Skip to content
DraconiticResearch
Search Sources API
203,203 studies31 sourcesUpdated 49 min ago
Peer-reviewedCC BYFrontiers in computational neuroscience

An attention-enhanced hybrid CNN-BiLSTM framework for multiclass epileptic seizure recognition using EEG signals.

  • Bobbinpreet Kaur1
  • Sheenam Middha1
  • Aleem Ali1
  • Noman Khan2
  • Reham Alhejaili3
  • Ahmed H Almutairi4
4 affiliations
  1. 1Department of Computer Science and Engineering, University Institute of Engineering (UIE) Chandigarh University, Gharuan, Punjab, India.
  2. 2Department of Computer Science and Engineering, Sejong University, Seoul, Republic of Korea.
  3. 3Department of Computer Science and Artificial Intelligence, College of Computer Science and Engineering, University of Jeddah, Jeddah, Saudi Arabia.
  4. 4Department of Computer Science, Applied College, Northern Border University, Arar, Saudi Arabia.
Read full textPDFDOICite

Abstract

Introduction

Electroencephalogram (EEG) signal classification plays a pivotal role in brain-computer interfaces (BCIs) and the diagnosis of neurological disorders. However, the non-stationary, non-linear, and low signal-to-noise ratio characteristics of EEG signals make accurate feature extraction challenging. Conventional deep learning approaches often struggle to simultaneously capture localized transient patterns, deep temporal dependencies, and long-range contextual relationships within EEG signals.Methods

To address these challenges, an optimized end-to-end hybrid deep learning framework, termed CNN-BiLSTM-MHSA, is proposed for multiclass epileptic seizure recognition. The architecture sequentially integrates a multilayer one-dimensional Convolutional Neural Network (CNN) for localized feature extraction, a Bidirectional Long Short-Term Memory (BiLSTM) network for capturing forward and backward temporal dependencies, and a Multi-Head Self-Attention (MHSA) mechanism for dynamically emphasizing discriminative neurological events. Robust preprocessing includes Butterworth bandpass filtering, Z-score normalization, and data augmentation using Gaussian noise injection and amplitude scaling. The framework was evaluated on the UCI/Kaggle Epileptic Seizure Recognition dataset comprising 11,500 EEG segments distributed across five classes.Results

The proposed framework achieved an overall accuracy of 98.83%, precision of 98.95%, recall (sensitivity) of 98.84%, F1-score of 98.90%, specificity of 99.71%, balanced accuracy of 98.84%, ROC-AUC of 99.80%, and PR-AUC of 99.72%. Class-wise accuracies exceeded 99% for most categories, with one seizure class achieving perfect recognition. Comparative evaluation further demonstrated that the proposed framework outperformed several recent state-of-the-art EEG seizure classification methods.Discussion

The superior performance can be attributed to the complementary representation capabilities of the hybrid architecture. CNN layers effectively learn localized signal patterns, BiLSTM captures bidirectional temporal dependencies, and MHSA enhances the representation of long-range contextual relationships by assigning greater importance to informative temporal regions. The combination of robust preprocessing and data augmentation further contributes to improved generalization and classification reliability.

Related

  1. YOLO-CBNet: A robust attention-enhanced detection framework for underwater fish recognition in aquaculture environments
    Mahdi Hamzaoui, Leila Bousbia, Mohamed Ould-Elhassen Aoueileyine +2
    PLOS OnePeer-reviewedCC BY 4.0Full textNeuroscienceZoology & animal behaviourPLOS
  2. VAD-EmotionNet: a spatial-spectral attention network for EEG emotion recognition in the 3D affective space
    Xiujun Li, Shen Yan, Dan Tong +2
    Cognitive NeurodynamicsPeer-reviewedLicence not statedFull textNeurosciencePMC
  3. Naturalistic face-directed attention predicts face recognition ability
    D. White, V. P. L. Varela, M. Piggott +4
    bioRxivPreprintCC BY-NCFull textZoology & animal behaviourbioRxiv
  4. Probing EEG Foundation Model Attention Maps for Lightweight Interpretable Emotion Recognition
    L. N. Arvanitopoulos, A. Dragomir, C. A. Fidas +1
    bioRxivPreprintCC BYFull textNeurosciencebioRxiv
  5. Subtle positive facial expression recognition is enhanced by comedy viewing: individual differences in empathy and depressive tendencies
    Keisuke Adachi, Miyu Kashiwa, Masaumi Shimizu +3
    Scientific ReportsPeer-reviewedCC BYFull textNeuroscienceDOAJ

