Abstract
Epilepsy is a serious neurological disorder that can significantly impact an individual's quality of life. This study proposes a novel method for the detection and mitigation of epileptic seizures through the integration of artificial intelligence (AI) and a brain-computer interface (BCI) system. Statistical features were extracted from intracranial electroencephalography (IEEG) signals using a multi-resolution decomposition technique and used to train five classification algorithms: support vector machines (SVM), k-nearest neighbors (KNN), Naïve Bayes (NB), artificial neural networks (ANN), and long short-term memory (LSTM). The model demonstrated strong performance, achieving classification accuracies of 98.28% (SVM), 93.88% (KNN), 95.73% (NB), 95.73% (ANN), and 95.00% (LSTM). Upon seizure detection, the proposed BCI system initiates an alert and offers the activation of an automated drug delivery mechanism to administer timely medication. This real-time system offers valuable support for clinicians in managing epilepsy and reducing the impact of seizures. The findings highlight the potential of AI-driven BCI technologies to enhance the monitoring and treatment of epileptic conditions.
Recommended Citation
Salaheldin, Ahmed, M. Dr.; Abdel Wahed, Manal Prof.; and Saleh, Neven
(2025)
"A Hybrid AI-Based Framework for Real-Time Epileptic Seizure Detection in Intracranial EEG Signals Using Brain-Computer Interfaces,"
Future Engineering Journal: Vol. 5:
Iss.
2, Article 4.
Available at:
https://digitalcommons.aaru.edu.jo/fej/vol5/iss2/4