Abstract
Many systems are developed for automatic sleep stage classification. However, nearly all models are based on handcrafted features. Because of the large feature space, there are so many features that feature selection should be used. Meanwhile, designing handcrafted features is a difficult and time-consuming task because the feature designing needs domain knowledge of experienced experts. Results vary when different sets of features are chosen to identify sleep stages. Additionally, many features that we may be unaware of exist. However, these features may be important for sleep stage classification. Therefore, a new sleep stage classification system, which is based on the complex-valued convolutional neural network (CCNN), is proposed in this study. Unlike the existing sleep stage methods, our method can automatically extract features from raw electroencephalography data and then classify sleep stage based on the learned features. Additionally, we also prove that the decision boundaries for the real and imaginary parts of a complex-valued convolutional neuron intersect orthogonally. The classification performances of handcrafted features are compared with those of learned features via CCNN. Experimental results show that the proposed method is comparable to the existing methods. CCNN obtains a better classification performance and considerably faster convergence speed than convolutional neural network. Experimental results also show that the proposed method is a useful decision-support tool for automatic sleep stage classification.
Research funding: Authors state no funding involved.
Conflict of interest: Authors state no conflict of interest.
References
[1] Aizenberg I. Complex-valued neural networks with multi-valued neurons. Heidelberg: Springer, Warsaw: Newelska 2011: 1–7.10.1007/978-3-642-20353-4Search in Google Scholar
[2] Álvarez-Estévez D, Fernández-Pastoriza JM, Hernández-Pereira E, et al. A method for the automatic analysis of the sleep macrostructure in continuum. Expert Syst Appl 2013; 40: 1796–1803.10.1016/j.eswa.2012.09.022Search in Google Scholar
[3] Amin MF, Murase K. Single-layered complex-valued neural network for real-valued classification problems. Neurocomputing 2009; 72: 945–955.10.1016/j.neucom.2008.04.006Search in Google Scholar
[4] Bai J, Wu Y, Zhang JM, et al. Subset based deep learning for RGB-D object recognition. Neurocomputing 2015; 165: 280–292.10.1016/j.neucom.2015.03.017Search in Google Scholar
[5] Bengio Y, LeCun Y. Scaling learning algorithms towards AI. In: Large scale kernel machines. Cambridge: MIT Press 2007.10.7551/mitpress/7496.003.0016Search in Google Scholar
[6] Cecotti H. A time–frequency convolutional neural network for the offline classification of steady-state visual evoked potential responses. Pattern Recogn Lett 1954; 32: 1492–1503.10.1016/j.patrec.2011.02.022Search in Google Scholar
[7] Cecotti H, Graser A. Convolutional neural networks for P300 detection with application to brain-computer interfaces. IEEE T Pattern Anal Mach Intell 2011; 33: 433–445.10.1109/TPAMI.2010.125Search in Google Scholar PubMed
[8] Charbonnier S, Zoubek L, Lesecq S, et al. Self-evaluated automatic classifier as a decision-support tool for sleep/wake staging. Comput Biol Med 2011; 41: 380–389.10.1016/j.compbiomed.2011.04.001Search in Google Scholar PubMed
[9] Cohen J. A coefficient of agreement for nominal scales. Educ Psychol Meas 1960; 20: 37–46.10.1177/001316446002000104Search in Google Scholar
[10] Flexer A, Gruber G, Dorffner G. A reliable probabilistic sleep stager based on a single EEG signal. Artif Intell Med 2005; 33: 199–207.10.1016/j.artmed.2004.04.004Search in Google Scholar PubMed
[11] Fraiwan L, Lweesy K, Khasawneh N, et al. Automated sleep stage identification system based on time-frequency analysis of a single EEG channel and random forest classifier. Comput Meth Prog Bio 2012; 108: 10–19.10.1016/j.cmpb.2011.11.005Search in Google Scholar PubMed
[12] Freye E, Levy JV. Cerebral monitoring in the operating room and the intensive care unit: an introductory for the clinician and a guide for the novice wanting to open a window to the brain. J Clin Monitor Comp 2005; 19: 1–76.10.1007/s10877-005-0712-zSearch in Google Scholar