Cite

BibTeXRIS
BibTeX
@article{kaur2026attentionenhanced,
  title = {{An attention-enhanced hybrid CNN-BiLSTM framework for multiclass epileptic seizure recognition using EEG signals.}},
  author = {Bobbinpreet Kaur and Sheenam Middha and Aleem Ali and Noman Khan and Reham Alhejaili and Ahmed H Almutairi},
  journal = {Frontiers in computational neuroscience},
  year = {2026},
  month = oct,
  doi = {10.3389/fncom.2026.1949040},
  url = {https://europepmc.org/article/MED/42903277},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - An attention-enhanced hybrid CNN-BiLSTM framework for multiclass epileptic seizure recognition using EEG signals.
AU  - Bobbinpreet Kaur
AU  - Sheenam Middha
AU  - Aleem Ali
AU  - Noman Khan
AU  - Reham Alhejaili
AU  - Ahmed H Almutairi
PY  - 2026
DA  - 2026/10/06
JO  - Frontiers in computational neuroscience
DO  - 10.3389/fncom.2026.1949040
UR  - https://europepmc.org/article/MED/42903277
AB  - Introduction  Electroencephalogram (EEG) signal classification plays a pivotal role in brain-computer interfaces (BCIs) and the diagnosis of neurological disorders. However, the non-stationary, non-linear, and low signal-to-noise ratio characteristics of EEG signals make accurate feature extraction challenging. Conventional deep learning approaches often struggle to simultaneously capture localized transient patterns, deep temporal dependencies, and long-range contextual relationships within EEG signals.Methods  To address these challenges, an optimized end-to-end hybrid deep learning framework, termed CNN-BiLSTM-MHSA, is proposed for multiclass epileptic seizure recognition. The architecture sequentially integrates a multilayer one-dimensional Convolutional Neural Network (CNN) for localized feature extraction, a Bidirectional Long Short-Term Memory (BiLSTM) network for capturing forward and backward temporal dependencies, and a Multi-Head Self-Attention (MHSA) mechanism for dynamically emphasizing discriminative neurological events. Robust preprocessing includes Butterworth bandpass filtering, Z-score normalization, and data augmentation using Gaussian noise injection and amplitude scaling. The framework was evaluated on the UCI/Kaggle Epileptic Seizure Recognition dataset comprising 11,500 EEG segments distributed across five classes.Results  The proposed framework achieved an overall accuracy of 98.83%, precision of 98.95%, recall (sensitivity) of 98.84%, F1-score of 98.90%, specificity of 99.71%, balanced accuracy of 98.84%, ROC-AUC of 99.80%, and PR-AUC of 99.72%. Class-wise accuracies exceeded 99% for most categories, with one seizure class achieving perfect recognition. Comparative evaluation further demonstrated that the proposed framework outperformed several recent state-of-the-art EEG seizure classification methods.Discussion  The superior performance can be attributed to the complementary representation capabilities of the hybrid architecture. CNN layers effectively learn localized signal patterns, BiLSTM captures bidirectional temporal dependencies, and MHSA enhances the representation of long-range contextual relationships by assigning greater importance to informative temporal regions. The combination of robust preprocessing and data augmentation further contributes to improved generalization and classification reliability.
SN  - 1662-5188
ER  -