Framework uses CNNs for joint sleep stage classification and prediction.
problem Diagnosing and treating sleep disorders requires accurate sleep stage identification.
method Joint classification-and-prediction CNN framework based on a novel architecture.
result Framework achieves 82.3% and 83.6% accuracy on two public datasets.
RobustSleepNet automates sleep stage classification for any PSG montage.
problem Manual sleep staging is tedious and expensive; automatic methods are limited by PSG montage and demographic differences.
method RobustSleepNet is a deep learning model that handles arbitrary PSG montages and is robust to demographic changes.
result RobustSleepNet achieves 97% F1 score on unseen data, outperforming specific training datasets by 2%.
Deep neural nets classify sleep stages from raw PSG data with high accuracy.
problem Automatically classifying sleep stages from raw polysomnogram signals.
method Deep residual neural networks trained on 50 convolutional layers.
result Best model achieved 84.1% accuracy and 0.746 Cohen's kappa.
Study proposes automated framework for REM Sleep Behaviour Disorder detection.
problem Early detection of REM Sleep Behaviour Disorder (RBD) as a predictor of Parkinson's disease.
method Automated sleep staging followed by RBD identification using a Random Forest classifier and 156 features from EEG, EOG, and EMG channels.
result Automated RBD detection achieved 96% accuracy, surpassing individual established metrics.
A wearable device-based sleep stage classifier using feature learning and RNNs.
problem Automatic sleep stage classification using wearable devices.
method Multi-level feature learning framework and RNN classifier with BLSTM.
result The algorithm achieves high precision, recall, and F1 scores in both resting and comprehensive groups.
Improved sleep stage classification using FT surrogates for class-balanced data.
problem Class imbalance in noisy signals for sleep stage classification.
method Generated FT surrogates to balance the CAPSLPDB database and trained a CNN.
result Surrogate-based augmentation improved mean F1-score by 7%.
SLEEPER combines deep learning with expert rules for accurate sleep staging.
problem Manual sleep staging is tedious and requires expert time.
method SLEEPER uses convolutional neural networks and expert rules to generate interpretable models.
result SLEEPER achieves comparable accuracy to human experts and deep neural networks.
Deep learning classifies sleep stages from EEG, EOG, and EMG signals.
problem Sleep stage classification by sleep experts is time-consuming and prone to errors.
method End-to-end deep learning model using multivariate and multimodal PSG signals.
result Deep learning model achieves state-of-the-art performance on PSG records.
Deep neural net improves sleep stage classification from raw EEG.
problem Improving accuracy of sleep stage classification from raw EEG data.
method 34-layer deep residual ConvNet architecture trained on raw single channel EEG data.
result Proposed network outperforms state-of-the-art methods in sleep staging accuracy.
Paper proposes an auto-encoder with selective attention for better sleep stage classification.
problem Challenges in automatic sleep staging, especially with large feature sets.
method Auto-encoder with selective attention mechanism for feature learning.
result Performance improvement over regular auto-encoder and DBN.
Study optimizes deep learning models for sleep stage classification.
problem Time-consuming and inconsistent manual sleep stage scoring.
method Investigated architectural choices in encoder-predictor architectures for polysomnography recordings.
result Robust architectures improve sleep stage classification performance.
New method uses HDP-HMM and multitaper spectral estimation for automated sleep state classification.
problem Manual sleep scoring is subjective, time-consuming, and doesn't capture neural dynamics.
method Hierarchical Dirichlet Process Hidden Markov Model (HDP-HMM) with multitaper spectral estimation.
result Automated algorithm recovers sleep dynamics and identifies subject-specific microstates.
We used convolutional neural networks (CNNs) for automatic sleep stage scoring based on single-channel electroencephalography (EEG) to learn task-specific filters for classification without using prior domain knowledge. We used an openly available dataset from 20 healthy young adults for evaluation and applied 20-fold …
Bayesian approach predicts brain-age from EEG sleep states across age.
problem Inconsistent brain-age predictions due to subjective sleep state classification.
method Unified Bayesian Network with Gaussian Mixture Models for EEG sleep states.
result Improved accuracy in brain-age prediction over a wider age range.
Study benchmarks automated sleep staging against human scorers, achieving human-level performance.
problem Lack of standardized comparison between human and automated sleep staging.
method Developed multi-scored datasets and a framework to compare multiple human scorers' consensus.
result Many automated methods can match human scorers' performance, with SimpleSleepNet achieving high F1 scores.
U-Time uses a fully convolutional network for sleep stage classification.
problem Challenges in tuning and optimizing recurrent neural networks for sleep data.
method U-Time is a fully feed-forward deep learning approach based on U-Net architecture.
result U-Time outperforms state-of-the-art models for sleep stage classification.
