A Deep Learning Model for Automatic Sleep Scoring using Multimodality Time Series

Yan, Rui; Li, Fan; Zhou, Dongdong; Ristaniemi, Tapani; Cong, Fengyu

doi:10.23919/eusipco47968.2020.9287518

Cited by 8 publications

(5 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 7 shows a comparison with related sleep stage recognition studies, whereas Table 8 shows a comparison with sleep disorder classification works. We can see that for the sleep stage classification case, both of our methods outperform the best-performing study [ 19 ] by 6% (MML-DMS1) to 9% (MML-DMS2). Note that [ 19 ] classified five sleep stage categories, whereas our approach used six categories.…”

Section: Discussionmentioning

confidence: 81%

“…We can see that for the sleep stage classification case, both of our methods outperform the best-performing study [ 19 ] by 6% (MML-DMS1) to 9% (MML-DMS2). Note that [ 19 ] classified five sleep stage categories, whereas our approach used six categories. Similarly, in sleep disorder classification, our approach outperformed the best results of [ 20 ] by 4% (MML-DMS1 and MML-DMS2).…”

Section: Discussionmentioning

confidence: 81%

“…Accuracies of 82% to 83% were reported using the Sleep EDF database [ 17 , 18 ]. Rui et al [ 19 ] used a multitask 2D-CNN to detect five sleep stages based on the time series features. A testing accuracy of 85% was achieved using the SHHS [ 14 , 15 ] and Sleep-EDF [ 17 , 18 ] data.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Simultaneous Sleep Stage and Sleep Disorder Detection from Multimodal Sensors Using Deep Learning

Cheng

Lech

Wilkinson

2023

Sensors

View full text Add to dashboard Cite

Sleep scoring involves the inspection of multimodal recordings of sleep data to detect potential sleep disorders. Given that symptoms of sleep disorders may be correlated with specific sleep stages, the diagnosis is typically supported by the simultaneous identification of a sleep stage and a sleep disorder. This paper investigates the automatic recognition of sleep stages and disorders from multimodal sensory data (EEG, ECG, and EMG). We propose a new distributed multimodal and multilabel decision-making system (MML-DMS). It comprises several interconnected classifier modules, including deep convolutional neural networks (CNNs) and shallow perceptron neural networks (NNs). Each module works with a different data modality and data label. The flow of information between the MML-DMS modules provides the final identification of the sleep stage and sleep disorder. We show that the fused multilabel and multimodal method improves the diagnostic performance compared to single-label and single-modality approaches. We tested the proposed MML-DMS on the PhysioNet CAP Sleep Database, with VGG16 CNN structures, achieving an average classification accuracy of 94.34% and F1 score of 0.92 for sleep stage detection (six stages) and an average classification accuracy of 99.09% and F1 score of 0.99 for sleep disorder detection (eight disorders). A comparison with related studies indicates that the proposed approach significantly improves upon the existing state-of-the-art approaches.

show abstract

Section: Discussionmentioning

confidence: 81%

Section: Discussionmentioning

confidence: 81%

See 1 more Smart Citation

Simultaneous Sleep Stage and Sleep Disorder Detection from Multimodal Sensors Using Deep Learning

Cheng

Lech

Wilkinson

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…In [20], EEG-, EMG-, EOG-, and ECG features were extracted from the convolutional layers of the CNN. Integration blocks were added to the network structure to merge the modalities.…”

Section: Related Workmentioning

confidence: 99%

Distributed Neural Network System for Multimodal Sleep Stage Detection

2023

View full text Add to dashboard Cite

Existing automatic sleep stage detection methods predominantly use convolutional neural network classifiers (CNNs) trained on features extracted from single-modality signals such as electroencephalograms (EEG). On the other hand, multimodal approaches propose very complexly stacked network structures with multiple CNN branches merged by a fully connected layer. It leads to very high computational and data requirements. This study proposes replacing a stacked network with a distributed neural network system for multimodal sleep stage detection. It has relatively low computational and training data requirements while providing highly competitive results. The proposed multimodal classification and decision-making system (MM-DMS) method applies a fully connected shallow neural network, arbitrating between classification outcomes given by an assembly of independent convolutional neural networks (CNNs), each using a different single-modality signal. Experiments conducted on the CAP Sleep Database data, including the EEG-, ECG-, and EMG modalities representing six stages of sleep, show that the MM-DMS significantly outperforms each single-modality CNN. The fully-connected shallow network arbitration included in the MM-DMS outperforms the traditional majority voting-, average probability-, and maximum probability decision-making methods.

show abstract

“…Clinically, whole-night sleep PSG data, including electroencephalogram (EEG), electromyogram (EMG), electrocardiogram (ECG), electrooculogram (EOG), etc, are divided into 30s epochs with labels of Wake (W), Rapid Eye movement (REM), Non-REM1 (N1), Non-REM2 (N2) and Non-REM3 (N3) by hands [4]. Although large amounts of deep learning methods have been proposed to handle this task automatically [5]- [12], it seems that there is still a gap from real-world implementation, one of possibilities is that the class imbalance problem (CIP) of PSG datasets which has not been paid enough attention and solved well. In simple terms, the CIP in sleep scoring refers to the duration of each sleep stage is not equal because of the special sleep structure.…”

Section: Introductionmentioning

confidence: 99%

Convolutional Neural Network Based Sleep Stage Classification with Class Imbalance

Zhou

Wang

et al. 2022

2022 International Joint Conference on Neural Networks (IJCNN)

Self Cite

View full text Add to dashboard Cite

Accurate sleep stage classification is vital to assess sleep quality and diagnose sleep disorders. Numerous deep learning based models have been designed for accomplishing this labor automatically. However, the class imbalance problem existing in polysomnography (PSG) datasets has been barely investigated in previous studies, which is one of the most challenging obstacles for the real-world sleep staging application. To address this issue, this paper proposes novel methods with signal-driven and image-driven ways of noise addition to balance the imbalanced relationship in the training dataset samples. We evaluate the effectiveness of the proposed methods which are integrated into a convolutional neural network (CNN) based model. Experimental results evaluated on Sleep-EDF-V1, Sleep-EDF and CCSHS databases demonstrate that the proposed balancing approaches with specific tensity Gaussian white noise could enhance the overall or stage N1 recognition to some degree, especially the combination of two types of Data augmentation (DA) strategies shows the superiority of overall accuracy improvement.

show abstract

A Deep Learning Model for Automatic Sleep Scoring using Multimodality Time Series

Cited by 8 publications

References 26 publications

Simultaneous Sleep Stage and Sleep Disorder Detection from Multimodal Sensors Using Deep Learning

Simultaneous Sleep Stage and Sleep Disorder Detection from Multimodal Sensors Using Deep Learning

Distributed Neural Network System for Multimodal Sleep Stage Detection

Convolutional Neural Network Based Sleep Stage Classification with Class Imbalance

Contact Info

Product

Resources

About