[13] Gath I, Feuerstein C, Geva A. Unsupervised classification and adaptive definition of sleep patterns. Pattern Recogn Lett 1994; 15: 977–984.10.1016/0167-8655(94)90029-9Search in Google Scholar
[14] Goldberger AL, Amaral LA, Glass L, et al. PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. Circulation 2000; 101: e215–e220.10.1161/01.CIR.101.23.e215Search in Google Scholar
[15] Gudmundsson S, Runarsson TP, Sigurdsson S. Automatic sleep staging using support vector machines with posterior probability estimates. In: International conference on intelligent agents, web technologies and internet commerce 2005: 366–372.Search in Google Scholar
[16] Hänsch R, Hellwich O. Classification of polarimetric SAR data by complex valued neural networks. In: ISPRS workshop high-resolution earth imaging for geospatial information 2009; 38: 4–7.Search in Google Scholar
[17] Hänsch R, Hellwich O. Complex-valued convolutional neural networks for object detection in PolSAR data. In: 8th European Conference on Synthetic Aperture Radar (EUSAR) 2010: 1–4.Search in Google Scholar
[18] Hau-tieng W, Talmon R, Yu-Lun L. Assess sleep stage by modern signal processing techniques. IEEE Trans Biomed Eng 2015; 62: 1159–1168.10.1109/TBME.2014.2375292Search in Google Scholar PubMed
[19] Holzmann DCA, Pérez CA, Held CM, et al. Expert-system classification of sleep/waking states in infants. Med Biol Eng Comput 1999; 37: 466–476.10.1007/BF02513332Search in Google Scholar PubMed
[20] Hsu YL, Yang YT, Wang JS, et al. Automatic sleep stage recurrent neural classifier using energy features of EEG signals. Neurocomputing 2013; 104: 105–114.10.1016/j.neucom.2012.11.003Search in Google Scholar
[21] Hubel DH, Wiesel TN. Receptive fields and functional architecture of monkey striate cortex. J Physiol 1968; 195: 215–243.10.1113/jphysiol.1968.sp008455Search in Google Scholar PubMed PubMed Central
[22] Hubel DH, Wiesel TN. Receptive fields of single neurons in the cat’s striate cortex. J Physiol 1959; 148: 574–591.10.1113/jphysiol.1959.sp006308Search in Google Scholar PubMed PubMed Central
[23] Kemp B, Gröneveld EW, Janssen A, et al. A model-based monitor of human sleep stages. Biol Cybern 1987; 57: 365–378.10.1007/BF00354982Search in Google Scholar PubMed
[24] Kim T, Adali T. Fully complex multi-layer perceptron network for nonlinear signal processing. J VLSI Signal Process Syst Signal Image Video Technol 2002; 32: 29–43.10.1023/A:1016359216961Search in Google Scholar
[25] Kiranyaz S, Ince T, Gabbouj M. Real-time patient-specific ECG classification by 1D convolutional neural networks. IEEE T Biomed Eng 2016; 63: 664–675.10.1109/TBME.2015.2468589Search in Google Scholar PubMed
[26] Koley B, Dey D. An ensemble system for automatic sleep stage classification using single channel EEG signal. Comput Biol Med 2012; 42: 1186–1195.10.1016/j.compbiomed.2012.09.012Search in Google Scholar PubMed
[27] Krakovská A, Mezeiová K. Automatic sleep scoring: a search for an optimal combination of measures. Artif Intell Med 2011; 53: 25–33.10.1016/j.artmed.2011.06.004Search in Google Scholar PubMed
[28] Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. In: Advances in neural information processing systems 2012: 1097–1105.Search in Google Scholar
[29] Kuo CE, Liang SF, Li YC, et al. An EOG-based sleep monitoring system and its application on on-line sleep-stage sensitive light control. In Proceedings of the International Conference on Physiological Computing Systems, 20-30, 2014, Lisbon, Portugal ISBN 978-989-758-006-2, DOI: 10.5220/0004725600200030.Search in Google Scholar
[30] Kurihara Y, Watanabe K. Sleep-Stage decision algorithm by using heartbeat and body-movement signals. IEEE T Syst Man Cybern A Syst Hum 2012; 42: 1450–1459.10.1109/TSMCA.2012.2192264Search in Google Scholar
[31] LeCun Y, Bottou L, Bengio Y, Haffner P. Gradient-based learning applied to document recognition. P IEEE 1998; 86: 2278–2324.10.1109/5.726791Search in Google Scholar
[32] LeCun Y, Huang FJ, Bottou L. Learning methods for generic object recognition with invariance to pose and lighting. In: Computer vision and pattern recognition 2004: II–97.10.1109/CVPR.2004.1315150Search in Google Scholar
