Analysis of Epileptic EEG Signals with Simple Random Sampling J48 Algorithm

Abstract

This paper describes the application of a Simple Random Sampling J48 (SRS-J48) model for classification of electroencephalogram (EEG) signals. Decision making is performed in two stages: feature extraction and classification. Eight statistical features are extracted from a two-level sample set model based on SRS technique and then classified by the J48 decision tree algorithm in Weka. The classification accuracy of the SRS-J48 is 16.35% higher than that of J48 according to the five groups of experiment with only 13% execution time on average. Besides, the proposed SRS-J48 algorithm has competitive or even better results on some of the experimental groups than Siuly’s Simple Random Sampling-Least Square-Support Vector Machine (SRS-LS-SVM).