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 Concept Videos

Seizures: Classification01:13

Seizures: Classification

802
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:
802
Epilepsy and Seizures: Overview01:24

Epilepsy and Seizures: Overview

480
Epilepsy is a chronic neurological disease marked by recurrent, unpredictable seizures. These seizures are caused by abnormal electrical discharges in the brain, leading to behavior, sensation, or consciousness alterations. They can also cause transient impairment of awareness, interfering with daily activities.
Various factors can trigger epilepsy, including genetic factors, brain damage, metabolic causes, and unknown etiology. Diagnosis of epilepsy involves electroencephalography (EEG), which...
480

You might also read

Related Articles

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

Sort by
Same author

The role of DNMT3B, GSK-3β and GJA3 in lens epithelial cell apoptosis and age-related cataract.

BMC ophthalmology·2026
Same author

Adaptive Multiscale Spatiotemporal Mixing Network for Multiview Seizure Detection.

International journal of neural systems·2026
Same author

Attention-based Multimodal Spatiotemporal Enhanced Interaction Network For Major Depressive Disorder Detection.

IEEE journal of biomedical and health informatics·2026
Same author

Polydopamine-coated TiO<sub>2</sub> nanoparticles endow pectin films with desirable physical and antibacterial properties for preserving perishable fruits.

International journal of biological macromolecules·2026
Same author

Histogram Analysis of Ultrasound Localization Microscopy for Predicting Isocitrate Dehydrogenase Status in Rat Glioblastoma.

Ultrasound in medicine & biology·2026
Same author

Contrast-free super-resolution ultrasound imaging based on two-stage diffusion probabilistic models.

Ultrasonics·2026

Related Experiment Video

Updated: Oct 26, 2025

Network Analysis of Foramen Ovale Electrode Recordings in Drug-resistant Temporal Lobe Epilepsy Patients
09:32

Network Analysis of Foramen Ovale Electrode Recordings in Drug-resistant Temporal Lobe Epilepsy Patients

Published on: December 18, 2016

12.6K

EEG-Based Seizure detection using linear graph convolution network with focal loss.

Yanna Zhao1, Changxu Dong1, Gaobo Zhang1

  • 1School of Information Science and Engineering, Shandong Normal University, Jinan 250358, P.R. China.

Computer Methods and Programs in Biomedicine
|July 27, 2021
PubMed
Summary

This study introduces a novel Linear Graph Convolutional Network (LGCN) for enhanced seizure detection from Electroencephalography (EEG) signals, achieving high accuracy by considering spatial relationships.

Keywords:
Electroencephalography (EEG)Focal lossLinear graph convolution networkPearson correctionSeizure detection

More Related Videos

Brain Source Imaging in Preclinical Rat Models of Focal Epilepsy using High-Resolution EEG Recordings
08:20

Brain Source Imaging in Preclinical Rat Models of Focal Epilepsy using High-Resolution EEG Recordings

Published on: June 6, 2015

15.5K
Equipment Setup and Artifact Removal for Simultaneous Electroencephalogram and Functional Magnetic Resonance Imaging for Clinical Review in Epilepsy
10:23

Equipment Setup and Artifact Removal for Simultaneous Electroencephalogram and Functional Magnetic Resonance Imaging for Clinical Review in Epilepsy

Published on: June 23, 2023

2.3K

Related Experiment Videos

Last Updated: Oct 26, 2025

Network Analysis of Foramen Ovale Electrode Recordings in Drug-resistant Temporal Lobe Epilepsy Patients
09:32

Network Analysis of Foramen Ovale Electrode Recordings in Drug-resistant Temporal Lobe Epilepsy Patients

Published on: December 18, 2016

12.6K
Brain Source Imaging in Preclinical Rat Models of Focal Epilepsy using High-Resolution EEG Recordings
08:20

Brain Source Imaging in Preclinical Rat Models of Focal Epilepsy using High-Resolution EEG Recordings

Published on: June 6, 2015

15.5K
Equipment Setup and Artifact Removal for Simultaneous Electroencephalogram and Functional Magnetic Resonance Imaging for Clinical Review in Epilepsy
10:23

Equipment Setup and Artifact Removal for Simultaneous Electroencephalogram and Functional Magnetic Resonance Imaging for Clinical Review in Epilepsy

Published on: June 23, 2023

2.3K

Area of Science:

  • Neuroscience
  • Artificial Intelligence
  • Biomedical Engineering

Background:

  • Epilepsy affects 70 million worldwide, characterized by abnormal brain neuron discharge.
  • Electroencephalography (EEG) based seizure detection is advancing, but often overlooks inter-channel spatial relationships.
  • Existing methods may fail to capture the complex spatial dynamics inherent in EEG signals.

Purpose of the Study:

  • To propose a novel seizure detection model using a Linear Graph Convolutional Network (LGCN).
  • To enhance feature embedding of raw EEG signals by incorporating spatial relationships between channels.
  • To address the data imbalance issue common in seizure detection.

Main Methods:

  • Constructed an input graph using the Pearson correlation matrix of raw EEG signals to represent spatial relationships.
  • Employed a graph neural network architecture with LGCN for feature extraction.
  • Utilized focal loss to manage data imbalance during training.
  • Implemented a softmax layer for final seizure/non-seizure classification.

Main Results:

  • Achieved high performance on the CHB-MIT dataset.
  • Reported seizure detection accuracy of 99.30%, specificity of 98.82%, sensitivity of 99.43%, F1 score of 98.73%, and AUC of 98.57%.
  • Demonstrated superior performance compared to state-of-the-art methods.

Conclusions:

  • The proposed LGCN model offers superior performance for EEG seizure detection.
  • The end-to-end model eliminates the need for manually designed features.
  • Effective handling of imbalanced data makes it suitable for real-world seizure detection applications.