A Hierarchical Neural Network for Sleep Stage Classification Based on Comprehensive Feature Learning and Multi-Flow Sequence Learning

Sun, Chenglu; Chen, Chen; Li, Wei; Fan, Jiahao; Chen, Wei

doi:10.1109/jbhi.2019.2937558

Cited by 66 publications

(43 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For example, (Hsu, 2013;Yu-Liang et al, 2013;Zhu et al, 2014;Hassan and Haque, 2015;Hassan and Bhuiyan, 2016;Sharma et al, 2017;Yildirim et al, 2019;Zhou et al, 2020) only analyzes the characteristics of a single sleep state and disrupts training between epochs, cutting off the continuity between tags. Dong et al (2018) uses MLP to extract features, LSTM to extract time series information, and (Sun et al, 2020) uses CNN combined with LSTM to extract features and time series information. However, LSTM can only extract the temporal context information of a short sequence, and cannot do anything about a long sequence, especially the time sequence information of a sleep state all night.…”

Section: Discussionmentioning

confidence: 99%

“…In Dong et al (2018), the model used by the author is common MLP+LSTM, using single-channel EEG as input, and an accuracy of 85% was obtained. The latest method proposed in 2020 is presented in Sun et al (2020). The common CNN+LSTM model was used to obtain an accuracy of 86%, which has been very representative.…”

Section: Comparison Of Different Channelsmentioning

confidence: 99%

“…Also, the proposed method achieved better results than other methods. After adding the class imbalance strategy, the accuracy rate could also compete with the methods proposed in Dong et al (2018) and Sun et al (2020), and the N1 recognition rate was significantly improved.…”

Section: Comparison Of Different Channelsmentioning

confidence: 99%

See 2 more Smart Citations

Automatic Sleep Staging Algorithm Based on Time Attention Mechanism

Feng

Wang

et al. 2021

Front. Hum. Neurosci.

View full text Add to dashboard Cite

The most important part of sleep quality assessment is the automatic classification of sleep stages. Sleep staging is helpful in the diagnosis of sleep-related diseases. This study proposes an automatic sleep staging algorithm based on the time attention mechanism. Time-frequency and non-linear features are extracted from the physiological signals of six channels and then normalized. The time attention mechanism combined with the two-way bi-directional gated recurrent unit (GRU) was used to reduce computing resources and time costs, and the conditional random field (CRF) was used to obtain information between tags. After five-fold cross-validation on the Sleep-EDF dataset, the values of accuracy, WF1, and Kappa were 0.9218, 0.9177, and 0.8751, respectively. After five-fold cross-validation on the our own dataset, the values of accuracy, WF1, and Kappa were 0.9006, 0.8991, and 0.8664, respectively, which is better than the result of the latest algorithm. In the study of sleep staging, the recognition rate of the N1 stage was low, and the imbalance has always been a problem. Therefore, this study introduces a type of balancing strategy. By adopting the proposed strategy, SEN-N1 and ACC of 0.7 and 0.86, respectively, can be achieved. The experimental results show that compared to the latest method, the proposed model can achieve significantly better performance and significantly improve the recognition rate of the N1 period. The performance comparison of different channels shows that even when the EEG channel was not used, considerable accuracy can be obtained.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Comparison Of Different Channelsmentioning

confidence: 99%

See 1 more Smart Citation

Automatic Sleep Staging Algorithm Based on Time Attention Mechanism

Feng

Wang

et al. 2021

Front. Hum. Neurosci.

