Analysis of EEG Signal to Classify Sleep Stages Using Machine Learning

Automated classification of sleep stages is in demand to overcome the limitations of manual sleep stage classification. Analyzing sleep stages manually using neurophysiological signals and inspecting visually is very difficult, time-consuming process. Many techniques have been proposed already in th...

Full description

Saved in:
Bibliographic Details
Published in:Sleep and vigilance 2020-12, Vol.4 (2), p.145-152
Main Authors: Santaji, Sagar, Desai, Veena
Format: Article
Language:English
Subjects:
Accuracy
Biomedical and Life Sciences
Biomedicine
Classification
Datasets
Decision trees
Digital signal processors
Electrocardiography
Electroencephalography
Embedded systems
Entropy
Eye movements
Fourier transforms
Human error
Insomnia
Machine learning
Medicine/Public Health
Methods
Neurology
Neurosciences
Original Article
Psychiatry
Random variables
Sleep apnea
Support vector machines
Wavelet transforms
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Automated classification of sleep stages is in demand to overcome the limitations of manual sleep stage classification. Analyzing sleep stages manually using neurophysiological signals and inspecting visually is very difficult, time-consuming process. Many techniques have been proposed already in the past two decades. Sleep experts, physicians do not have assurance with such techniques concerned with accuracy, specificity and sensitivity. The aim of the paper is to propose an efficient technique for sleep stage classification based on Electroencephalogram (EEG) signals analysis using machine learning algorithms by considering 10 s of epochs. EEG signals have played significant role in automatic sleep stage classification. EEG signals are filtered and decomposed into frequency sub-bands using band-pass filter. Statistical features are extracted and trained with Decision Tree, Support Vector Machine and Random Forest algorithms with different testing dataset percentage. Results show Random Forest algorithm achieves 97.8% of accuracy.
ISSN:2510-2265
2510-2265
DOI:10.1007/s41782-020-00101-9