A Framework on Performance Analysis of Mathematical Model-Based Classifiers in Detection of Epileptic Seizure from EEG Signals with Efficient Feature Selection
Table 1
Detailed description of the implementation environment of the study.
Dataset
Methodology
Classifiers
Software
Feature extraction
Feature selection
Bonn university EEG datasets (A–E). Each set input [4096 samples 100 epochs]
Wavelet level 4 decomposition (Haar, db4, and Sym8) [256 100]
PSO [256 10]
LR, NLR, GMM, K-NN, and SVM (linear, polynomial, and RBF)