Recognition of wake-sleep stage 1 multichannel eeg patterns using spectral entropy features for drowsiness detection

N. Sriraam, T. K. Padma Shri, Uma Maheshwari

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Electroencephalographic (EEG) activity recorded during the entire sleep cycle reflects various complex processes associated with brain and exhibits a high degree of irregularity through various stages of sleep. The identification of transition from wakefulness to stage1 sleep is a challenging area of research for the biomedical community. In this paper, spectral entropy (SE) is used as a complexity measure to quantify irregularities in awake and stage1 sleep of 8-channel sleep EEG data from the polysomnographic recordings of ten healthy subjects. The SE measures of awake and stage1 sleep EEG data are estimated for each second and applied to a multilayer perceptron feed forward neural network (MLP-FF). The network is trained using back propagation algorithm for recognizing these two patterns. Initially, the MLP network is trained and tested for randomly chosen subject-wise combined datasets I and II and then for the combined large dataset III. In all cases, 60 % of the entire dataset is used for training while 20 % is used for testing and 20 % for validation. Results indicate that the MLP neural network learns with maximum testing accuracy of 95.9 % for dataset II. In the case of combined large dataset, the network performs with a maximum accuracy of 99.2 % with 100 hidden neurons. Results show that in channels O1, O2, F3 and F4 (A1, A2 as reference), the mean of the spectral entropy value is higher in awake state than in stage1 sleep indicating that the EEG becomes more regular and rhythmic as the subject attains stage1 sleep from wakefulness. However, in C3 and C4 the mean values of SE values are not very much discriminative of both groups. This may prove to be a very effective indicator for scoring the first two stages of sleep EEG and may be used to detect the transition from wakefulness to stage1 sleep.

Original languageEnglish
Pages (from-to)797-806
Number of pages10
JournalAustralasian Physical and Engineering Sciences in Medicine
Volume39
Issue number3
DOIs
Publication statusPublished - 01-09-2016

Fingerprint

Sleep Stages
Entropy
Sleep
Wakefulness
Neural Networks (Computer)
varespladib methyl
Backpropagation algorithms
Feedforward neural networks
Biomedical Research
Testing
Multilayer neural networks
Healthy Volunteers
Datasets
Neurons
Brain
Neural networks

All Science Journal Classification (ASJC) codes

  • Biophysics
  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Cite this

@article{a0db0dd055e249fa979a5fa415e38752,
title = "Recognition of wake-sleep stage 1 multichannel eeg patterns using spectral entropy features for drowsiness detection",
abstract = "Electroencephalographic (EEG) activity recorded during the entire sleep cycle reflects various complex processes associated with brain and exhibits a high degree of irregularity through various stages of sleep. The identification of transition from wakefulness to stage1 sleep is a challenging area of research for the biomedical community. In this paper, spectral entropy (SE) is used as a complexity measure to quantify irregularities in awake and stage1 sleep of 8-channel sleep EEG data from the polysomnographic recordings of ten healthy subjects. The SE measures of awake and stage1 sleep EEG data are estimated for each second and applied to a multilayer perceptron feed forward neural network (MLP-FF). The network is trained using back propagation algorithm for recognizing these two patterns. Initially, the MLP network is trained and tested for randomly chosen subject-wise combined datasets I and II and then for the combined large dataset III. In all cases, 60 {\%} of the entire dataset is used for training while 20 {\%} is used for testing and 20 {\%} for validation. Results indicate that the MLP neural network learns with maximum testing accuracy of 95.9 {\%} for dataset II. In the case of combined large dataset, the network performs with a maximum accuracy of 99.2 {\%} with 100 hidden neurons. Results show that in channels O1, O2, F3 and F4 (A1, A2 as reference), the mean of the spectral entropy value is higher in awake state than in stage1 sleep indicating that the EEG becomes more regular and rhythmic as the subject attains stage1 sleep from wakefulness. However, in C3 and C4 the mean values of SE values are not very much discriminative of both groups. This may prove to be a very effective indicator for scoring the first two stages of sleep EEG and may be used to detect the transition from wakefulness to stage1 sleep.",
author = "N. Sriraam and {Padma Shri}, {T. K.} and Uma Maheshwari",
year = "2016",
month = "9",
day = "1",
doi = "10.1007/s13246-016-0472-8",
language = "English",
volume = "39",
pages = "797--806",
journal = "Australasian Physical and Engineering Sciences in Medicine",
issn = "0158-9938",
publisher = "Springer Netherlands",
number = "3",

}

Recognition of wake-sleep stage 1 multichannel eeg patterns using spectral entropy features for drowsiness detection. / Sriraam, N.; Padma Shri, T. K.; Maheshwari, Uma.

