Hybrid Grasshopper Optimization Algorithm and Support Vector Machines for Automatic Seizure Detection in EEG Signals

Abstract

In this paper, a hybrid classification model using Grasshopper Optimization Algorithm (GOA) and support vector machines (SVMs) for automatic seizure detection in EEG is proposed called GOA-SVM approach. Various parameters were extracted and employed as the features to train the SVM with radial basis function (RBF) kernel function (SVM-RBF) classifiers. GOA was used for selecting the effective feature subset and the optimal settings of SVMs parameters in order to obtain a successful EEG classification. The experimental results confirmed that the proposed GOA-SVM approach, able to detect epileptic and could thus further enhance the diagnosis of epilepsy with accuracy 100% for normal subject data versus epileptic data. Furthermore, the proposed approach has been compared with Particle Swarm Optimization (PSO) with support vector machines (PSO-SVMs) and SVM using RBF kernel function. The computational results reveal that GOA-SVM approach achieved better classification accuracy outperforms both PSO-SVM and typical SVMs.