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

A Hybrid Deep Learning Framework with Supervised Contrastive Learning for Robust Seizure Detection in Long-Term EEG.

Haotian Li1, Weisen Lu1, Xiangwen Zhong1

  • 1School of Integrated Circuits, Shandong University, Jinan, 250100, P. R. China.

Journal of Medical Systems
|June 3, 2026
PubMed
Summary

Related Concept Videos

Seizures: Classification01:13

Seizures: Classification

Epilepsy is primarily characterized by unpredictable seizures, either provoked by an identifiable factor, such as injury or illness, or unprovoked, occurring spontaneously without apparent cause.
Seizures are typically classified into two main categories: focal and generalized seizures.
Focal Seizures
Focal seizures originate from specific regions of the brain. These seizures are further sub-classified into two types:
Seizures l: Introduction01:20

Seizures l: Introduction

Understanding seizures and epilepsy relies on key definitions that help in recognizing, classifying, and managing these disorders. These definitions provide a framework for recognizing, classifying, and managing seizure disorders.DefinitionsA seizure is a sudden, abnormal burst of electrical activity in the brain that can cause changes in awareness, movement, sensation, or behavior, depending on the area involved. Epilepsy is a chronic condition characterized by recurrent, unprovoked seizures,...

You might also read

Related Articles

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

Sort by
Same author

SHREC 2025: Protein surface shape retrieval including electrostatic potential.

Computers & graphics·2026
Same author

Treatment Patterns and Barriers to Care Among U.S. Adults With Co-Occurring Substance Use Disorder and Mental Illness.

The American journal of psychiatry·2026
Same author

Orbital-Engineered Sn/RuO<sub>2</sub> Nanocatalyst with Self-Regulating Electron Configuration for Durable Chlorine Evolution at Industrial Current Densities.

ACS applied materials & interfaces·2026
Same author

The role of macrophage-myofibroblast transition in the pathogenesis of multi-organ fibrosis.

Tissue & cell·2026
Same author

Correction: Time-dependent diffusion MRI for noninvasive molecular subtype differentiation and biological correlation in breast cancer: emphasizing the emerging three-tier HER2 classification.

Frontiers in oncology·2026
Same author

Discrete Wavelet Convolution for Learnable Time-Frequency Representation with Application to Seizure Prediction.

International journal of neural systems·2026
This summary is machine-generated.

This study introduces CNN-SwT, a deep learning model for automatic epileptic seizure detection from electroencephalogram (EEG) data. The framework achieves high accuracy, addressing challenges like data imbalance in clinical EEG analysis.

Area of Science:

  • Neuroscience
  • Artificial Intelligence
  • Biomedical Engineering

Background:

  • Automatic epileptic seizure detection from electroencephalogram (EEG) is vital for clinical efficiency.
  • Challenges include complex EEG dynamics and severe class imbalance in long-term data.

Purpose of the Study:

  • To develop an end-to-end hybrid deep learning framework for accurate and timely automatic seizure detection.
  • To address the critical challenge of class imbalance in long-term EEG data.

Main Methods:

  • Developed CNN-SwT, integrating Convolutional Neural Network (CNN) for local spatiotemporal features and Swin Transformer (SwT) for global dependencies.
  • Employed supervised contrastive learning to mitigate extreme data imbalance, replacing traditional cross-entropy loss.
Keywords:
Contrastive learningConvolutional Neural NetworkElectroencephalogramSeizure detectionSwin Transformer

Related Experiment Videos

Main Results:

  • Achieved 100% event-based sensitivity with 0.36/h False Discovery Rate (FDR) on the CHB-MIT database.
  • Attained 94.44% event-based sensitivity with 0.78/h FDR on the SH-SDU database.

Conclusions:

  • The CNN-SwT model demonstrates robust performance across different databases.
  • The framework shows significant potential for advancing clinical epileptic seizure detection.