In: Australasian Physical and Engineering Sciences in Medicine, Vol. 39, No. 3, 01.09.2016, p. 797-806.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Recognition of wake-sleep stage 1 multichannel eeg patterns using spectral entropy features for drowsiness detection

AU - Sriraam, N.

AU - Padma Shri, T. K.

AU - Maheshwari, Uma

PY - 2016/9/1

Y1 - 2016/9/1

N2 - Electroencephalographic (EEG) activity recorded during the entire sleep cycle reflects various complex processes associated with brain and exhibits a high degree of irregularity through various stages of sleep. The identification of transition from wakefulness to stage1 sleep is a challenging area of research for the biomedical community. In this paper, spectral entropy (SE) is used as a complexity measure to quantify irregularities in awake and stage1 sleep of 8-channel sleep EEG data from the polysomnographic recordings of ten healthy subjects. The SE measures of awake and stage1 sleep EEG data are estimated for each second and applied to a multilayer perceptron feed forward neural network (MLP-FF). The network is trained using back propagation algorithm for recognizing these two patterns. Initially, the MLP network is trained and tested for randomly chosen subject-wise combined datasets I and II and then for the combined large dataset III. In all cases, 60 % of the entire dataset is used for training while 20 % is used for testing and 20 % for validation. Results indicate that the MLP neural network learns with maximum testing accuracy of 95.9 % for dataset II. In the case of combined large dataset, the network performs with a maximum accuracy of 99.2 % with 100 hidden neurons. Results show that in channels O1, O2, F3 and F4 (A1, A2 as reference), the mean of the spectral entropy value is higher in awake state than in stage1 sleep indicating that the EEG becomes more regular and rhythmic as the subject attains stage1 sleep from wakefulness. However, in C3 and C4 the mean values of SE values are not very much discriminative of both groups. This may prove to be a very effective indicator for scoring the first two stages of sleep EEG and may be used to detect the transition from wakefulness to stage1 sleep.

AB - Electroencephalographic (EEG) activity recorded during the entire sleep cycle reflects various complex processes associated with brain and exhibits a high degree of irregularity through various stages of sleep. The identification of transition from wakefulness to stage1 sleep is a challenging area of research for the biomedical community. In this paper, spectral entropy (SE) is used as a complexity measure to quantify irregularities in awake and stage1 sleep of 8-channel sleep EEG data from the polysomnographic recordings of ten healthy subjects. The SE measures of awake and stage1 sleep EEG data are estimated for each second and applied to a multilayer perceptron feed forward neural network (MLP-FF). The network is trained using back propagation algorithm for recognizing these two patterns. Initially, the MLP network is trained and tested for randomly chosen subject-wise combined datasets I and II and then for the combined large dataset III. In all cases, 60 % of the entire dataset is used for training while 20 % is used for testing and 20 % for validation. Results indicate that the MLP neural network learns with maximum testing accuracy of 95.9 % for dataset II. In the case of combined large dataset, the network performs with a maximum accuracy of 99.2 % with 100 hidden neurons. Results show that in channels O1, O2, F3 and F4 (A1, A2 as reference), the mean of the spectral entropy value is higher in awake state than in stage1 sleep indicating that the EEG becomes more regular and rhythmic as the subject attains stage1 sleep from wakefulness. However, in C3 and C4 the mean values of SE values are not very much discriminative of both groups. This may prove to be a very effective indicator for scoring the first two stages of sleep EEG and may be used to detect the transition from wakefulness to stage1 sleep.

UR - http://www.scopus.com/inward/record.url?scp=84983490133&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84983490133&partnerID=8YFLogxK

U2 - 10.1007/s13246-016-0472-8

DO - 10.1007/s13246-016-0472-8

M3 - Article

C2 - 27550443

AN - SCOPUS:84983490133

VL - 39

SP - 797

EP - 806

JO - Australasian Physical and Engineering Sciences in Medicine

JF - Australasian Physical and Engineering Sciences in Medicine

SN - 0158-9938

IS - 3

ER -