Journal Home > Volume 6 , Issue 4
Brain Science Advances 2020, 6(4): 355-363 https://doi.org/10.26599/BSA.2020.9050016
Research Article | Open Access | Issue | Published: 28 February 2021

A multiplex visibility graph motif-based convolutional neural network for characterizing sleep stages using EEG signals

Show Author's Information Qing Cai,  Jianpeng An,  Zhongke Gao( )
School of Electrical and Information Engineering, Tianjin University, Tianjin 300072, China
Keywords:
sleep-stage detection, multiplex visibility graph (MVG), MVG motif, complex network, electroencephalogram (EEG), convolutional neural network (CNN)
Cite this article:
Cai Q, An J, Gao Z. A multiplex visibility graph motif-based convolutional neural network for characterizing sleep stages using EEG signals. Brain Science Advances, 2020, 6(4): 355-363. https://doi.org/10.26599/BSA.2020.9050016
Download citation
EndNote(RIS)
BibTeX

896

Views

72

Downloads

Citations

7

Crossref

N/A

WoS

N/A

Scopus

N/A

CSCD

Abstract Full text About this article

Sleep is an essential integrant in everyone’s daily life; therefore, it is an important but challenging problem to characterize sleep stages from electroencephalogram (EEG) signals. The network motif has been developed as a useful tool to investigate complex networks. In this study, we developed a multiplex visibility graph motif-based convolutional neural network (CNN) for characterizing sleep stages using EEG signals and then introduced the multiplex motif entropy as the quantitative index to distinguish the six sleep stages. The independent samples t-test shows that the multiplex motif entropy values have significant differences among the six sleep stages. Furthermore, we developed a CNN model and employed the multiplex motif sequence as the input of the model to classify the six sleep stages. Notably, the classification accuracy of the six-state stage detection was 85.27%. Results demonstrated the effectiveness of the multiplex motif in characterizing the dynamic features underlying different sleep stages, whereby they further provide an essential strategy for future sleep-stage detection research.


menu
Abstract
Full text
Outline
About this article

A multiplex visibility graph motif-based convolutional neural network for characterizing sleep stages using EEG signals

Show Author's information Qing Cai, Jianpeng An, Zhongke Gao( )
School of Electrical and Information Engineering, Tianjin University, Tianjin 300072, China

Abstract

Sleep is an essential integrant in everyone’s daily life; therefore, it is an important but challenging problem to characterize sleep stages from electroencephalogram (EEG) signals. The network motif has been developed as a useful tool to investigate complex networks. In this study, we developed a multiplex visibility graph motif-based convolutional neural network (CNN) for characterizing sleep stages using EEG signals and then introduced the multiplex motif entropy as the quantitative index to distinguish the six sleep stages. The independent samples t-test shows that the multiplex motif entropy values have significant differences among the six sleep stages. Furthermore, we developed a CNN model and employed the multiplex motif sequence as the input of the model to classify the six sleep stages. Notably, the classification accuracy of the six-state stage detection was 85.27%. Results demonstrated the effectiveness of the multiplex motif in characterizing the dynamic features underlying different sleep stages, whereby they further provide an essential strategy for future sleep-stage detection research.

Keywords: sleep-stage detection, multiplex visibility graph (MVG), MVG motif, complex network, electroencephalogram (EEG), convolutional neural network (CNN)

References(31)