View full text Add to dashboard Cite

show abstract

“…A recurrent neural network (RNN) captures the sequential information, especially the transition rules within sleep epochs, in the second stage. Compared with existing works ( Sun et al, 2019b , a ), the proposed method can achieve promising sleep staging performance from single-channel EOG signals.…”

Section: Introductionmentioning

confidence: 91%

EOGNET: A Novel Deep Learning Model for Sleep Stage Classification Based on Single-Channel EOG Signal

et al. 2021

Self Cite

View full text Add to dashboard Cite

In recent years, automatic sleep staging methods have achieved competitive performance using electroencephalography (EEG) signals. However, the acquisition of EEG signals is cumbersome and inconvenient. Therefore, we propose a novel sleep staging approach using electrooculogram (EOG) signals, which are more convenient to acquire than the EEG. A two-scale convolutional neural network first extracts epoch-wise temporary-equivalent features from raw EOG signals. A recurrent neural network then captures the long-term sequential information. The proposed method was validated on 101 full-night sleep data from two open-access databases, the montreal archive of sleep studies and Sleep-EDF, achieving an overall accuracy of 81.2 and 76.3%, respectively. The results are comparable to those models trained with EEG signals. In addition, comparisons with six state-of-the-art methods further demonstrate the effectiveness of the proposed approach. Overall, this study provides a new avenue for sleep monitoring.

show abstract

“…Therefore, numerous studies have been proposing automatic sleep stage classification by using the main signals containing the characteristics of each stage including EEG, EOG, and sub-mental EMG. The techniques can be categorized into three groups: 1) human-engineered feature extraction with automatic decision making algorithms [7]- [16], 2) the application of extracted features on the Deep Learning (DL) approach [17], [18], and 3) the use of an end-to-end training of the DL approach including Convolutional Neural Network (CNN) or Recurrent Neural Network (RNN) [19]- [25], which involved state-of-the-art sleep staging networks, e.g., DeepSleepNet [26] and SeqSleepNet [27].…”

Section: Introductionmentioning

confidence: 99%

MetaSleepLearner: A Pilot Study on Fast Adaptation of Bio-Signals-Based Sleep Stage Classifier to New Individual Subject Using Meta-Learning

Banluesombatkul

Ouppaphan

Leelaarporn

et al. 2021

IEEE J. Biomed. Health Inform.

Self Cite

View full text Add to dashboard Cite

Identifying bio-signals based-sleep stages requires time-consuming and tedious labor of skilled clinicians. Deep learning approaches have been introduced in order to challenge the automatic sleep stage classification conundrum. However, the difficulties can be posed in replacing the clinicians with the automatic system due to the differences in many aspects found in individual bio-signals, causing the inconsistency in the performance of the model on every incoming individual. Thus, we aim to explore the feasibility of using a novel approach, capable of assisting the clinicians and lessening the workload. We propose the transfer learning framework, entitled MetaSleepLearner, based on Model Agnostic Meta-Learning (MAML), in order to transfer the acquired sleep staging knowledge from a large dataset to new individual subjects (source code is available at https://github.com/IoBT-VISTEC/MetaSleepLearner). The framework was demonstrated to require the labelling of only a few sleep epochs by the clinicians and allow the remainder to be handled by the system. Layer-wise Relevance Propagation (LRP) was also applied to understand the learning course of our approach. In all acquired datasets, in comparison to the conventional approach, MetaSleepLearner achieved a range of 5.4% to 17.7% improvement with statistical difference in the mean of both approaches. The illustration of the model interpretation after the adaptation to each subject also confirmed that the performance was directed towards reasonable learning. MetaSleepLearner outperformed the conventional approaches as a result from the fine-tuning using the recordings of both healthy subjects and patients. This is the first work that investigated a nonconventional pre-training method, MAML, resulting in a possibility for human-machine collaboration in sleep stage classification and easing the burden of the clinicians in labelling the sleep stages through only several epochs rather than an entire recording.

show abstract

A Hierarchical Neural Network for Sleep Stage Classification Based on Comprehensive Feature Learning and Multi-Flow Sequence Learning

Cited by 66 publications

References 28 publications

Automatic Sleep Staging Algorithm Based on Time Attention Mechanism

Automatic Sleep Staging Algorithm Based on Time Attention Mechanism

EOGNET: A Novel Deep Learning Model for Sleep Stage Classification Based on Single-Channel EOG Signal

MetaSleepLearner: A Pilot Study on Fast Adaptation of Bio-Signals-Based Sleep Stage Classifier to New Individual Subject Using Meta-Learning

Contact Info

Product

Resources

About