EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

SeriesSleepNet: an EEG time series model with partial data augmentation for automatic sleep stage scoring

Minji Lee, Heon-Gyu Kwak, Hyeong-Jin Kim, Dong-Ok Won, Seong-Whan Lee

Frontiers in Physiology · 28.08.2023 · 14

DOI: 10.3389/fphys.2023.1188678 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Physiology, online erschienen am 28.08.2023. Verfasst von Minji Lee und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedical Software Engineering, The Catholic University of Korea, Bucheon, Republic of Korea. Die Arbeit wurde bisher 34-mal zitiert (Crossref) und nennt 62 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

We propose an automatic sleep stage scoring model, referred to as SeriesSleepNet, based on convolutional neural network (CNN) and bidirectional long short-term memory (bi-LSTM) with partial data augmentation. We used single-channel raw electroencephalography signals for automatic sleep stage scoring.

Methods

Our framework was focused on time series information, so we applied partial data augmentation to learn the connected time information in small series. In specific, the CNN module learns the time information of one epoch (intra-epoch) whereas the bi-LSTM trains the sequential information between the adjacent epochs (inter-epoch). Note that the input of the bi-LSTM is the augmented CNN output. Moreover, the proposed loss function was used to fine-tune the model by providing additional weights. To validate the proposed framework, we conducted two experiments using the Sleep-EDF and SHHS datasets. Results and Discussion: The results achieved an overall accuracy of 0.87 and 0.84 and overall F1-score of 0.80 and 0.78 and kappa value of 0.81 and 0.78 for five-class classification, respectively. We showed that the SeriesSleepNet was superior to the baselines based on each component in the proposed framework. Our architecture also outperformed the state-of-the-art methods with overall F1-score, accuracy, and kappa value. Our framework could provide information on sleep disorders or quality of sleep to automatically classify sleep stages with high performance.

Schlagwörter

Stichwörter der Autor:innen

automatic sleep stage scoringbi-directional long-short term memoryconvolutional neural networkdeep learningsingle-channel EEG

Autor:innen und Institutionen

  • Department of Biomedical Software Engineering, The Catholic University of Korea, Bucheon, Republic of Korea.
  • Department of Artificial Intelligence, Korea University, Seoul, Republic of Korea.
  • Department of Brain and Cognitive Engineering, Korea University, Seoul, Republic of Korea.
  • Department of Artificial Intelligence Convergence, Hallym University, Chuncheon, Republic of Korea.

Zitieren

APA

Lee, M., Kwak, H. G., Kim, H. J., Won, D. O., & Lee, S. W. (2023). SeriesSleepNet: an EEG time series model with partial data augmentation for automatic sleep stage scoring. Frontiers in Physiology, 14. https://doi.org/10.3389/fphys.2023.1188678

Vancouver

Lee M, Kwak HG, Kim HJ, Won DO, Lee SW. SeriesSleepNet: an EEG time series model with partial data augmentation for automatic sleep stage scoring. Frontiers in Physiology. 2023;14. doi:10.3389/fphys.2023.1188678

BibTeX
@article{Lee2023,
  author = {Lee, Minji and Kwak, Heon-Gyu and Kim, Hyeong-Jin and Won, Dong-Ok and Lee, Seong-Whan},
  title = {SeriesSleepNet: an EEG time series model with partial data augmentation for automatic sleep stage scoring},
  journal = {Frontiers in Physiology},
  year = {2023},
  volume = {14},
  doi = {10.3389/fphys.2023.1188678}
}
Kostenlos starten →