Classification of Epileptic and Non-Epileptic Electroencephalogram (EEG) Signals Using Fractal Analysis and Support Vector Regression

G Buchanna,A Govardhan,P Premchand

doi:10.28991/esj-2022-06-01-011

Abstract

Seizures are a common symptom of this neurological condition, which is caused by the discharge of brain nerve cells at an excessively fast rate. Chaos, nonlinearity, and other nonlinearities are common features of scalp and intracranial Electroencephalogram (EEG) data recorded in clinics. EEG signals that aren't immediately evident are challenging to categories because of their complexity. The Gradient Boost Decision Tree (GBDT) classifier was used to classify the majority of the EEG signal segments automatically. According to this study, the Hurst exponent, in combination with AFA, is an efficient way to identify epileptic signals. As with any fractal analysis approach, there are problems and factors to keep in mind, such as identifying whether or not linear scaling areas are present. These signals were classified as either epileptic or non-epileptic by using a combination of GBDT and a Support Vector Regression (SVR). The combined method's identification accuracy was 98.23%. This study sheds light on the effectiveness of AFA feature extraction and GBDT classifiers in EEG classification. The findings can be utilized to develop theoretical guidance for the clinical identification and prediction of epileptic EEG signals. Doi: 10.28991/ESJ-2022-06-01-011 Full Text: PDF

Highlights

An epileptic condition is caused by seizures associated with altered brain activity, is a Central Nervous System (CNS) malfunction
Where the samples are divided into five groups Y = 1, 2, 3, 4, 5; such as a) Class 5 eyes open during recoding EEG signal (E.Y.E.O. in this research) b) Class 4 - eyelids closed during recording EEG signal (E.Y.E.C. in this research). c) Class 3 - Yes, an EEG from the healthy brain area revealed a brain tumour, labelled H.S.T.U
We evaluated eight models of different configurations to pick optimal model parameters

Summary

Introduction

An epileptic condition is caused by seizures associated with altered brain activity, is a Central Nervous System (CNS) malfunction. Symptoms of these seizures include loss of consciousness, odd behaviour, and perplexity. Because most seizures happen rapidly, many researchers have struggled to establish techniques for predicting when someone is likely to have a seizure. Classification algorithms, like the one employed in this research, can help predict whether or not a person will experience a seizure. Numerous studies have looked at brain scans from people with diseases including Parkinson's [6] and depression [7], as well as those from persons in good health [9–11] and epilepsy sufferers, which is the subject of this research [12-22]

Methods

Results

Conclusion