[33] Liang SF, Kuo CE, Hu YH, et al. Automatic stage scoring of single-channel sleep EEG by using multiscale entropy and autoregressive models. IEEE T Instrum Meas 2012; 61: 1649–1657.10.1109/TIM.2012.2187242Search in Google Scholar
[34] Mateo J, Torres AM, Sanchez-Morla EM, et al. Eye movement artifact suppression using Volterra filter for electroencephalography signals. J Med Biol Eng 2015; 35: 395–405.10.1007/s40846-015-0036-5Search in Google Scholar
[35] Michel HE, Awwal AAS. Enhanced artificial neural networks using complex numbers. In: The 1999 international joint conference on 1999; 1: 456–461.10.1109/IJCNN.1999.831538Search in Google Scholar
[36] Mirowski PW, LeCun Y, Madhavan D, et al. Comparing SVM and convolutional networks for epileptic seizure prediction from intracranial EEG. In: IEEE workshop on machine learning for signal process 2008:244–249.10.1109/MLSP.2008.4685487Search in Google Scholar
[37] Mirowski PW, Madhavan D, LeCun Y. Time-delay neural networks and independent component analysis for EEG-based prediction of epileptic seizures propagation. In: Proceedings of the twenty-second AAAI conference on artificial intelligence 2007; 22: 1892–1893.Search in Google Scholar
[38] Moser D, Anderer PG, Parapatics S, et al. Sleep classification according to AASM and Rechtschaffen & Kales: effects on sleep scoring parameters. Sleep 2009; 32: 139–149.10.1093/sleep/32.2.139Search in Google Scholar PubMed PubMed Central
[39] Nitta T. The computational power of complex-valued neuron. Artif Neural Netw Neural Inf Process ICANN/ICONIP Lect Notes Comput Sc 2003; 2714: 993–1000.10.1007/3-540-44989-2_118Search in Google Scholar
[40] Nitta T. Orthogonality of decision boundaries in complex-valued neural networks. Neural Comput 2004; 16: 73–97.10.1162/08997660460734001Search in Google Scholar PubMed
[41] Rechtschaffen A, Kales A. A manual of standardized terminology, techniques and scoring system for sleep stages of human subjects. Washington DC: Government Printing Office, Public Health Service 1968: 3–7.Search in Google Scholar
[42] Ronzhina M, Janoušek O, Kolářová J, et al. Sleep scoring using artificial neural networks. Sleep Med Rev 2012; 16: 251–263.10.1016/j.smrv.2011.06.003Search in Google Scholar PubMed
[43] Schulz H. Rethinking sleep analysis: comment on the AASM manual for the scoring of sleep and associated events. J Clin Sleep Med 2008; 4: 99–103.10.5664/jcsm.27124Search in Google Scholar
[44] Sharpless BA, Barber JP. Lifetime prevalence rates of sleep paralysis: a systematic review. Sleep Med Rev 2011; 15: 311–315.10.1016/j.smrv.2011.01.007Search in Google Scholar PubMed PubMed Central
[45] Sokolova M, Japkowicz N, Szpakowicz S. Beyond accuracy, F-score and ROC: a family of discriminant measures for performance evaluation. Adv Artif Intell 1970; 4304: 1015–1021.10.1007/11941439_114Search in Google Scholar
[46] Stober S, Cameron DJ, Grahn JA. Using convolutional neural networks to recognize rhythm stimuli from electroencephalography recordings. In: Advances in neural information processing systems 2014: 1499–1457.Search in Google Scholar
[47] Suresh S, Sundararajan N, Savitha R. Supervised learning with complex-valued neural networks. Berlin Heidelberg: Springer 2013: 125–132.10.1007/978-3-642-29491-4_7Search in Google Scholar
[48] Wulsin DF, Gupta JR, Mani R, et al. Modeling electroencephalography waveforms with semi-supervised deep belief nets: fast classification and anomaly measurement. J Neural Eng 2011; 8: 53–57.10.1088/1741-2560/8/3/036015Search in Google Scholar PubMed PubMed Central
[49] Yang CC, Bose NK. Landmine detection and classification with complex-valued hybrid neural network using scattering parameters dataset. IEEE T Neural Networ 2005; 16: 743–753.10.1109/TNN.2005.844906Search in Google Scholar PubMed
[50] Yu D, Deng L. Deep learning and its applications to signal and information processing. IEEE Signal Process Mag 2011; 28:145–154.10.1109/MSP.2010.939038Search in Google Scholar
[51] Zoubek L, Charbonnier S, Lesecq S, et al. Feature selection for sleep/wake stages classification using data driven methods. Biomed Signal Process Control 2007; 2: 171–179.10.1016/j.bspc.2007.05.005Search in Google Scholar
©2018 Walter de Gruyter GmbH, Berlin/Boston
