurosciences · 23.01.2026

DOI: 10.1177/09727531251396337 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Annals of Neurosciences, online erschienen am 23.01.2026. Verfasst von Tony Bayan und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Information Technology, Gauhati University, Guwahati, Assam, India. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background and Purpose Electroencephalography (EEG) is a popular non-invasive method for studying brain dynamics because of its excellent temporal resolution. However, the non-stationarity, intersubject variability and class imbalance of EEG data, make it difficult to automatically discriminate between brain states that correspond to various cognitive or sensory circumstances. With the use of a deep hybrid convolutional neural networks (CNNs) and bidirectional long short-term memory (BiLSTM) networks with an attention architecture intended to improve discriminative learning from wavelet-based time–frequency features, this study attempts to categorise EEG recordings into discrete brain states recorded prior to and during auditory (mantra) stimulation.

Methods

Experienced practitioners (mean age: 37 ± 6 years; mean practice: 5 years) had their EEG data recorded in two different experimental settings: (a) When they were at rest before the auditory stimulus and (b) while they were listening to mantras. Each segment’s time–frequency representations were produced using wavelet transforms and fed into a hybrid model that combined convolutional, recurrent and attention layers. To guarantee steady convergence, adaptive learning rate scheduling and early stopping were used in the model optimisation process.

Results

With CNN (76.92%), long short-term memory (LSTM) (75.30%), CNN+LSTM (84.62%) and CNN+BiLSTM (88.65%), baseline models performed moderately. The suggested CNN–BiLSTM–Attention model achieved an independent test accuracy of 99.46%, greatly outperforming all baselines. High discriminative capability was confirmed by the receiver operating characteristic (ROC) analysis, which produced an AUC near 1.0.

Conclusion

The inclusion of convolutional, recurrent and attention methods greatly improves spatial–temporal feature learning, as demonstrated by the suggested framework’s ability to distinguish between resting and during mantra EEG states. These results demonstrate the model’s resilience and possible use in neurophysiological monitoring and real-time cognitive state detection.

Schlagwörter

Stichwörter der Autor:innen

Convolutional neural network (CNN)OMlong short-term memory (LSTM)mantrameditationwavelet

Autor:innen und Institutionen

  • Department of Information Technology, Gauhati University, Guwahati, Assam, India.

Zitieren

APA

Bayan, T., Das, D., & Deb, N. (2026). Deep Hybrid CNN–BiLSTM–Attention Model for EEG Classification Using Wavelet Features. Annals of Neurosciences. https://doi.org/10.1177/09727531251396337

Vancouver

Bayan T, Das D, Deb N. Deep Hybrid CNN–BiLSTM–Attention Model for EEG Classification Using Wavelet Features. Annals of Neurosciences. 2026. doi:10.1177/09727531251396337

BibTeX
@article{Bayan2026,
  author = {Bayan, Tony and Das, Daisy and Deb, Nabamita},
  title = {Deep Hybrid CNN–BiLSTM–Attention Model for EEG Classification Using Wavelet Features},
  journal = {Annals of Neurosciences},
  year = {2026},
  doi = {10.1177/09727531251396337}
}
Kostenlos starten →