A1 Journal article (refereed)
Automatic sleep scoring : a deep learning architecture for multi-modality time series (2021)
Yan, R., Li, F., Zhou, D.D., Ristaniemi, T., & Cong, F. (2021). Automatic sleep scoring : a deep learning architecture for multi-modality time series. Journal of Neuroscience Methods, 348, Article 108971. https://doi.org/10.1016/j.jneumeth.2020.108971
JYU authors or editors
Publication details
All authors or editors: Yan, Rui; Li, Fan; Zhou, Dong Dong; Ristaniemi, Tapani; Cong, Fengyu
Journal or series: Journal of Neuroscience Methods
ISSN: 0165-0270
eISSN: 1872-678X
Publication year: 2021
Volume: 348
Article number: 108971
Publisher: Elsevier
Publication country: Netherlands
Publication language: English
DOI: https://doi.org/10.1016/j.jneumeth.2020.108971
Publication open access: Not open
Publication channel open access:
Publication is parallel published (JYX): https://jyx.jyu.fi/handle/123456789/73831
Abstract
Method: The model adopts a linear function to address different numbers of inputs, thereby extending model applications. Two-dimensional convolution neural networks are used to learn features from multi-modality polysomnographic signals, a “squeeze and excitation” block to recalibrate channel-wise features, together with a long short-term memory module to exploit long-range contextual relation. The learnt features are finally fed to the decision layer to generate predictions for sleep stages.
Result: Model performance is evaluated on three public datasets. For all tasks with different available channels, our model achieves outstanding performance not only on healthy subjects but even on patients with sleep disorders (SHHS: Acc-0.87, K-0.81; ISRUC: Acc-0.86, K-0.82; Sleep-EDF: Acc-0.86, K-0.81). The highest classification accuracy is achieved by a fusion of multiple polysomnographic signals.
Comparison: Compared to state-of-the-art methods that use the same dataset, the proposed model achieves a comparable or better performance, and exhibits low computational cost.
Conclusions: The model demonstrates its transferability among different datasets, without changing model architecture or hyper-parameters across tasks. Good model transferability promotes the application of transfer learning on small group studies with mismatched channels. Due to demonstrated availability and versatility, the proposed method can be integrated with diverse polysomnography systems, thereby facilitating sleep monitoring in clinical or routine care.
Keywords: sleep; sleep research; signal analysis; signal processing; machine learning
Free keywords: polysomnography; automatic sleep scoring; multi-modality analysis; deep learning
Contributing organizations
Ministry reporting: Yes
Reporting Year: 2021
JUFO rating: 1