Automatic sleep stage classification: From classical machine learning methods to deep learning

Sekkal, Rym Nihel; Bereksi–Reguig, F.; Ruiz-Fernández, Daniel; Dib, Nabil; Salihović, Samira

doi:10.1016/j.bspc.2022.103751

Cited by 51 publications

(18 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Although there have been various approaches automating sleep state classification by taking advantage of the sequential nature of the states as suggested by the American Academy of Sleep Medicine (AASM) classification (Craik et al, 2019; Silber et al, 2007; Supratak et al, 2017), studies have shown that including information from neighboring epochs does not necessarily improve classification (Sekkal et al, 2022; Tsinalis et al, 2016). Most deep learning methods also rely on supervised learning, but, due to the high inter-scorer variability in manual classification that these models rely on (Himanen & Hasan, 2000; Younes et al, 2016), we chose an unsupervised method instead.…”

Section: Resultsmentioning

confidence: 99%

“…studies have shown that including information from neighboring epochs does not necessarily improve classification (Sekkal et al, 2022;Tsinalis et al, 2016). Most deep learning methods also rely on supervised learning, but, due to the high inter-scorer variability in manual classification that these models rely on (Himanen & Hasan, 2000;Younes et al, 2016), we chose an unsupervised method instead.…”

Section: Classification Of Sleep Statesmentioning

confidence: 99%

See 1 more Smart Citation

Local field potentials and single unit dynamics in motor cortex of unconstrained macaques during different behavioral states

Yun

Mishler

Perlmutter

et al. 2022

Preprint

View full text Add to dashboard Cite

Different sleep states have been shown to be vital for a variety of brain function, including learning, memory, and skill consolidation. However, our understanding of neural dynamics during sleep and the role of prominent LFP frequency bands remain incomplete. To discern changes between different behavioral states we collected multichannel LFP and spike data in primary motor cortex of unconstrained macaques for up to 24 hours using the Neurochip3. Each 8 second bin of time was classified into awake and moving (Move), awake and at rest (Rest), REM sleep (REM), or non-REM sleep (NREM) by using dimensionality reduction and clustering on the average spectral density and the acceleration of the head. LFP power showed high delta during NREM, high theta during REM, and high beta when the animal was awake. Cross-frequency phase-amplitude coupling typically showed higher coupling for deeper sleep between all pairs of frequency bands except for high delta-high gamma and theta-high gamma coupling during Move, and high theta-beta coupling during REM. Sorted single units showed decreased firing rate with deeper sleep, though with higher “bursty” patterns during NREM compared to other states. Spike-LFP synchrony showed high delta synchrony during Move, and higher coupling with all other frequency bands during NREM. These results altogether are consistent with previous findings showing reactivation of cortical circuitry activated during the day, which may be driven by the delta band LFP.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Classification Of Sleep Statesmentioning

confidence: 99%

Local field potentials and single unit dynamics in motor cortex of unconstrained macaques during different behavioral states

Yun

Mishler

Perlmutter

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…In [17], the authors provided an extensive comparison of common machine learning algorithms and neural network performance for automatic sleep stage classification using EEG signals from the Sleep-EDF expanded database. At the pre-processing stage, DC artifacts and low-frequency deviations are removed, which is followed by a denoising step where two independent components are denoised using a wavelet transform.…”

Section: Related Workmentioning

confidence: 99%

Mixed-Input Deep Learning Approach to Sleep/Wake State Classification by Using EEG Signals

Hasan

Koo

2023

Diagnostics

View full text Add to dashboard Cite

Sleep stage classification plays a pivotal role in predicting and diagnosing numerous health issues from human sleep data. Manual sleep staging requires human expertise, which is occasionally prone to error and variation. In recent times, availability of polysomnography data has aided progress in automatic sleep-stage classification. In this paper, a hybrid deep learning model is proposed for classifying sleep and wake states based on a single-channel electroencephalogram (EEG) signal. The model combines an artificial neural network (ANN) and a convolutional neural network (CNN) trained using mixed-input features. The ANN makes use of statistical features calculated from EEG epochs, and the CNN operates on Hilbert spectrum images generated during each epoch. The proposed method is assessed using single-channel Pz-Oz EEG signals from the Sleep-EDF database Expanded. The classification performance on four randomly selected individuals shows that the proposed model can achieve accuracy of around 96% in classifying between sleep and wake states from EEG recordings.

show abstract

“…[ 10 , 11 , 12 , 13 ]. However, there are some disadvantages to the realization of sleep staging using convolutional neural networks [ 14 ]. Generally speaking, there are three types of information fusion in EEG signals processing: spatial information fusion, temporal information fusion, and spatial and temporal information fusion [ 15 ].…”

Section: Introductionmentioning

confidence: 99%

Multi-Layer Graph Attention Network for Sleep Stage Classification Based on EEG

Wang

Guo

Shen

et al. 2022

Sensors

View full text Add to dashboard Cite

Graph neural networks have been successfully applied to sleep stage classification, but there are still challenges: (1) How to effectively utilize epoch information of EEG-adjacent channels owing to their different interaction effects. (2) How to extract the most representative features according to confused transitional information in confused stages. (3) How to improve classification accuracy of sleep stages compared with existing models. To address these shortcomings, we propose a multi-layer graph attention network (MGANet). Node-level attention prompts the graph attention convolution and GRU to focus on and differentiate the interaction between channels in the time-frequency domain and the spatial domain, respectively. The multi-head spatial-temporal mechanism balances the channel weights and dynamically adjusts channel features, and a multi-layer graph attention network accurately expresses the spatial sleep information. Moreover, stage-level attention is applied to easily confused sleep stages, which effectively improves the limitations of a graph convolutional network in large-scale graph sleep stages. The experimental results demonstrated classification accuracy; MF1 and Kappa reached 0.825, 0.814, and 0.775 and 0.873, 0.801, and 0.827 for the ISRUC and SHHS datasets, respectively, which showed that MGANet outperformed the state-of-the-art baselines.

show abstract

Automatic sleep stage classification: From classical machine learning methods to deep learning

Cited by 51 publications

References 51 publications

Local field potentials and single unit dynamics in motor cortex of unconstrained macaques during different behavioral states

Local field potentials and single unit dynamics in motor cortex of unconstrained macaques during different behavioral states

Mixed-Input Deep Learning Approach to Sleep/Wake State Classification by Using EEG Signals

Multi-Layer Graph Attention Network for Sleep Stage Classification Based on EEG

Contact Info

Product

Resources

About