بهره‌گیری از بیان تنک به‌منظور کلاس‌بندی مراحل خواب با استفاده از سیگنال الکتروانسفالوگرام

نوع مقاله : مقاله پژوهشی

نویسندگان

گروه مهندسی پزشکی، دانشکده مهندسی برق و کامپیوتر، دانشگاه تبریز، تبریز، ایران

چکیده

در این مقاله، از بیان تنک سیگنال EEG به‌منظور طبقه‌بندی مراحل خواب استفاده شده است. در این راستا دو روند کلی تنک‌سازی پیشنهاد شده و تاثیر آن‌ها بر روند تشخیص مراحل چهارگانه خواب بررسی شده است. روش پیشنهادی اول مبتنی بر به‌کارگیری روش تحلیل مولفه اصلی تنک (SPCA) برای حالت‌های به‌کارگیری ویژگی‌های مختلف، از جمله زمانی، فرکانسی و زمان-فرکانسی و اعمال به کلاس‌بندی ماشین بردار پشتیبان (SVM) است. روش پیشنهادی دوم بر اساس به‌کارگیری طبقه‌بندی‌کننده مبتنی بر بیان تنک (SRC) است که از الگوریتم پیگیر تطبیق متعامد (OMP) در مرحله ایجاد دیکشنری و بیان تنک بهره می‌برد. به منظور ارزیابی کارایی الگوریتم‌های پیشنهادی، عملکرد آن‌ها  با الگوریتم‌های موجود مشابه مقایسه شده است و بدین منظور از داده‌های ثبت شده در پایگاه داده بین‌المللی PhysioNet استفاده شده است. مقایسه نتایج روش های پیشنهادی نشان دهنده بالاتر بودن دقت میانگین روش پیشنهادی اول نسبت به روش PCA و روش یادگیری عمیق به ترتیب %8.36 و %8.26 است. همچنین سرعت اجرای روش پیشنهادی دوم نسبت به دو روش مذکور %118 و %72 بالاتر است.

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Exploiting Sparse Representation for Sleep Stage Classification Using Electroencephalogram Signal

نویسندگان [English]

  • B. Azadian
  • T. Yousefi Rezaii
  • S. Meshgini
Department of Biomedical Engineering, Faculty of Electrical and Computer Engineering, University of Tabriz, Tabriz, Iran
چکیده [English]

In this paper, sparse representation of EEG signal is used to automatically classify sleep stages. In this regard, two general sparse representation trends are proposed to classify 4-class sleep stages. The first proposed method is based on sparse principal component analysis (SPCA) which uses different features including time, frequency, and time-frequency features applied to support vector machine (SVM) classifier. The second proposed method is based on sparse representation-based classifier (SRC) which uses orthogonal matching pursuit (OMP) algorithm to obtain sparse coding of the EEG signal. In order to evaluate the effectiveness of the proposed algorithms, their performance is compared with the conventional SVM classification based on PCA method using time, frequency, and time-frequency features. The study is carried out on EEG signal from Physionet international database. Simulation results show on the average 8.36% and 8.26% improvement of the first proposed method in terms of classification accuracy compared to the PCA and deep learning methods, respectively, while the second proposed method has achieved the running time of 118% and 72% faster than the existing PCA and deep learning methods, respectively.

کلیدواژه‌ها [English]

  • Sleep classification
  • compressed sensing (CS)
  • sparse
  • electroencephalogram (EEG) signal

