ISSN 0869-6632 (Print)
ISSN 2542-1905 (Online)

For citation:

Emelyanova E. P., Selskii A. O. Marking stages of REM and non-REM sleep using recurrent analysis. Izvestiya VUZ. Applied Nonlinear Dynamics, 2023, vol. 31, iss. 5, pp. 643-649. DOI: 10.18500/0869-6632-003060, EDN: WGHKJW

This is an open access article distributed under the terms of Creative Commons Attribution 4.0 International License (CC-BY 4.0).
Full text PDF(Ru):
Full text PDF(En):
Article type: 
Short communication

Marking stages of REM and non-REM sleep using recurrent analysis

Emelyanova Elizaveta Petrovna, Saratov State University
Selskii Anton Olegovich, Saratov State University

The purpose of this study — to develop a simple technique for labeling sleep stages according to EEG data obtained from half-somnography recordings. To test the work of the method, it will be applied to three groups of subjects: conditionally healthy, patients with Parkinson’s disease, patients with sleep apnea.

Methods. In this work, to recognize sleep stages, we use the calculation of a recurrent indicator and its subsequent assessment. It is shown that the stages of REM (Rapid Eye Movement) and non-REM sleep demonstrate different values of the recurrent index.

Results. Depending on the range in which the recurrent indicator falls, the stages of REM and non-REM sleep were determined for the subjects, according to their nightly polysomnographic records. For three groups of subjects, the average knowledge of the accuracy of the method was calculated, which for all groups exceeded 72.5%.

Conclusion. It is shown that on the basis of recurrent analysis it is possible to create a simple and effective method for recognizing sleep stages. For patients with apnea, the average accuracy of the method is higher than for apparently healthy subjects, for whom, in turn, this value was higher than for patients with Parkinson’s disease. This can be explained by the fact that the variability in the group of statistical characteristics of sleep stages in patients with apnea is lower, and in patients with Parkinson’s disease is higher, compared with apparently healthy subjects.

The work was supported by the Russian Science Foundation, project No. 22-72-10061
  1. Ebrahimi F, Alizadeh I. Automatic sleep staging by cardiorespiratory signals: a systematic review. Sleep and Breathing. 2002;26(2):965–981. DOI: 10.1007/s11325-021-02435-8.
  2. Mikkelsen KB, Villadsen DB, Otto M, Kidmose P. Automatic sleep staging using ear-EEG. BioMedical Engineering OnLine. 2017;16(1):111. DOI: 10.1186/s12938-017-0400-5.
  3. Parro VC, Valdo L. Sleep-wake detection using recurrence quantification analysis. Chaos. 2018;28(8):085706. DOI: 10.1063/1.5024692.
  4. Acharya UR, Sree SV, Swapna G, Martis RJ, Suri JS. Automated EEG analysis of epilepsy: A review. Knowledge-Based Systems. 2013;45:147–165. DOI: 10.1016/j.knosys.2013.02.014.
  5. Acharya UR, Sree SV, Chattopadhyay S, Yu W, Ang PCA. Application of recurrence quantification analysis for the automated identification of epileptic EEG signals. International Journal of Neural Systems. 2011;21(3):199–211. DOI: 10.1142/S0129065711002808.
  6. Eckmann JP, Kamphorst SO, Ruelle D. Recurrence plots of dynamical systems. Europhysics Letters. 1987;4(9):973–977. DOI: 10.1209/0295-5075/4/9/004.
  7. Ramos AMT, Builes-Jaramillo A, Poveda G, Goswami B, Macau EEN, Kurths J, Marwan N. Recurrence measure of conditional dependence and applications. Phys. Rev. E. 2017;95(5):052206. DOI: 10.1103/PhysRevE.95.052206.
  8. Zhu L, Wang C, He Z, Zhang Y. A lightweight automatic sleep staging method for children using single-channel EEG based on edge artificial intelligence. World Wide Web. 2022;25(5):1883–1903. DOI: 10.1007/s11280-021-00983-3.
Available online: