Epileptic Seizures Detection Using DCT-II and KNN Classifier in Long-Term EEG Signals

Mahmood A Jumaah,Ammar Ibrahim Shihab,Akeel Abdulkareem Farhan

doi:10.24996/ijs.2020.61.10.26

Mahmood A Jumaah, Ammar Ibrahim Shihab + Show 1 more

Open Access

https://doi.org/10.24996/ijs.2020.61.10.26

Copy DOI

Abstract

Epilepsy is one of the most common diseases of the nervous system around the world, affecting all age groups and causing seizures leading to loss of control for a period of time. This study presents a seizure detection algorithm that uses Discrete Cosine Transformation (DCT) type II to transform the signal into frequency-domain and extracts energy features from 16 sub-bands. Also, an automatic channel selection method is proposed to select the best subset among 23 channels based on the maximum variance. Data are segmented into frames of one Second length without overlapping between successive frames. K-Nearest Neighbour (KNN) model is used to detect those frames either to ictal (seizure) or interictal (non-seizure) based on Euclidean distance. The experimental results are tested on 21 patients included in the CHB-MIT dataset. The average F1-score was found to be 93.12, whereas the False-Positive Rate (FPR) average was determined to be 0.07.

Highlights

Epilepsy is one of the widespread disorders and non-communicable disease that affects the human's nerve system [1]
Patients of epilepsy cannot be aware of the seizure due to differentiation in the nature of human beings, which may increase the physical injury
People with epilepsy suffer from social stigma and vocational obstacles

Summary

Introduction

Epilepsy is one of the widespread disorders and non-communicable disease that affects the human's nerve system [1]. Epileptic seizures cause abnormal behaviours in the electricity of the brain, which produce symptoms such as losing consciousness, tension or convulsion of the whole-body. Patients of epilepsy cannot be aware of the seizure due to differentiation in the nature of human beings, which may increase the physical injury. People with epilepsy suffer from social stigma and vocational obstacles. Another load for patients is the condition of continuous seizure activity without a recovery of consciousness between seizures, which is a life-threatening emergency condition [2]. The ability to detect (localize) epileptic seizures would have a deep impact of saving the lives of epilepsy patients [3]

Objectives

Methods

Results

Conclusion