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.
Similar content being viewed by others
References
Redline HL, Kirchner SF, Quan SE, Gottlieb DJ, Kapur V, Newman A (2004) The effects of age, sex, ethnicity, and sleep-disordered breathing on sleep architecture. JAMA Intern Med 164:406–418
Rossow AB, Salles EOT, Coco KF (2011) Automatic sleep staging using a single-channel eeg modeling by kalman filter and HMM. In: International conference IEEE Engineering in Medicine and Biology Society, vol 1 pp 1-6
Rechtschaffen A, Kales A (1968) A manual of standardized terminology techniques and scoring sleep stage of human subjects. Public Health Service US Govt Printing Office, Washington DC
Le QK, Truong QDK, Van Toi V (2011) A tool for analysis and classification of sleep stages. In: International conference on advanced technologies for communications, pp 307–310
See AR, Liang CK (2011) A study on sleep EEG using sample entropy and power spectrum analysis. In: International conference on defence science research, pp 1–4
Khalighi S, Sousa T, Oliveira D, Pires G, Nunes U (2011). Efficient feature selection for sleep staging based on maximal overlap discrete wavelet transform and SVM. 33rd Annual international conference IEEE Engineering Medicine Biology Society, pp 3306–3309
Liang SF, Kuo CE, Hu YH, Cheng YS (2011) A rule-based automatic sleep staging method. In: International conference of the IEEE Engineering in Medicine & Biology Society, pp 6067–6070
Herrera LJ, Mora AM, Fernandes C, Migotina, D (2011) Symbolic representation of the EEG for sleep stage classification. In: International conference on intelligent system design and applications, pp 253–258
Sloboda J, Das M (2011). A simple sleep stage identification technique for incorporation in inexpensive electronic sleep screening devices. In: Proceedings IEEE national aerospace and electronics conference, pp 21–24
Langkvist M, Karlsson L, Loutfi A (2012) Sleep stage classification using unsupervised feature learning. Adv Artif Neural Syst. doi:10.1155/2012/107046
Phan H, Do Q, Do TL, Vu DL (2013). Metric learning for automatic sleep stage classification. In: International conference IEEE Engineering in Medicine Biology Society, pp 3–7
Christopher Letellier, Claudia Lainscek (2012) Method and system for automatic scoring of sleep stages, the Patent Cooperation Treaty (PCT). World Intellectual Property Organization International Bureau, Geneva
Modarres-Zadeh M (2005) A neuro-behavioral test and algorithms for quantification of sleepiness and characterization of wake-sleep transitions. In: Proceedings of IEEE EMBS 27th annual conference, Shanghai, pp 5746–5749
De Gennaro L, Ferrara M, Ferlazzo F, Bertini M (2000) Slow eye movements and EEG power spectra during wake-sleep transition. J Clin Neurophysiol 111:2107–2115
Purnima BR, Sriraam N, Krishnaswamy U, Radhika K (2014) A measure to detect sleep onset using statistical analysis of spike rhythmicity. Int J Biomed Clin Eng 3:27–41
Sriraam N, Purnima BR (2014) Sleep wake transition using relative spike amplitude. In: International conference on medical imaging, health & emerging communication systems, pp 437–441
Sriraam N, Purnima BR, Uma K, PadmaShri TK (2014) Hurst exponents Based detection of wake-sleep—A pilot study IEEE. In: Proceedings international conference on circuits, communication, control & computing, pp 1–4
Svanborg E, Guilleminault C (1996) EEG frequency changes during sleep apneas. J Sleep 19(3):248–254
Dingli K, Assimakopoulos T, Fietze I, Witt C, Wraith PK, Douglas NJ (2002) Electroencephalographic spectral analysis: detection of cortical activity changes in sleep apnea patients. J Eur Respir 20:1246–1253
Morisson F, Lavigne G, Petit D, Nielson T, Malo J, Montplaisir J (1998) Spectral analysis of wakefulness and REM sleep EEG in patients with sleep apnea syndrome. J Eur Respir 11:1135–1140
Fell J, Roschke J, Mann K, Schaffner C (1996) Discrimination of sleep stages: a comparison between spectral and nonlinear EEG measures. J Clin Neurophysiol 98:401–410
Huang RS, Kuo CJ, Ling-Ling T, Chen OTC (1996) EEG pattern recognition-arousal states detection and classification. In: IEEE international conference on neural networks
Flexer A, Sykacek P Rezek I, Dorffner G (2000) Using hidden markov models to build an automatic, continuous and probabilistic sleep stager. In: International joint conference on neural networks, vol 3, pp 627–631
Germain A, Nielson TA (2001) EEG Power associated with early sleep onset images differing in sensory content. J Sleep Res Online 4:83–90
Chaparro-Vargas R, Dissayanaka PC, Penzel T, Ahmed B (2014) Sleep onset detection based on time-varying autoregressive models with particle filter estimation. In: IEEE conference on biomedical engineering. & sciences, pp 436–441
Krakovska A, Mezeiova K (2011) Automatic sleep scoring: a search for an optimal combination of measures. J Artif Intell Med 53(1):25–33
