Enhanced Method for Epileptic Seizure Diagnosis Using Multi DWTS and ACO Integrated with Machine Learning Classifiers

Epileptic seizure detection plays a vital role in ensuring timely medical intervention and improving patient care.Traditional diagnostic methods heavily rely on the manual analysis of EEG signals, which can be labor-intensive, subjective, and prone to errors.To address these limitations, this research presents an advanced seizure detection system that integrates Multi Discrete Wavelet Transforms (DWTs) using db6 and sym10 for effective feature extraction.The extracted features are then optimized using the Whale Optimization Algorithm (WOA) to eliminate redundant and irrelevant data, enhancing the overall efficiency of the system.For accurate classification, Support Vector Machines (SVM) and Bagging Classifiers are employed, ensuring robust seizure detection with improved accuracy.The integration of these machine learning techniques significantly reduces false positives, leading to a more reliable diagnostic system.Additionally, the proposed system is designed to support realtime monitoring, allowing healthcare professionals to receive instant alerts during seizure occurrences.Extensive experiments validate the effectiveness of this approach, demonstrating superior detection performance compared to traditional methods.The proposed framework provides a computationally efficient and highly accurate solution, contributing to the advancement of automated epileptic seizure diagnosis and paving the way for future innovations in neurological disorder detection.