Sleep Stages Classification Using Spectral Based Statistical Moments as Features


  • Eduardo Tiago Braun Universidade Federal de Santa Maria
  • Alice de Jesus Kozakevicius Universidade Federal de Santa Maria
  • Thiago Lopes Trugillo da Silveira Universidade Federal do Rio Grande do Sul
  • Cesar Ramos Rodrigues Universidade Federal de Santa Maria
  • Giovani Baratto Universidade Federal de Santa Maria



sleep stage classification, frequency domain, single EEG channel, random forest


In the pursuit of highly effective and efficient portable sleep classification systems, researchers have been testing a massive number of combinations of EEG features and classifiers.  State of art sleep classification ensembles achieve accuracy in the order of 90%.  However, there is presently no consensus regarding the best setof features for sleep staging with single channel EEG, leading researchers to modify feature selection according to the number of classification stages. This paper introduces a reduced set of frequency-domain features capable of yielding high classification accuracy (90.9%, 91.8%, 92.4%, 94.3% and 97.1%) for all 6- to 2-state sleep stages.  The proposed system uses fast Fourier transform (FFT) to convert data from Pz-Oz EEG channel into the frequency domain. Afterwards, eight statistical features are extracted from specific frequency ranges and fed into a random forest classifier.


Download data is not yet available.


COLE, R. J. et al. Automatic sleep/wake identification from wrist activity. Sleep, v. 15, n. 5, p. 461 – 469, 1992.

IBER, C. et al. The AASM Manual for the Scoring of Sleep and Associated Events: Rules, Terminology and Technical Specifications. 1. ed. Darien, USA, 2007.

JAP, B. T. et al. Using EEG spectral components to assess algorithms for detecting fatigue. Expert Systems with Applications, v. 36, n. 2, p. 2352–2359, 2009.

BERTHOMIER, C. et al. Automatic analysis of single-channel sleep EEG: Validation in healthy individuals. Sleep, v. 30, n. 11, p. 1587–1595, 2007.

SILVEIRA, T. da; KOZAKEVICIUS, A. de J.; RODRIGUES, C. R. Drowsiness detection for single channel EEG by DWT best m-term approximation. Research on Biomedical Engineering, v. 31, n. 2, p. 107 – 115, 2015.

SILVEIRA, T. L. T. da; KOZAKEVICIUS, A. J.; RODRIGUES, C. R. Automated drowsiness detection through wavelet packet analysis of a single EEG channel. Expert Systems With Applications, v. 55, n. 3, p. 559–565, 2016.

ZHU, G.; LI, Y.; WEN, P. Analysis and classification of sleep stages based on difference visibility graphs from a single-channel EEG signal. IEEE Journal of Biomedical and Health Informatics, v. 18, n. 6, p. 1813–1821, 2014.

RECHTSCHAFFEN, A.; KALES, A. A manual of standardized terminology, techniques and scoring system for sleep stages of human subjects. Electroencephalography and Clinical Neurophysiology, v. 26, n. 6, p. 644, 1969.

MOSER, D. et al. Sleep classification according to AASM and rechtschaffen & kales: effects on sleep scoring parameters. SLEEP, v. 32, n. 2, p. 139–149, 2009.

EBRAHIMI, F. et al. Automated sleep stage classification based on EEG signals by using neural networks and wavelet packet. In: IEEE. 30th Annual International IEEE EMBS Conference. Vancouver, Canada: IEEE, 2008. v. 1, n. 1.

RONZHINA, M. et al. Sleep scoring using artificial neural networks. Sleep Medicine Reviews, v. 16, n. 3, p. 251–263, 2012.

SILVEIRA, T. L. T. da; KOZAKEVICIUS, A. J.; RODRIGUES, C. R. Single-channel EEG sleep stage classification based on a streamlined set of statistical features in wavelet domain. Medical & Biological Engineering & Computing, v. 55, n. 2, p. 343––352, 2017.