Model tracks sleep stages from CPAP flow signals, improving accuracy.
problem Accurate sleep staging from CPAP flow signals for monitoring CPAP therapy.
method End-to-end framework combining deep convolution and recurrent neural networks with a structured output layer.
result Improved accuracy by 10% compared to previous methods.
Deep neural networks improve sleep stage classification across diverse datasets.
problem Manual sleep scoring is subjective and lacks reliability; automatic systems generalize poorly.
method Developed a deep neural network using 15,684 polysomnography studies from five cohorts.
result Classification accuracy improved with more training data and multiple data sources.
Deep learning classifies sleep stages from EEG signals, aiding professionals.
problem Manual scoring of sleep stages from EEG signals is tedious and requires trained professionals.
method Multitaper spectral analysis and deep convolutional neural networks for automatic classification.
result System accurately classifies sleep stages in new patients, favorably compared to state-of-the-art.
Deep transfer learning improves automatic sleep staging accuracy.
problem Small cohort data variability and inefficiency in sleep studies.
method Deep transfer learning approach using a large dataset to a small cohort.
result Significant performance improvement on automatic sleep staging.
New deep learning method validated across multiple sleep staging databases.
problem Improving automatic sleep scoring accuracy across different datasets.
method Ensemble of local models using deep learning for automatic sleep staging.
result Good general performance compared to human experts and state-of-the-art methods.
CNN classifies sleep-wake states from heart rate variability.
problem Classifying sleep-wake states from heart rate data.
method Convolutional Neural Network (CNN) trained on ECG data.
result CNN achieves high accuracy in classifying wake/sleep stages.
SeqSleepNet tackles automatic sleep staging as a sequence-to-sequence problem.
problem Automatic sleep staging as a sequence-to-sequence classification problem.
method End-to-end hierarchical recurrent neural network (SeqSleepNet) with filterbank and attention-based recurrent layers.
result SeqSleepNet achieves high accuracy (87.1% overall accuracy, 83.3% macro F1-score, 0.815 Cohen's kappa) on a publicly available dataset.
Simple machine learning models outperform deep learning for sleep scoring.
problem Limited applicability and lack of interpretability of deep learning solutions for sleep scoring.
method Revisited sleep stage classification using classical machine learning, including preprocessing, feature extraction, and simple machine learning models.
result Competitive performance achieved with conventional machine learning models on public datasets.
The present study proposes a deep learning model, named DeepSleepNet, for automatic sleep stage scoring based on raw single-channel EEG. Most of the existing methods rely on hand-engineered features which require prior knowledge of sleep analysis. Only a few of them encode the temporal information such as transition ru…
Personalized sleep staging achieved with single-night data using KL-divergence regularization.
problem Improving automatic sleep staging accuracy with limited single-night data.
method KL-divergence regularization for transfer learning from a pretrained model to a personalized model.
result Personalized sleep staging accuracy of 79.6% with KL-divergence regularization.
Deep transfer learning improves sleep staging with small datasets.
problem Insufficient data for deep neural networks due to channel mismatch.
method Transfer learning from large to small datasets, finetuning the pretrained network.
result Significant performance improvement in sleep staging.
Deep learning detects sleep events like arousals and leg movements.
problem Detecting arousals and leg movements in polysomnogram for sleep disorders.
method Deep learning model trained on 1,485 subjects, tested on 1,000 recordings.
result Optimal detection achieved with dynamic event window for arousals and static window for leg movements.
The monitoring of sleep patterns without patient's inconvenience or involvement of a medical specialist is a clinical question of significant importance. To this end, we propose an automatic sleep stage monitoring system based on an affordable, unobtrusive, discreet, and long-term wearable in-ear sensor for recording t…
DOSED detects sleep micro-architecture events in EEG signals.
problem Manual annotation of sleep micro-architecture events is time-consuming and prone to variability.
method DOSED is a deep learning architecture that jointly predicts event locations, durations, and types in EEG time series.
result DOSED outperforms current state-of-the-art detection methods on 4 datasets and 3 types of events (spindles, K-complexes, arousals).
Deep learning detects sleep events in EEG, reducing expert dependency.
problem Manual EEG event annotation by sleep experts is time-consuming and variable.
method Convolutional neural network for joint event detection in EEG signals.
result Deep learning method outperforms existing event-specific algorithms.
Study tackles database variability in medical data using ensemble models and CNNs.
problem Achieving robust generalization in machine learning models across multiple medical databases.
method Ensemble of local models based on convolutional neural networks (CNNs) and various data preprocessing techniques.
result Improved inter-database generalization performance and scalability of models.
