Sleep staging is an important part of sleep research. Traditional automatic sleep staging based on machine learning requires extensive feature extraction and selection.
OBJECTIVE:
This paper proposed a deep learning algorithm without feature extraction based on one-dimensional convolutional neural network and long short-term memory.
METHODS:
The algorithm can automatically divide sleep into 5 phases including awake period, non-rapid eye movement sleep period (N1 N3) and rapid eye movement using the electroencephalogram signals. The raw signal was processed by the wavelet transform. Then, the processed signal was directly input into the deep learning algorithm to obtain the staging result.
RESULTS:
The accuracy of staging is 93.47% using the Fpz-Cz electroencephalogram signal. When using the Fpz-Cz and electroencephalogram signal, the algorithm can obtain the highest accuracy of 94.15%.
CONCLUSION:
These results show that this algorithm is suitable for different physiological signals and can realize end-to-end automatic sleep staging without any manual feature extraction.
WangQZhaoDWangY, et al. Ensemble learning algorithm based on multi-parameters for sleep staging. Med Biol Eng Comput2019; 57(8): 1693-1707.
2.
LiangSFKuoCEHuYH, et al. A rule-based automatic sleep staging method. J Neurosci Methods2012; 205(1): 169-176.
3.
SharmaMGoyalDAchuthPV, et al. An accurate sleep stages classification system using a new class of optimally time-frequency localized three-band wavelet filter bank. Comput Biol Med2018; 98: 58-75.
4.
SupratakADongHWuC, et al. DeepSleepNet: a model for automatic sleep stage scoring based on raw single-channel EEG. IEEE Trans Neural Syst Rehabil Eng2017; 25(11): 1998-2008.
5.
AlickovicESubasiA. Ensemble SVM method for automatic sleep stage classification. IEEE Trans Instrum Meas2018; 67(6): 1258-1265.
6.
LajnefTChaibiSRubyP, et al. Learning machines and sleeping brains: automatic sleep stage classification using decision-tree multi-class support vector machines. J Neurosci Methods2015; 250: 94-105.
7.
ZafarRDassSCMalikS. Electroencephalogram-based decoding cognitive states using convolutional neural network and likelihood ratio based score fusion. PLoS One2017; 12(5): e0178410.
8.
AkinMKurtMBSezginN, et al. Estimating vigilance level by using EEG and EMG signals. Neural Comput Appl2018; 17(3): 227-236.
9.
ZhangYZhangXLiuW, et al. Automatic sleep staging using multi-dimensional feature extraction and multi-kernel fuzzy support vector machine. J Healthc Eng2014; 5(4): 505-520.
10.
GaidukMPenzelTOrtegaJA, et al. Automatic sleep stages classification using respiratory, heart rate and movement signals. Physiol Meas2018; 9(12): 124008.
11.
NoviyantoAIsaSMWasitoI, et al. Selecting features of single lead ECG signal for automatic sleep stages classification using correlation-based feature subset selection. IJCSI International Journal of Computer Science Issues2011; 8(5): 139-148.
12.
JiangDYuMAYuanyuanW. Sleep stage classification using covariance features of multi-channel physiological signals on Riemannian manifolds. Comput Methods Programs Biomed2019; 178: 19-30.
13.
MovahediFCoyleJLSejdicE. Deep belief networks for electroencephalography: a review of recent contributions and future outlooks. IEEE J Biomed Health Inform2018; 22(3): 642-652.
14.
JestrovićICoyleJLSejdićE. Decoding human swallowing via electroencephalography: a state-of-the-art review. J Neural Eng2015; 12(5): 051001.
15.
Oliver Faust, Hajar Razaghi, Ragab Barika, et al. A review of automated sleep stage scoring based on physiological signals for the new millennia. Comput Methods Programs Biomed2019; 176: 81-91.
16.
U Rajendra Acharya, Shreya Bhat, Oliver Faust, et al. Nonlinear dynamics measures for automated EEG-based sleep stage detection. European Neurology2015; 74(5-6): 268-287.
17.
ThamaraiPAdalarasuK. Denoising of EEG, ECG and PPG signals using wavelet transform. J Pharm Sci2018; 10(1): 156-161.
18.
MateoJTorresAMGarcíaMA. Dynamic fuzzy neural network based learning algorithms for ocular artefact reduction in EEG recordings. Neural Processing Letters2014; 39(1): 45-67.
19.
ZhaoDWangYWangQ, et al. Comparative analysis of different characteristics of automatic sleep stages. Comput Methods Programs Biomed2019; 17553-72.
20.
MousaviSAfghahFAcharyaUR. SleepEEGNet: Automated sleep stage scoring with sequence to sequence deep learning approach. PloS One2019; 14(5): e0216456.
DereymaekerAPillayKVervischJ, et al. An automated quiet sleep detection approach in preterm infants as a gateway to assess brain maturation. Int J Neural Syst2017; 27(6): 1750023.
23.
PławiakP. Novel genetic ensembles of classifiers applied to myocardium dysfunction recognition based on ECG signals. Swarm Evol Comput 2018; 39: 192-208.
24.
YildirimÖ. A novel wavelet sequence based on deep bidirectional LSTM network model for ECG signal classification. Comput Biol Med 2018; 96: 189-202.
25.
AcharyaUROhSLHagiwaraY, et al. A deep convolutional neural network model to classify heartbeats. Comput Biol Med2017; 89: 389-396.
26.
YildirimÖPławiakPTanRS, et al. Arrhythmia detection using deep convolutional neural network with long duration ECG signals. Comput Biol Med2018; 102: 411-420.
27.