[1]
ZK Gao, M Small, J Kurths. Complex network analysis of time series. EPL. 2016, 116(5): 50001.
Google Scholar
[2]
WX Wang, YC Lai, C Grebogi. Data based identification and prediction of nonlinear and complex dynamical systems. Phys Rep. 2016, 644: 1-76.
Google Scholar
[3]
L Lacasa, B Luque, F Ballesteros, et al. From time series to complex networks: the visibility graph. Proc Natl Acad Sci USA. 2008, 105(13): 4972-4975.
Google Scholar
[4]
ZK Gao, Q Cai, YX Yang, et al. Visibility graph from adaptive optimal kernel time-frequency representation for classification of epileptiform EEG. Int J Neural Syst. 2017, 27(4): 1750005.
Google Scholar
[5]
ZG Shao. Network analysis of human heartbeat dynamics. Appl Phys Lett. 2010, 96(7): 073703.
Google Scholar
[6]
HZ An, XY Gao, W Fang, et al. The role of fluctuating modes of autocorrelation in crude oil prices. Phys A: Stat Mech Appl. 2014, 393: 382-390.
Google Scholar
[7]
R Milo, S Shen-Orr, S Itzkovitz, et al. Network motifs: simple building blocks of complex networks. Science. 2002, 298(5594): 824-827.
Google Scholar
[8]
J Iacovacci, L Lacasa. Sequential motif profile of natural visibility graphs. Phys Rev E. 2016, 94(5-1): 052309.
Google Scholar
[9]
GI Choudhary, W Aziz, IR Khan, et al. Analysing the dynamics of interbeat interval time series using grouped horizontal visibility graph. IEEE Access. 2019, 7: 9926-9934.
Google Scholar
[10]
WJ Xie, RQ Han, WX Zhou. Tetradic motif profiles of horizontal visibility graphs. Commun Nonlinear Sci Numer Simul. 2019, 72: 544-551.
Google Scholar
[11]
WK Ren, ND Jin. Sequential limited penetrable visibility-graph motifs. Nonlinear Dyn. 2020, 99(3): 2399-2408.
Google Scholar
[12]
Q Cai, ZK Gao, YX Yang, et al. Multiplex limited penetrable horizontal visibility graph from EEG signals for driver fatigue detection. Int J Neural Syst. 2019, 29(5): 1850057.
Google Scholar
[13]
S Sannino, S Stramaglia, L Lacasa, et al. Visibility graphs for fMRI data: multiplex temporal graphs and their modulations across resting state networks. Netw Neurosci. 2017, 1(3): 208-221.
Google Scholar
[14]
L Lacasa, V Nicosia, V Latora. Network structure of multivariate time series. Sci Rep. 2015, 5: 15508.
Google Scholar
[15]
M Adnane, ZW Jiang, ZH Yan. Sleep-wake stages classification and sleep efficiency estimation using single-lead electrocardiogram. Expert Syst Appl. 2012, 39(1): 1401-1413.
Google Scholar
[16]
ZM Zhang, SS Wei, GH Zhu, et al. Efficient sleep classification based on entropy features and a support vector machine classifier. Physiol Meas. 2018, 39(11): 115005.
Google Scholar
[17]
R Boostani, F Karimzadeh, M Nami. A comparative review on sleep stage classification methods in patients and healthy individuals. Comput Methods Programs Biomed. 2017, 140: 77-91.
Google Scholar
[18]
UR Acharya, S Bhat, O Faust, et al. Nonlinear dynamics measures for automated EEG-based sleep stage detection. Eur Neurol. 2015, 74(5/6): 268-287.
Google Scholar
[19]
M Diykh, Y Li, P Wen. EEG sleep stages classification based on time domain features and structural graph similarity. IEEE T Neur Sys Reh. 2016, 24(11): 1159-1168.
Google Scholar
[20]
GH Zhu, Y Li, PP Wen. Analysis and classification of sleep stages based on difference visibility graphs from a single-channel EEG signal. IEEE J Biomed Health Inform. 2014, 18(6): 1813-1821.
Google Scholar
[21]
SF Liang, CN Kuo, YH Hu, et al. Automatic stage scoring of single-channel sleep EEG by using multiscale entropy and autoregressive models. IEEE Trans Instrum Meas. 2012, 61(6): 1649-1657.
Google Scholar
[22]
ZK Gao, XM Wang, YX Yang, et al. EEG-based spatio-temporal convolutional neural network for driver fatigue evaluation. IEEE Trans Neural Netw Learn Syst. 2019, 30(9): 2755-2763.
Google Scholar
[23]
SM Mathews, C Kambhamettu, KE Barner. A novel application of deep learning for single-lead ECG classification. Comput Biol Med. 2018, 99: 53-62.
Google Scholar
[24]
O Faust, Y Hagiwara, TJ Hong, et al. Deep learning for healthcare applications based on physiological signals: a review. Comput Methods Programs Biomed. 2018, 161: 1-13.
Google Scholar
[25]
A Sors, S Bonnet, S Mirek, et al. A convolutional neural network for sleep stage scoring from raw single-channel EEG. Biomed Signal Process Control. 2018, 42: 107-114.
Google Scholar
[26]
ZH Cui, XW Zheng, XX Shao, et al. Automatic sleep stage classification based on convolutional neural network and fine-grained segments. Complexity. 2018: 1-13.
Google Scholar
[27]
AH Ansari, O De Wel, M Lavanga, et al. Quiet sleep detection in preterm infants using deep convolutional neural networks. J Neural Eng. 2018, 15(6): 066006.
Google Scholar
[28]
N Michielli, UR Acharya, F Molinari. Cascaded LSTM recurrent neural network for automated sleep stage classification using single-channel EEG signals. Comput Biol Med. 2019, 106: 71-81.
Google Scholar
[29]
B Kemp, AH Zwinderman, B Tuk, et al. Analysis of a sleep-dependent neuronal feedback loop: the slow-wave microcontinuity of the EEG. IEEE Trans Biomed Eng. 2000, 47(9): 1185-1194.
Google Scholar
[30]
M Ronzhina, O Janoušek, J Kolářová, et al. Sleep scoring using artificial neural networks. Sleep Med Rev. 2012, 16(3): 251-263.
Google Scholar
[31]
R Sharma, RB Pachori, A Upadhyay. Automatic sleep stages classification based on iterative filtering of electroencephalogram signals. Neural Comput Appl. 2017, 28(10): 2959-2978.
Google Scholar
Publication history
Copyright
Rights and permissions

Publication history

Received: 10 May 2020
Revised: 18 June 2020
Accepted: 19 June 2020
Published: 28 February 2021
Issue date: December 2020

Copyright

© The authors 2020

Rights and permissions

This article is published with open access at journals.sagepub.com/home/BSA

Creative Commons Non Commercial CC BY-NC: This article is distributed under the terms of the Creative Commons Attribution-NonCommercial 4.0 License (http://www.creativecommons.org/licenses/by-nc/4.0/) which permits non-commercial use, reproduction and distribution of the work without further permission provided the original work is attributed as specified on the SAGE and Open Access pages (https://us.sagepub.com/en-us/nam/open-access-at-sage).

Return