Robust Optimization of electroencephalograph (EEG) Signals for Epilepsy Seizure Prediction by utilizing VSPO Genetic Algorithms with SVM and Machine Learning Methods

Objectives: To optimize the EEG signals in order to predict epileptic seizures at early stage and improve accuracy level by employing genetic algorithm machine learning methods. Methods: Virus Swarm Particle Optimization Technique (VSPO) based Genetic is utilized for purpose of feature selection Machine Learning SVM technique classification determine seizure or non-seizure. The Discrete Wavelet Transform (DWT) factor extraction assess recurrence range associated with seizures, partition them into separate spaces using DWT symbols, consider variations between normal functionality. VPSO-GA extracts features from Andrzejak R G dataset then selects relevant function perform prediction ES level. demonstrate effectiveness proposed algorithm, MATLAB used implementation. performance results are compared existing baseline versions FCM-MPSO, EDMLC K-MODE. Findings: optimized done 98.13% level, 98.03% sensitivity, 98.01% specificity, 98.90% Precision, 97.96% Recall, 191 True Positive, 104 Negative 98.46% F-Score an manner which high versions. Novelty: According findings comprehensive study, VPSO-SVM outperforms K-MODE terms optimizing a robust manner. Keywords: Epilepsy Seizure; Algorithm; Classification; SVM;