scholarly journals Sleep Stage Classification for Prediction of Human Sleep Disorders by Using Machine Learning Approach

2020 ◽  
Vol 5 (7) ◽  
pp. 1268-1272
Author(s):  
Mayuri A. Rakhonde ◽  
Dr. Kishor P. Wagh ◽  
Prof. Ravi V. Mante
Keyword(s):  
Machine Learning ◽  
Sleep Disorders ◽  
Learning Algorithm ◽  
Sleep Stage ◽  
Stochastic Gradient Descent ◽  
Sleep Stages ◽  
Power Spectral ◽  
Stage Classification ◽  
Sleep Stage Classification ◽  
Welch Method

Sleep is a fundamental need of human body. In order to maintain health, sufficient sleep is must. Efficiency of sleep is based on sleep stages. Sleep stage classification is required to identify sleep disorders. Sleep stage classification identifies different stages of sleep. In this paper, we used Stochastic Gradient Descent(SGD) a machine learning algorithm for sleep stage classification. In feature extraction, Power Spectral Density(Welch method) is used. We acheived 89% overall accuracy using this model.

scholarly journals Classification of Brainwaves for Sleep Stages by High-Dimensional FFT Features from EEG Signals

2020 ◽  
Vol 10 (5) ◽  
pp. 1797 ◽  
Author(s):  
Mera Kartika Delimayanti ◽  
Bedy Purnama ◽  
Ngoc Giang Nguyen ◽  
Mohammad Reza Faisal ◽  
Kunti Robiatul Mahmudah ◽  
...  
Keyword(s):  
Machine Learning ◽  
Sleep Stage ◽  
Machine Learning Algorithms ◽  
High Dimensional ◽  
Sleep Stages ◽  
Eeg Signals ◽  
Stage Classification ◽  
Sleep Stage Classification ◽  
Low Dimensional

Manual classification of sleep stage is a time-consuming but necessary step in the diagnosis and treatment of sleep disorders, and its automation has been an area of active study. The previous works have shown that low dimensional fast Fourier transform (FFT) features and many machine learning algorithms have been applied. In this paper, we demonstrate utilization of features extracted from EEG signals via FFT to improve the performance of automated sleep stage classification through machine learning methods. Unlike previous works using FFT, we incorporated thousands of FFT features in order to classify the sleep stages into 2–6 classes. Using the expanded version of Sleep-EDF dataset with 61 recordings, our method outperformed other state-of-the art methods. This result indicates that high dimensional FFT features in combination with a simple feature selection is effective for the improvement of automated sleep stage classification.

scholarly journals Shallow Classifier with Sampling for Sleep Stage Classification of Autism Patients

2018 ◽  
Vol 7 (4.44) ◽  
pp. 194
Author(s):  
Intan Nurma Yulita ◽  
Mohamad Ivan Fanany ◽  
Aniati Murni Arymurthy
Keyword(s):  
Sleep Disorders ◽  
Nearest Neighbor ◽  
Sleep Stage ◽  
The Other ◽  
Sleep Stages ◽  
K Nearest Neighbor ◽  
Class Imbalance Problem ◽  
Other Hand ◽  
Stage Classification ◽  
Sleep Stage Classification

Autism is a brain development disorder that affects the patient's ability to communicate and interact with others. Most people with autism get sleep disorders. But they have some difficulty to communicate, so this problem is getting worse. The alternative that can be done is to detect sleep disorders through polysomnography. One of the test purposes is to classify the sleep stages. The doctors need a long time to process it. This paper presents an automatic sleep stage classification. The classification was based on the shallow classifiers, namely naive Bayes, k-nearest neighbor (KNN), multi-layer perceptron (MLP), and C4.5 (a type of decision tree). On the other hand, this dataset has a class imbalance problem. As a solution, this study carried out the mechanism of resampling. The results show that the use of d as a measure of the uniformity of data distribution greatly influenced the classification performance. The higher d, the more uniform the distribution of data (0 <= d <= 1). The performance with d = 1 was higher than d = 0. On the other hand, KNN was the best classifier. The highest accuracy and F-measure were 83.07 and 82.80 respectively. 

A MULTI-LAYER HYBRID MACHINE LEARNING MODEL FOR AUTOMATIC SLEEP STAGE CLASSIFICATION

2018 ◽  
Vol 30 (06) ◽  
pp. 1850041
Author(s):  
Thakerng Wongsirichot ◽  
Anantaporn Hanskunatai
Keyword(s):  
Machine Learning ◽  
Sleep Stage ◽  
Learning Model ◽  
Alternative Methods ◽  
Sleep Stages ◽  
Machine Learning Model ◽  
Subject Specific ◽  
Stage Classification ◽  
Sleep Stage Classification ◽  
Hybrid Machine