SleepNet detects sleep disorders using neural networks trained on PSG data.
problem Automated detection of sleep disorders like apnea and hypopnea.
method Dense Convolutional Neural Network (DRCNN) trained on Polysomnography (PSG) data.
result SleepNet achieved the first place in a sleep arousal detection challenge.
Paper characterizes early-stage dementia signatures from sensor data.
problem Detecting early-stage dementia from sensor data.
method Developed bespoke behavioural models from longitudinal sensor data.
result Found subtle differences in sleep quality and wandering between dementia patients and controls.
Study uses CNNs to detect sleep arousals more accurately.
problem Accurate detection of sleep arousals for better sleep quality assessment.
method Investigated five 1D CNN models on EEG signals from PhysioNet/Computing in Cardiology Challenge 2018.
result Best 1D CNN model achieved high precision and recall metrics.
Landmark AD improves AD's efficiency without sacrificing performance.
problem Computational burden in diffusion-based sensor fusion.
method Inspired by landmark diffusion, proposes Landmark AD.
result Landmark AD offers superior computational efficiency.
CNN improves OSA diagnosis accuracy from PSG data.
problem Manual PSG analysis by specialists is tedious, time-consuming, and prone to errors.
method 1D CNN architecture with convolutional and FCN layers for OSA severity classification.
result Proposed CNN model achieves excellent classification results without manual preprocessing.
IITNet learns sleep stages from raw EEG using sub-epoch features and temporal contexts.
problem Automatic sleep scoring from raw single-channel EEG.
method IITNet uses a residual neural network to extract sub-epoch features and bidirectional LSTM to capture intra- and inter-epoch temporal contexts.
result IITNet achieves comparable performance to state-of-the-art methods, especially with longer sequence lengths.
Improved sleep apnea detection using sensor fusion and backward shortcut connections.
problem Untreated sleep apnea leads to severe health consequences; automated detection is needed.
method Late sensor fusion using backward shortcut connections to improve deep learning models.
result Significant improvement in predictive performance over single sensor methods.
Develops a fast non-invasive tool for diagnosing pediatric sleep apnea.
problem Diagnosing pediatric obstructive sleep apnea using an overnight sleep study is often impractical.
method Combines persistent homology, geometric shape analysis, and convolutional neural networks to classify facial images.
result Facial features associated with obstructive sleep apnea can be recognized for diagnosis.
The problem of information fusion from multiple data-sets acquired by multimodal sensors has drawn significant research attention over the years. In this paper, we focus on a particular problem setting consisting of a physical phenomenon or a system of interest observed by multiple sensors. We assume that all sensors m…
Learned factor graphs improve inference from time sequences using neural networks.
problem Inference from time sequences with limited labeled data.
method Combines model-based algorithms and data-driven ML tools for stationary time sequences.
result Learned factor graphs can accurately infer from small training sets.
REST improves robustness and efficiency of sleep monitoring models.
problem Noise and energy efficiency in deep learning models for home health monitoring.
method Adversarial training and spectral/sparsity regularization.
result REST models achieve 19x parameter reduction and 15x MFLOPS reduction with 17x energy reduction and 9x faster inference.
SCRIB assigns multiple labels to each example to control class-specific prediction risks.
problem Lack of a sound mechanism to decide when to refrain from predicting in DL classifiers.
method Set-classifier with Class-specific Risk Bounds (SCRIB) that assigns multiple labels to each example and controls class-specific prediction risks.
result SCRIB obtained class-specific risks 35%-88% closer to the target risks than baseline methods.
Deep learning detects microsleep episodes in EEG data.
problem Automatic detection of microsleep episodes (MSEs) in EEG data.
method Convolutional neural networks (CNNs) and LSTM networks were implemented to analyze MWT data.
result Deep learning algorithms showed good performance close to human experts in detecting MSEs.
Study uses machine learning to detect sleep disorders by identifying brain patterns.
problem Detecting sleep disorders through EEG patterns in NREM sleep cycles.
method Feature engineering and machine learning model for predicting Cyclic Alternating Patterns (CAP).
result The model accurately predicts CAP sequences associated with sleep disorders.
New methods for predicting compositional data using conformal prediction.
problem No well-established methods for constructing valid prediction sets in compositional data.
method Investigated three conformal prediction-based approaches for Dirichlet regression models.
result HDR approximation approach is robust in terms of coverage, while grid discretization reduces overcoverage.
Deep learning detects sleep state fluctuations in neonates from single EEG channel.
problem Monitoring sleep state fluctuations in neonatal intensive care units.
method Deep learning-based algorithm trained on 53 EEG recordings, validated on 30 polysomnography recordings.
result High accuracy (90%) in detecting quiet sleep states from single EEG channel, generalizing well to external dataset.