Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

MFST-GCN: A Sleep Stage Classification Method Based on Multi-Feature Spatio-Temporal Graph Convolutional Network.

Huifu Li1, Xun Zhang1,2,3, Ke Guo1

  • 1School of Computer and Artificial Intelligence, Beijing Technology and Business University, Beijing 100048, China.

Brain Sciences
|February 27, 2026
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

Stages of Sleep01:22

Stages of Sleep

1.6K
Sleep progresses through distinct stages, each characterized by specific brain wave patterns and physiological responses ranging from wakefulness to stages of non-rapid eye movement, known as non-REM, to rapid eye movement, referred to as REM. Understanding these stages helps in recognizing how sleep supports various bodily and cognitive functions.
Before sleep begins, in wakefulness, the brain exhibits primarily beta waves, which are high in frequency and low in amplitude, indicating alertness...
1.6K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

High-Precision Microscale Particulate Matter Prediction in Diverse Environments Using a Long Short-Term Memory Neural Network and Street View Imagery.

Environmental science & technology·2024
Same author

A Multi-Scale and Multi-Level Fusion Approach for Deep Learning-Based Liver Lesion Diagnosis in Magnetic Resonance Images with Visual Explanation.

Life (Basel, Switzerland)·2021
Same author

Multi-Scale Aggregation Graph Neural Networks Based on Feature Similarity for Semi-Supervised Learning.

Entropy (Basel, Switzerland)·2021
Same author

An Interpretation Architecture for Deep Learning Models with the Application of COVID-19 Diagnosis.

Entropy (Basel, Switzerland)·2021
Same author

Spatiotemporal Characteristics and Driving Factors of Black Carbon in Augsburg, Germany: Combination of Mobile Monitoring and Street View Images.

Environmental science & technology·2020
Same journal

Anterior Cingulate Cortex Mediates State-Dependent Prioritization of Distressed Conspecifics.

Brain sciences·2026
Same journal

Hemispherotomy for Pediatric Post-Traumatic Epilepsy.

Brain sciences·2026
Same journal

When Robots Learn: Artificial Intelligence and the Next Human-Centered Era of Neurorehabilitation.

Brain sciences·2026
Same journal

The Association Between Changes in White Matter Microstructure and Cognitive Function in Older Adults with Mild Cognitive Impairment.

Brain sciences·2026
Same journal

Beyond Ventricular Enlargement: Multimodal MRI Assessment Improves Surgical Decision-Making in Normal Pressure Hydrocephalus.

Brain sciences·2026
Same journal

The Effects of Personalized Observation, Execution, and Mental Imagery (POEM) Therapy in Logopenic Primary Progressive Aphasia: A Telepractice-Based Single-Case Study.

Brain sciences·2026
See all related articles

This study introduces a novel graph deep learning framework, MFST-GCN, for accurate sleep stage classification. It effectively models brain signal time-lags and regional variations, significantly improving sleep disorder diagnosis.

Area of Science:

  • Neuroscience
  • Artificial Intelligence
  • Signal Processing

Background:

  • Accurate sleep stage classification is crucial for sleep quality assessment and sleep disorder diagnosis.
  • Current deep learning models struggle with complex brain dynamics, including neural signal time-lags and regional activation differences.

Purpose of the Study:

  • To develop an advanced deep learning framework, MFST-GCN, for improved sleep stage classification.
  • To explicitly model neurobiological phenomena like time-lag effects and regional variations in brain activity.

Main Methods:

  • Proposed the MFST-GCN, a graph-based deep learning framework with three modules: DDFCM, MMFEN, and ASTGCN.
  • DDFCM models time-varying functional connectivity using dual-scale correlations (1s and 5s).
  • MMFEN extracts frequency-specific EEG features, and ASTGCN integrates spatio-temporal information with attention mechanisms.
Keywords:
graph connection networkmulti-scale attention networksleep functional connectivitysleep stage classification

Related Experiment Videos

Main Results:

  • Achieved high F1-scores of 0.823 on ISRUC-S1 and 0.835 on ISRUC-S3 datasets.
  • Outperformed existing state-of-the-art methods in sleep stage classification.
  • Ablation studies confirmed the significant contribution of time-lag modeling.

Conclusions:

  • The MFST-GCN framework demonstrates superior performance in sleep stage classification.
  • Explicit modeling of time-lag effects is vital for accurately distinguishing transitional sleep stages.
  • This approach enhances the potential for improved diagnosis of sleep disorders.