Sleep Stage Classification (SSC) is a standard process in the Polysomnography (PSG) for studying sleep patterns and events. The SSC provides sleep stage information of a patient throughout an entire sleep test. A physician uses results from SSCs to diagnose sleep disorder symptoms. However, the SSC data processing is time-consuming and requires trained sleep technicians to complete the task. Over the years, researchers attempted to find alternative methods, which are known as Automatic Sleep Stage Classification (ASSC), to perform the task faster and more efficiently. Proposed ASSC techniques usually derived from existing statistical methods and machine learning (ML) techniques. The objective of this study is to develop a new hybrid ASSC technique, Multi-Layer Hybrid Machine Learning Model (MLHM), for classifying sleep stages. The MLHM blends two baseline ML techniques, Decision Tree (DT) and Support Vector Machine (SVM). It operates on a newly developed multi-layer architecture. The multi-layer architecture consists of three layers for classifying [Formula: see text], [Formula: see text] and [Formula: see text], [Formula: see text], [Formula: see text] in different epoch lengths. Our experiment design compares MLHM and baseline ML techniques and other research works. The dataset used in this study was derived from the ISRUC-Sleep database comprising of 100 subjects. The classification performances were thoroughly reviewed using the hold-out and the 10-fold cross-validation method in both subject-specific and subject-independent classifications. The MLHM achieved a certain satisfactory classification results. It gained 0.694[Formula: see text][Formula: see text][Formula: see text]0.22 of accuracy ([Formula: see text]) in subject-specific classification and 0.942[Formula: see text][Formula: see text][Formula: see text]0.02 of accuracy ([Formula: see text]) in subject-independent classification. The pros and cons of the MLHM with the multi-layer architecture were thoroughly discussed. The effect of class imbalance was rationally discussed towards the classification results.

scholarly journals 1201 Performance Evaluation Of A Novel Contactless Breathing Monitor And Machine Learning Algorithm For Sleep Stage Classification In A Healthy Population

SLEEP ◽  
2020 ◽  
Vol 43 (Supplement_1) ◽  
pp. A459-A459
Author(s):  
T Lauteslager ◽  
S Kampakis ◽  
A J Williams ◽  
M Maslik ◽  
F Siddiqui
Keyword(s):  
Machine Learning ◽  
Home Environment ◽  
Sleep Stage ◽  
Machine Learning Algorithms ◽  
Sleep Stages ◽  
Obstructive Sleep ◽  
Longitudinal Data Collection ◽  
Sleep Assessment ◽  
Stage Classification ◽  
Sleep Stage Classification

Abstract Introduction Although polysomnography (PSG) remains the gold standard for sleep assessment in a lab setting, non-EEG signals such as respiration and motion are directly affected by sleep stages and can be used for sleep stage prediction. Importantly, these signals can be obtained in a low-cost and unobtrusive manner, allowing for large scale and longitudinal data collection in a home environment. The Circadia C100 System (FDA 510(k) clearance expected Q1 2020) is a novel ‘nearable’ device that uses radar for contactless monitoring of respiration and motion. The current study aims to validate the performance of the associated sleep analysis algorithm. Methods A total of 41 nights of sleep data were recorded from 33 healthy participants using the device, alongside PSG. Data were recorded both in a sleep lab and home environment. PSG data were scored by RPSGT-certified technicians. Respiration and movement features were extracted, and machine learning algorithms were developed to perform sleep stage classification and predict sleep metrics. Algorithms were trained and validated on PSG data using cross-validation. Results An epoch-by-epoch true positive rate of 56.2%, 79.4%, 55.5% and 72.6% was found for ‘Wake’, ‘REM’, ‘Light’ and ‘Deep’ respectively. No statistical differences in performance were found between home-recorded and lab-recorded contactless data. Mean absolute error of total sleep time (TST), wake after sleep onset (WASO), and sleep efficiency (SE) was 13.2 minutes, 11.3 minutes and 3%, respectively. The contactless monitor was found to outperform both medical grade and clinical grade actigraphy based devices: The Philips Actiwatch Spectrum Plus and the Fitbit Alta HR. Conclusion Current results are encouraging and suggest that the contactless monitor could be used for long-term sleep assessment and continuous evaluation of sleep therapy outcomes. Further clinical validation work is ongoing in subjects diagnosed with sleep disorders such as obstructive sleep apnea. Support -

scholarly journals Automated Detection of Sleep Stages Using Deep Learning Techniques: A Systematic Review of the Last Decade (2010–2020)

2020 ◽  
Vol 10 (24) ◽  
pp. 8963
Author(s):  
Hui Wen Loh ◽  
Chui Ping Ooi ◽  
Jahmunah Vicnesh ◽  
Shu Lih Oh ◽  
Oliver Faust ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Deep Learning ◽  
Sleep Disorders ◽  
Sleep Stage ◽  
Automated Detection ◽  
Sleep Stages ◽  
Sleep Analysis ◽  
Stage Classification ◽  
Sleep Stage Classification ◽  
Eeg Recordings