Koley B, Dey D (2012) An ensemble system for automatic sleep stage classification using single channel EEG signal. J Comput Biol Med 10:1–10
lvarez-Estevez DA, Fernandez-Pastoriza JM, Hernandez-Pereira E, Moret-Bonillo V (2013) A method for the automatic analysis of the sleep macrostructure in continuum. J Expert Syst Appl 40(5):1796–1803
Ogilvie RD (2001) The process of falling asleep. J Sleep Med Rev 5:247–270
Malcangi M, Smirne S (2012) Fuzzy-logic inference for early detection of sleep onset in car driver. J Eng Appl Neural Netw 311:41–50
Acharya R, Faust O, Kannathal N, Chua T, Laxminarayan S (2005) Non-linear analysis of EEG signals at various sleep stages. J Comput Methods Progr Biomed 80:37–45
Diambra L, Bastos de Figueiredo JC, Malta CP (1999) Epileptic activity recognition in EEG recording. J Phys A 273:495–505
Abasolo D, Hornero R, Espino P, Poza J, Sanchez CI, de la Rosa R (2005) Analysis of regularity in the EEG background activity of Alzheimer’s disease patients with approximate entropy. J Clin Neurophysiol 116:1826–1834
Pincus SM, Goldberger A (1994) Physiological time series analysis: what does regularity quantify? Am J Physiol 266:1643–1656
Mathew BA (2006) Entropy of electroencephalogram (EEG) signal changes with sleep state. University of Kentucky Master’s Theses Graduate School
Rampil Ira J (1998) A primer for EEG signals processing in anesthesia. J Am Soc Anesthesiol 89:980–1002
Vakkuri A, Yli-Hankala A, Talja P (2004) Time-frequency balanced spectral entropy as a measure of anesthetic drug effect in central nervous system during sevoflurane, propofol, and thiopental anesthesia. J Acta Anaesthesiol Scand 48:145–153
Oja-Viertio H, Maja V, Sarkela M, Talja P, Tenkanen N, Tolvanen-Laakso H, Paloheimo M, Vakkuri A, Yli-Hankala A, Merilainen P (2004) Description of the entropytm algorithm as applied in the Datex-Ohmeda S/5TM entropy module. J Acta Anesthesiol Scand 48:154–161
Maksimow K, Kaisti S, Aalto S, Maenpaa M, Jaaskelainen S, Hinkka S, Martens M, Sarkela H, Oja V, Scheinin H (2005) Correlation of EEG spectral entropy with regional cerebral blood flow during sevoflurane and propofol anesthesia. J Anesth 60:862–869
Sleigh J, Olofsen, WE, Dahan EA, de Goede J, Steyn-Ross A (2001) Entropies of the EEG: the effects of general anesthesia. In: Fifth conference on memory, anesthesia and consciousness, New York
Shannon CE (1948) A mathematical theory of communication. J Bell Syst Technol 27:623–656
Johnson RW, Shore JE (1984) Which is the better entropy expression for speech processing: S log S or log S? IEEE Trans Acoust 32:129–137
Ross Steyn ML (1999) Theoretical electroencephalogram stationary spectrum for a white-noise-driven cortex: evidence for a general anesthetic-induced phase transition. J Phys Rev 60:7299–7311
Anier A, Lipping T, Ferenets R, Puumala P, Sonkajarvi E, Ratsep I, Jantti V (2012) Relationship between approximate entropy and visual inspection of irregularity in the EEG signal, a comparison with spectral entropy. Brit J Anesth 109:928–934
Haykin S (1999) Neural networks, a comprehensive foundation, 2nd edn. Prentice Hall, New Jersey
Carskadon MA, Dement WC (2011) Monitoring and staging human sleep. J Princ Pract Sleep Med 5:16–26
Tinguely G, Finelli LA, Landolt HP, Borbély A, Achermann P (2006) Functional EEG topography in sleep and waking: state-dependent and state independent features. J Neuro Image 32:283–292
Dissayanaka C (2015) Sleep onset detection with multiple EEG alpha-band features: comparison between healthy, insomniac and schizophrenic patients. In: Biomedical circuits and systems conference (BioCAS ) 2015 IEEE, Atlanta, pp 1–4
Nguyen T, Ahn S, Jang H, Jun SC, Kim JG (2015) Sleep onset detection based on simultaneous EEG-NIRS measurement, In: International congress of ophthalmology and optometry, China
Sun H, Bi L, Chen B, Guo Y (2015) EEG-based safety driving performance estimation and alertness using support vector machine. Int J Secur Appl 9:125–134
Acknowledgments
We thank Dr. Uma Maheshwari and Sleep Lab staff of MS Ramaiah Medical College and Hospitals, Bangalore, India, for providing us with the PSG recordings of sleep data.
Authors contribution
N. Sriram and T.K. Padma Shri contributed equally in terms of the data collection, analysis and performing the classification. Uma Maheshwari Krishnaswamy was involved in clinical validation of the data and ensuring the statistical analysis of the data. All the three authors contributed equally in terms of manuscript preparation and finalization.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
We hereby declare that there is no conflict of interest.
Rights and permissions
About this article
Cite this article
Sriraam, N., Padma Shri, T.K. & Maheshwari, U. Recognition of wake-sleep stage 1 multichannel eeg patterns using spectral entropy features for drowsiness detection. Australas Phys Eng Sci Med 39, 797–806 (2016). https://doi.org/10.1007/s13246-016-0472-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13246-016-0472-8