OhSLHagiwaraYRaghavendraU, et al. A deep learning approach for Parkinson’s disease diagnosis from EEG signals. Neural Comput Appl. 2018.
28.
AntoniadesASpyrouLMartin-LopezD, et al. Deep neural architectures for mapping scalp to intracranial EEG. Int J Neural Sys2018; 28(8): 1850009.
29.
HassanARSubasiA. Automatic identification of epileptic seizures from EEG signals using linear programming boosting. Comput Methods Programs Biomed2016; 136: 65-77.
30.
LängkvistMKarlssonLLoutfiA. Sleep stage classification using unsupervised feature learning. Advances in Artificial Neural Systems2012; 2012(5): 1-9.
31.
CharbonnierSZoubekLLesecqS, et al. Self-evaluated automatic classifier as a decision-support tool for sleep/wake staging. Computers in Biology & Medicine2011; 41(6): 380-389.
32.
PhanHAndreottiFCoorayN, et al. Joint classification and prediction CNN framework for automatic sleep stage classification. IEEE Trans Biomed Eng2018; 66(5): 1285-1296.
33.
AcharyaUROhSLHagiwaraY, et al. Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals. Comput Biol Med2018; 100: 270-278.
34.
YildirimÖBalogluUBAcharyaUR. A deep learning model for automated sleep stages classification using psg signals. Int J Environ Res Public Health2019; 16(4): 599(1-21).
35.
YulitaINFananyMIArymurthyAM. Fast convolutional method for automatic sleep stage classification. Healthc. Inform. Res. 2018.
36.
DongHSupratakAPanW, et al. Mixed neural network approach for temporal sleep stage classification. IEEE Trans Neural Syst Rehabil Eng2018; 26(2): 324-333.
37.
MichielliNAcharyaURMolinariF. Cascaded LSTM recurrent neural network for automated sleep stage classification using single-channel EEG signals. Comput Biol Med2019; 106: 71-81.
DiykhMLiYWenP. EEG sleep stages classification based on time domain features and structural graph similarity. IEEE Trans Neural Syst Rehabil Eng2016; 24(11): 1159-1168.
40.
Manish Sharma, Sohamkumar Patel, Siddhant Choudhary, et al. Automated Detection of Sleep Stages Using Energy-Localized Orthogonal Wavelet Filter Banks. Arab J Sci Eng. 2019.
41.
Sharma, Manish, Dhere, Abhinav, et al. An Automatic Detection of Focal EEG Signals Using New Class of Time-Frequency Localized Orthogonal Wavelet Filter Banks. Knowl Based Syst. 2016: 118217-227.
42.
RussakovskyODengJSuH, et al. Imagenet large scale visual recognition challenge. Int J Comput Vis2015; 115(3): 211-252.
43.
FaustOHagiwaraYHongTJ, et al. Deep learning for healthcare applications based on physiological signals: a review. Comput Methods Programs Biomed2018; 161: 1-13.
44.
BalogluUBYildirimÖ. Convolutional long-short term memory networks model for long duration EEG signal classification. J Mech Med Biol2019; 19(1).
45.
O"ReillyCGosselinNCarrierJ, et al. Montreal Archive of Sleep Studies: an open-access resource for instrument benchmarking and exploratory research. J Sleep Res2014; 23(6): 628-635.
46.
ChambonSGaltierMNArnalPJ, et al. A deep learning architecture for temporal sleep stage classification using multivariate and multimodal time series. IEEE Trans Neural Syst Rehabil Eng2018; 26(4): 758-769.
47.
TsinalisOMatthewsPMGuoY. Automatic sleep stage scoring using time-frequency analysis and stacked sparse autoencoders. Ann Biomed Eng2016; 44(5): 1587-1597.
48.
TripathyRKAcharyaUR. Use of features from RR-time series and EEG signals for automated classification of sleep stages in deep neural network framework. Biocybern Biomed Eng2018; 38(4): 890-902.
49.
ZhangJWuYBaiJ, et al. Automatic sleep stage classification based on sparse deep belief net and combination of multiple classifiers. T I MEAS CONTROL2016; 38(4): 435-451.
50.
SharmaRPachoriRBUpadhyayA. Automatic sleep stages classification based on iterative filtering of electroencephalogram signals. Neural Comput Appl2017; 28(10(SI)): 2959-2978.
51.
ZhangJWuY. A new method for automatic sleep stage classification. IEEE Trans Biomed Circuits Syst2017; 11(5): 1097-1110.
52.
PhanHAndreottiFCoorayN, et al. SeqSleepNet: end-to-end hierarchical recurrent neural network for sequence-to-sequence automatic sleep staging. IEEE Trans Neural Syst Rehabil Eng2019; 27(3): 400-410.
53.
HassanAR, Bhuiyan MIH. Computer-aided sleep staging using complete ensemble empirical mode decomposition with adaptive noise and bootstrap aggregating. Biomed Signal Process Control2016; 24: 1-10.
54.
ZhuGLiYWenPP. Analysis and classification of sleep stages based on difference visibility graphs from a single-channel EEG signal. IEEE J Biomed Health Inform2014; 18(6): 1813-1821.
55.
HassanARBhuiyanMIH. Automated identification of sleep states from EEG signals by means of ensemble empirical mode decomposition and random under sampling boosting. Comput Methods Programs Biomed2017; 140: 201-210.
56.
MalafeevALaptevDBauerS, et al. Automatic human sleep stage scoring using deep neural networks. Front Neurosci2018; 12: 781(1-15).
57.
Da SilveiraTLTKozakeviciusAJRodriguesCR. Single-channel EEG sleep stage classification based on a streamlined set of statistical features in wavelet domain. Med Biol Eng Comput2017; 55(2): 343-352.
