Beta
106742

Automatic Classification of Sleep Stages Using EEG Records.

Article

Last updated: 22 Jan 2023

Subjects

-

Tags

Electronics and Communications Engineering

Abstract

Currently in the world there is an alarming number of people who suffer from sleep disorders. A number of biomedical signals, such as EEG, EMG, ECG, EOG are used in sleep labs among other for diagnosis and treatment of sleep relayed disorders. The usual method for sleep stages classification is visual inspection by a sleep specialist. This is a very time consuming and laborious exercise. Automatic sleep stages classification can facilitate this process. In this work an attempt was made to classify six sleep stages consisting of Awake, Stage 1, Stage 2, Stage3, Stage 4, and REMS. Spectral analysis, Wavelet transform and artificial neural networks were deployed for this purpose. Twenty-four recordings of a healthy six stages studied per 30s epochs. The results demonstrated that the performance for automatically discriminated for these six sleep stages from each other when using wavelet packet with Sym3 where the classification was with average 81.94%. Data fusion improves the accuracy of classification results using fusion at the feature extraction level to 87.7%.

DOI

10.21608/bfemu.2020.106742

Keywords

Artificial Neural Networks, Sleep Analysis, Electroencephalogram (EEG), Data fusion

Authors

First Name

Mohamed

Last Name

Mowafy

MiddleName

-

Affiliation

Prof. of Electronics and Communications Engineering Department, Faculty of Engineering, Mansoura University

Email

eng_elmowafy@ymail.com

City

-

Orcid

-

First Name

Marwa

Last Name

Obayya

MiddleName

-

Affiliation

Electronics and Communications Engineering Department, Faculty of Engineering, Mansoura University.

Email

marwa_obayya@yahoo.com

City

-

Orcid

-

First Name

F.

Last Name

Abou-Chadi

MiddleName

E. Z.

Affiliation

Electronics and Communications Engineering Department, Faculty of Engineering, Mansoura University

Email

f-abochadi@ieee.org

City

-

Orcid

-

First Name

Mohamed

Last Name

saad

MiddleName

-

Affiliation

Head of Dept. Neurology, Faculty of Medicine, Mansoura University

Email

-

City

-

Orcid

-

Volume

38

Article Issue

3

Related Issue

16051

Issue Date

2013-09-01

Receive Date

2013-07-09

Publish Date

2020-08-09

Page Start

1

Page End

8

Print ISSN

1110-0923

Online ISSN

2735-4202

Link

https://bfemu.journals.ekb.eg/article_106742.html

Detail API

https://bfemu.journals.ekb.eg/service?article_code=106742

Order

8

Type

Research Studies

Type Code

1,205

Publication Type

Journal

Publication Title

MEJ. Mansoura Engineering Journal

Publication Link

https://bfemu.journals.ekb.eg/

MainTitle

-

Details

Type

Article

Created At

22 Jan 2023