FRAIWAN, L. et al. Automated sleep stage identification system based on time-frequency analysis of a single EEG channel and random forest classifier. Computer Methods and Programs in Biomedicine, v. 108, n. 1, p. 10–19, 2012.

LIANG, S. F. et al. Automatic stage scoring of single-channel sleep EEG by using multiscale entropy and autoregressive models. IEEE Transactions on Instrumentation and Measurement, v. 61, n. 6, p. 1649–1657, 2012.

HSU, Y.-L. et al. Automatic sleep stage recurrent neural classifier using energy features of EEG signals. Neurocomputing, v. 104, n. 1, p. 105–114, 2013.

PAPADELIS, C. et al. Indicators of sleepiness in an ambulatory EEG study of night driving. In: NEUMAN, M. (Ed.). 28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. New York, USA: IEEE, 2006. v. 25, n. 3.

BRIGGS, W. L.; HENSON, V. E. The DFT: An Owners’ Manual for the Discrete Fourier Transform. 1.

ed. Philadelphia, USA: Society for Industrial and Applied Mathematics, 1995. v. 1. (Miscellaneous Bks, v. 1).

SUBASI, A. Automatic recognition of alertness level from EEG by using neural network and wavelet coefficients. Experts Systems with Applications, v. 28, n. 4, p. 701–711, 2005.

KRYGER, M. H. Atlas of Clinical Sleep Medicine: Expert consult. 2. ed. Philadelphia, USA: Saunders, 2009.

CORSI-CABRERA, M. et al. Power and coherent oscillations distinguish REM sleep, stage 1 and wakefulness. International Journal of Psychophysiology, v. 60, n. 1, p. 59–66, 2006.

JIA, X.; KOHN, A. Gamma rhythms in the brain. PLoS Biology, v. 9, n. 4, p. 1–4, 2011.

BOOSTANI, R.; KARIMZADEH, F.; NAMI, M. A comparative review on sleep stage classification methods in patients and healthy individuals. Computer Methods and Programs in Biomedicine, v. 140, n. Supplement C, p. 77 – 91, 2017.

KRAKOVSKA,A.;MEZEIOVA,K.Automaticsleep scoring: A search for an optimal combination of measures. Artificial Intelligence in Medicine, v. 53, n. 1, p. 25–33, 2011.

CHARBONNIER, S. et al. Self-evaluated automatic classifier as a decision-support tool for sleep/wake staging. Computers in Biology and Medicine, v. 41, n. 6, p. 380 – 389, 2011.

S ̧ EN, B. et al. A comparative study on classification of sleep stage based on EEG signals using feature selection and classification algorithms. J Med Syst, v. 38, n. 3, p. 1–21, 2014.

HASSAN, A. R.; BHUIYAN, M. I. H. Automated identification of sleep states from eeg signals by means of ensemble empirical mode decomposition and random under sampling boosting. Computer Methods and Programs in Biomedicine, v. 140, n. Supplement C, p. 201 – 210, 2017.

ASADZADEH, M.; HASHEMI, E.; KOZAKEVICIUS, A. Efficiency of combined daubechies and statistical parameters applied in mammography. Applied and Computational Mathematics: An International Journal, v. 12, n. 3, p. 289–305, 2013.

GOLDBERGER, A. L. et al. Physiobank, physiotoolkit, and physionet: Components of a new research resource for complex physiologic signals. Circulation, v. 101, n. 23, p. 215–220, 2000.

PHYSIONET. The Sleep-EDF-X Database. 2013. ⟨⟩. Online; Accessed on May 12th 2015.

KEMP, B. et al. Analysis of a sleep-dependent neuronal feedback loop: the slow-wave microcontinuity of the EEGkemp2000a. IEEE Transactions on Biomedical Engineering, v. 47, n. 9, p. 1185–1194, 2000.




How to Cite

Braun, E. T., Kozakevicius, A. de J., da Silveira, T. L. T., Rodrigues, C. R., & Baratto, G. (2018). Sleep Stages Classification Using Spectral Based Statistical Moments as Features. Revista De Informática Teórica E Aplicada, 25(1), 11–22.



Regular Papers