EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MM-SleepNet: An Automatic Sleep Staging Network Based on Modal Re-Weighting and Mamba

Bin Li iD, Aolin Lin, Yonghan Zhang, Zhuang Li iD

Sensors · 30.10.2026 · 26 (21) · 6872

DOI: 10.3390/s26216872 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 30.10.2026. Verfasst von Bin Li und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science, Northeast Electric Power University, Jilin 132012, China. Hauptthemen laut MEDLINE: Sleep Stages, Polysomnography. Die Arbeit nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Key Laboratory of Intelligent Rehabilitation and Barrier-free for the Disabled (Changchun Univer-sity).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Sleep staging is the key step in sleep quality assessment and sleep disorder diagnosis. In clinical practice, doctors usually use polysomnography (PSG) to stage sleep. PSG contains physiological signals such as electroencephalography (EEG) and electrooculography (EOG) and is divided into continuous epochs of fixed duration. In order to achieve more efficient and accurate automatic interpretation of PSG, this paper proposes MM-SleepNet, an automatic sleep staging network based on modal re-weighting and Mamba. MM-SleepNet divides each epoch into several overlapping patches and uses a newly designed patch feature extractor to extract the features of each patch, in order to solve the problem of key waveforms in the patch being obscured by non-key waveforms throughout the epoch. Afterward, MM-SleepNet calculates the importance of different signals on patches at the same time point through a dynamic re-weighting module. MM-SleepNet uses a bidirectional Mamba encoder that considers positional encoding to learn contextual information across epochs to adapt to the transition patterns between sleep stages. The experimental results on the Sleep-EDF and ISRUC datasets show that the proposed MM-SleepNet outperforms state-of-the-art methods. In addition, ablation experiments have demonstrated the effectiveness of various modules in MM-SleepNet.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Sleep StagesPolysomnographyHumansElectroencephalographySignal Processing, Computer-AssistedElectrooculographyAlgorithms

Stichwörter der Autor:innen

MambaPSG recordingsdeep learningmodal re-weightingsleep staging

Autor:innen und Institutionen

  • School of Computer Science, Northeast Electric Power University, Jilin 132012, China.
  • School of Mathematical and Computer Sciences, Heriot-Watt University, Edinburgh EH14 4AS, UK.

ORCID-Profile: Bin Li, Zhuang Li

Förderung

  • Key Laboratory of Intelligent Rehabilitation and Barrier-free for the Disabled (Changchun Univer-sity)

Zitieren

APA

Li, B., Lin, A., Zhang, Y., & Li, Z. (2026). MM-SleepNet: An Automatic Sleep Staging Network Based on Modal Re-Weighting and Mamba. Sensors, 26(21), 6872. https://doi.org/10.3390/s26216872

Vancouver

Li B, Lin A, Zhang Y, Li Z. MM-SleepNet: An Automatic Sleep Staging Network Based on Modal Re-Weighting and Mamba. Sensors. 2026;26(21):6872. doi:10.3390/s26216872

BibTeX
@article{Li2026,
  author = {Li, Bin and Lin, Aolin and Zhang, Yonghan and Li, Zhuang},
  title = {MM-SleepNet: An Automatic Sleep Staging Network Based on Modal Re-Weighting and Mamba},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {21},
  pages = {6872},
  doi = {10.3390/s26216872}
}
Kostenlos starten →