Enhanced epileptic seizure detection using CNNs with convolutional block attention and short-term memory networks

Area of Science:

• Neurology
• Artificial Intelligence
• Biomedical Engineering

Background:

• Epilepsy monitoring requires accurate electroencephalography (EEG) signal analysis.
• Early detection and intervention of epileptic seizures are crucial for patient well-being.
• Existing methods for seizure detection have limitations in accuracy and efficiency.

Purpose of the Study:

• To develop a novel deep learning-based method for accurate epileptic seizure detection using EEG signals.
• To enhance the quality of life for epilepsy patients through improved seizure detection capabilities.

Main Methods:

• A hybrid deep learning model combining Convolutional Neural Networks (CNN) and Long-Short-Term Memory Networks (LSTM) was developed.
• The Convolutional Block Attention Module (CBAM) was integrated to enable focus on critical EEG signal features.
• The proposed CNN_CBAM_LSTM model was trained and validated on the Bonn University dataset.

Main Results:

• The CNN_CBAM_LSTM model achieved a high accuracy of 98.80% in detecting epileptic seizures from EEG data.
• The model demonstrated superior performance compared to existing state-of-the-art seizure detection methods.
• Ablation studies and parameter optimization confirmed the model's effectiveness.

Conclusions:

• The developed CNN_CBAM_LSTM model offers a highly accurate and effective solution for epileptic seizure detection.
• This deep learning approach has the potential to significantly improve the management and quality of life for epilepsy patients.
• Further research can explore the clinical application of this model for real-time seizure monitoring and intervention.