Sleep is vital for one’s general well-being, but it is often neglected, which has led to an increase in sleep disorders worldwide. Indicators of sleep disorders, such as sleep interruptions, extreme daytime drowsiness, or snoring, can be detected with sleep analysis. However, sleep analysis relies on visuals conducted by experts, and is susceptible to inter- and intra-observer variabilities. One way to overcome these limitations is to support experts with a programmed diagnostic tool (PDT) based on artificial intelligence for timely detection of sleep disturbances. Artificial intelligence technology, such as deep learning (DL), ensures that data are fully utilized with low to no information loss during training. This paper provides a comprehensive review of 36 studies, published between March 2013 and August 2020, which employed DL models to analyze overnight polysomnogram (PSG) recordings for the classification of sleep stages. Our analysis shows that more than half of the studies employed convolutional neural networks (CNNs) on electroencephalography (EEG) recordings for sleep stage classification and achieved high performance. Our study also underscores that CNN models, particularly one-dimensional CNN models, are advantageous in yielding higher accuracies for classification. More importantly, we noticed that EEG alone is not sufficient to achieve robust classification results. Future automated detection systems should consider other PSG recordings, such as electroencephalogram (EEG), electrooculogram (EOG), and electromyogram (EMG) signals, along with input from human experts, to achieve the required sleep stage classification robustness. Hence, for DL methods to be fully realized as a practical PDT for sleep stage scoring in clinical applications, inclusion of other PSG recordings, besides EEG recordings, is necessary. In this respect, our report includes methods published in the last decade, underscoring the use of DL models with other PSG recordings, for scoring of sleep stages.

Causal Probabilistic Network and Power Spectral Estimation Used in Sleep Stage Classification

1997 ◽  
Vol 36 (04/05) ◽  
pp. 41-46
Author(s):  
A. Kjaer ◽  
W. Jensen ◽  
T. Dyrby ◽  
L. Andreasen ◽  
J. Andersen ◽  
...  
Keyword(s):  
Sleep Stage ◽  
Spectral Estimation ◽  
Interrater Agreement ◽  
Probabilistic Networks ◽  
Probabilistic Network ◽  
Spectral Bands ◽  
Power Spectral ◽  
Stage Classification ◽  
Sleep Stage Classification ◽  
The Brain

Abstract.A new method for sleep-stage classification using a causal probabilistic network as automatic classifier has been implemented and validated. The system uses features from the primary sleep signals from the brain (EEG) and the eyes (AOG) as input. From the EEG, features are derived containing spectral information which is used to classify power in the classical spectral bands, sleep spindles and K-complexes. From AOG, information on rapid eye movements is derived. Features are extracted every 2 seconds. The CPN-based sleep classifier was implemented using the HUGIN system, an application tool to handle causal probabilistic networks. The results obtained using different training approaches show agreements ranging from 68.7 to 70.7% between the system and the two experts when a pooled agreement is computed over the six subjects. As a comparison, the interrater agreement between the two experts was found to be 71.4%, measured also over the six subjects.

scholarly journals Capturing the Development of Internal Representations in a High-Performing Deep Network for Sleep Stage Classification

2021 ◽  
Vol 2 (4) ◽  
Author(s):  
Sarun Paisarnsrisomsuk ◽  
Carolina Ruiz ◽  
Sergio A. Alvarez
Keyword(s):  
Input Data ◽  
Single Channel ◽  
Sleep Stage ◽  
Quantitative Measure ◽  
Classification Performance ◽  
Sleep Stages ◽  
Layer Depth ◽  
Human Sleep ◽  
Stage Classification ◽  
Sleep Stage Classification

AbstractDeep neural networks can provide accurate automated classification of human sleep signals into sleep stages that enables more effective diagnosis and treatment of sleep disorders. We develop a deep convolutional neural network (CNN) that attains state-of-the-art sleep stage classification performance on input data consisting of human sleep EEG and EOG signals. Nested cross-validation is used for optimal model selection and reliable estimation of out-of-sample classification performance. The resulting network attains a classification accuracy of $$84.50 \pm 0.13\%$$ 84.50 ± 0.13 % ; its performance exceeds human expert inter-scorer agreement, even on single-channel EEG input data, therefore providing more objective and consistent labeling than human experts demonstrate as a group. We focus on analyzing the learned internal data representations of our network, with the aim of understanding the development of class differentiation ability across the layers of processing units, as a function of layer depth. We approach this problem visually, using t-Stochastic Neighbor Embedding (t-SNE), and propose a pooling variant of Centered Kernel Alignment (CKA) that provides an objective quantitative measure of the development of sleep stage specialization and differentiation with layer depth. The results reveal a monotonic progression of both of these sleep stage modeling abilities as layer depth increases.

End-to-end machine learning on raw EEG signals for sleep stage classification

2019 ◽  
Vol 64 ◽  
pp. S139
Author(s):  
E. Gunnlaugsson ◽  
H. Ragnarsdóttir ◽  
H.M. þráinsson ◽  
E. Finnsson ◽  
S.Æ. Jónsson ◽  
...  
Keyword(s):  
Machine Learning ◽  
Sleep Stage ◽  
Eeg Signals ◽  
Stage Classification ◽  
Sleep Stage Classification ◽  
End To End
Sign in / Sign up

Export Citation Format

Share Document