A novel finite spectral entropy: Gated term memory unit recursive network integrated with Ladybug Beetle Optimization...

Area of Science:

• Biomedical Engineering
• Computational Neuroscience
• Artificial Intelligence in Medicine

Background:

• Epileptic seizure detection from electroencephalography (EEG) signals is crucial for patient care.
• Current visual inspection methods are time-consuming, subjective, and inefficient for large datasets.
• Existing automated techniques often lack the required performance and scalability.

Purpose of the Study:

• To design an automated tool for accurate epileptic seizure prediction from EEG signals.
• To address the limitations of current detection methods by employing advanced computational techniques.
• To assist medical professionals with a reliable and efficient diagnostic aid.

Main Methods:

• EEG signal preprocessing including decomposition, filtering, and artifact removal using finite Haar wavelet transformation.
• Non-linear feature extraction using finite spectral entropy (FSE) for time, frequency, and time-frequency domains.
• Epileptic seizure classification employing a novel gated term memory unit recursive network (GTRN) model.
• Optimization of the classification process using the Ladybug Beetle Optimization (LBO) algorithm for logistic sigmoid function computation.

Main Results:

• The proposed FSE-GTRN-LBO mechanism demonstrated high accuracy in classifying healthy and seizure-affected EEG signals.
• The system efficiently processed EEG signals through advanced wavelet transformation and feature extraction.
• Validation on benchmark EEG datasets showed superior seizure prediction accuracy and performance compared to existing methods.

Conclusions:

• The developed automated system offers a significant advancement in epileptic seizure detection.
• The integration of FSE, GTRN, and LBO provides an efficient and accurate solution for EEG-based seizure prediction.
• This technology has the potential to enhance clinical diagnosis and patient management for epilepsy.