Scholarlink

<p>Epileptic seizure prediction remains a major challenge in neuroscience, with significant implications for patient safety and quality of life. This study introduces a novel hybrid deep learning architecture that combines a three-dimensional Convolutional Neural Network (3D-CNN) with a Transformer encoder to predict and classify epileptic seizures from electroencephalogram (EEG) signals transformed via Short-Time Fourier Transform (STFT). The 3D-CNN component efficiently extracts local spatio-spectro-temporal features from multichannel EEG data, while the Transformer captures long-range temporal dependencies essential for modeling preictal brain dynamics. The proposed model was trained and evaluated on the CHB-MIT scalp EEG dataset and compared to a standalone Transformer-based approach. Experimental results demonstrate that the hybrid 3D-CNN–Transformer significantly outperforms the baseline, achieving an accuracy of 98.4%, a sensitivity of 98.2%, and an F1-score of 97%. Moreover, the model achieved a perfect seizure detection rate (100%) with a low false prediction rate (0.03 FPR/h) and an average detection delay of 2172.95 s. These findings highlight the complementary strengths of convolutional and attention-based mechanisms and confirm the effectiveness of their integration for robust, early, and accurate epileptic seizure forecasting, paving the way toward real-time and personalized clinical applications.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

EEG-Based Epileptic Seizure Prediction and Classification Using a Hybrid Deep Learning Model Combining 3D-CNN and Transformer Networks

  • 期刊论文

  • 发表日期：

    2026年6月2日

查看全文
  • Hosni Jamaoui,
  • Ibtihel Nouira,
  • Besma Ben Ismail,
  • Mohamed Hédi Bedoui

摘要

Epileptic seizure prediction remains a major challenge in neuroscience, with significant implications for patient safety and quality of life. This study introduces a novel hybrid deep learning architecture that combines a three-dimensional Convolutional Neural Network (3D-CNN) with a Transformer encoder to predict and classify epileptic seizures from electroencephalogram (EEG) signals transformed via Short-Time Fourier Transform (STFT). The 3D-CNN component efficiently extracts local spatio-spectro-temporal features from multichannel EEG data, while the Transformer captures long-range temporal dependencies essential for modeling preictal brain dynamics. The proposed model was trained and evaluated on the CHB-MIT scalp EEG dataset and compared to a standalone Transformer-based approach. Experimental results demonstrate that the hybrid 3D-CNN–Transformer significantly outperforms the baseline, achieving an accuracy of 98.4%, a sensitivity of 98.2%, and an F1-score of 97%. Moreover, the model achieved a perfect seizure detection rate (100%) with a low false prediction rate (0.03 FPR/h) and an average detection delay of 2172.95 s. These findings highlight the complementary strengths of convolutional and attention-based mechanisms and confirm the effectiveness of their integration for robust, early, and accurate epileptic seizure forecasting, paving the way toward real-time and personalized clinical applications.