مراجع

[1] M. Hamilton, “Development of a rating scale for primary depressive illness”, Br. J. Soc. Clin. Psychol., vol. 6, No. 4, pp. 278-296, 1967.
[2] S. Holm, “A simple sequentially rejective multiple test procedure”, Scand. J. Statist., vol. 6, No. 1, pp. 65-70, 1979.
[3] F. Ebrahimi, M. Mikaeili, E. Estrada, and H. Nazeran, "Automatic sleep stage classification based on EEG signals by using neural networks and wavelet packet coefficients", 30th Annual International IEEE EMBS Conference, Vancouver, pp. 1151-1154, 2008.
[4] N. Schaltenbrand, R. Lengelle, M. Toussaint, R. Luthringer, G. Carelli, A. Jacqrnin, E. Lainey, A. Muzet, and J. P. Macher, "Sleep stage scoring using the neural network model: comparison between visual and automatic analysis in normal subjects and patients", Sleep, Vol. 19, No.1, pp. 26-35, 1996.
[5] S. Holm, “A simple sequentially rejective multiple test procedure”, Scand. J. Statist., vol. 6, No. 1, pp. 65-70, 1979.
[6] E. Oropesa, H. L. Cycon, M. Jobert, “Sleep Stage Classification using Wavelet Transform and Neural Network”, International Computer Science Institute (ICSI), 1999.
[7] M. Kiymik, M. Akin, A, Subasi, “Automatic recognition of alertness level by using wavelet transform and artificial neural network”, J. Neuroscience Methods, vol.139, No. 1, pp.231-240, 2004.
[8] H. Yu, H. Lu, T. Ouyang, H. Liu, and B. Lu, "Vigilance detection based on sparse representation of EEG" , Conf. Proc. IEEE Eng. Med. Biol. Soc. ,pp. 2439-2442, 2010.
[9] S. Motamedi-Fakhr, M. Moshrefi-Torbati, M. Hill, C.M. Hill, and P.R. White, “Signal processing techniques applied to human sleep EEG signals— A review,” Biomed Signal Process Control, vol. 10, No. 1, pp 21-33, 2014.
[10] K. Samieea, P. Kov´acsb, S. Kiranyaza, M. Gabbouja, T. Saram¨aki, "Sleep stage classification using sparse rational decomposition of single channel EEG records", Signal Processing Conference (EUSIPCO), pp. 1905-1909, 2015.
[11] H. T. Ocbagabir, K. A. I. Aboalayon, M. Faezipour, "Efficient EEG analysis for seizure monitoring in epileptic patients," Systems, Applications and Technology Conference (LISAT), IEEE Long Island, pp.1-6, May 2013.
[12] K. Aboalayon, H. Ocbagabir, and M. Faezipour, "Efficient Sleep Stage Classification Based on EEG Signals", Systems, Applications and Technology Conference (LISAT), 2014.
[13] H. Liu, H. Yu, Q. Ren, H. Lu, "Estimate vigilance level in driving simulation based on sparse representation", International Conference on Machine Learning and Cybernetics (ICMLC) pp.1111-1115, 2010.
[14] C. Vural, and M. Yildiz, " Determination of sleep stage separation ability of features extracted from EEG signals using Principle component analysis", J. Med. Syst., Vol. 34, 83-89, 2010.
[15] M. Jobert, H. Escola E. Poiseau, p. Gaillard, "Automatic analysis of sleep using two parameters based on principal component analysis of electroencephalography spectral data", Biological Cybernetics, Vol. 71, No. 3, pp. 197-207, 1994.
[16] A. Subasi, “Automatic recognition of alertness level from EEG by using neural network and wavelet coefficients”, Expert Systems with Applications, vol. 28, No. 1, pp. 701–711, 2005.
[17] Vatankhah, M.; Akbarzadeh-T, M-R; Moghimi, A., "An intelligent system for diagnosing sleep stages using wavelet coefficients," International Joint Conference on Neural Networks (IJCNN), pp. 18-23, 2010.
[18] Faezeh Movahedi, James L. Coyle, Ervin Sejdi´, " Deep belief networks for electroencephalography: A review of recent contributions and future utlooks",  IEEE Journal of Biomedical and Health Informatics, Vol. 22, no. 3, pp. 642-652, 2018
[19] J. Zhang, Y. Wu, J. Bai, and F. Chen, "Automatic sleep stage classification based on sparse deep belief net and combination of multiple classifiers", Computer Methods and Programs in Biomedicine, Vol. 38, No. 4, pp. 2016.
[20] M. Langkvist, L. Karlsson, and A. Loutfi, "Sleep stage classification using unsupervised feature learning",  Advances in Artificial Neural Systems, Vol. 1, no. 1, pp. 1-9, 2012.
[21] Kunyang Li , Weifeng Pan , Qing Jiang , Guanzheng Liu, "A Method to Detect Sleep Apnea based on Deep Neural Network and Hidden Markov Model using Single-Lead ECG signal", Neurocomputing, Vol. 294, no. 1, pp. 94-101, 2018.
[22] K. Pillay, A. Dereymaeker, K. Jansen, G. Naulaers, S. V. Huffel, and M. D. Vos," Automated EEG sleep staging in the term-age baby using a generative modelling approach",  Journal of Neural Engineering, Vol. 15, no. 1, pp. 1-13, 2018.
[23] International Database PhysioNet Sleep Recordings: http://www.physionet.org.
[24] Y. Zhang and L. E. Ghaoui, " Large-Scale Sparse Principal Component Analysis with Application to Text Data",  The Neural Information Processing Systems Conference (NIPS), Granada, Spain, December 2011.

فایل ها

هم رسانی

ارجاع به این مقاله

آمار