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

Arteries of the Lower Limbs01:24

Arteries of the Lower Limbs

181
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...
181

You might also read

Related Articles

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

Sort by
Same author

PG-MCTFormer: A Prior-Guided Multi-Scale Convolutional Transformer for Interpretable Motor Imagery EEG Classification.

Biomimetics (Basel, Switzerland)·2026
Same authorSame journal

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

International journal of neural systems·2026
Same author

Multiscale Cosine Convolution Neural Network for Robust and Interpretable Epileptic EEG Detection.

Biosensors·2026
Same author

A Novel Morlet Convolutional Neural Network.

International journal of neural systems·2025
Same author

Efficient Seizure Detection by Complementary Integration of Convolutional Neural Network and Vision Transformer.

International journal of neural systems·2025
Same author

Epileptic Seizure Prediction Using Spatiotemporal Feature Fusion on EEG.

International journal of neural systems·2024

Related Experiment Video

Updated: Jun 11, 2025

Author Spotlight: Unraveling Seizure Dynamics and Novel Therapeutics for Status Epilepticus Using CMOS High-Density Microelectrode Array Systems
06:28

Author Spotlight: Unraveling Seizure Dynamics and Novel Therapeutics for Status Epilepticus Using CMOS High-Density Microelectrode Array Systems

Published on: September 27, 2024

2.2K

A Lightweight Convolutional Neural Network-Reformer Model for Efficient Epileptic Seizure Detection.

Haozhou Cui1,2, Xiangwen Zhong1,2, Haotian Li1,2

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

International Journal of Neural Systems
|September 30, 2024
PubMed
Summary
This summary is machine-generated.

A new Convolutional Neural Network-Reformer (CNN-Reformer) model offers real-time epileptic seizure detection from EEG data. This efficient system significantly improves diagnostic speed and accuracy for epilepsy treatment.

Keywords:
ElectroencephalogramReformerconvolutional neural networklocality sensitive hashing attentionseizure detection

More Related Videos

Long-term Continuous EEG Monitoring in Small Rodent Models of Human Disease Using the Epoch Wireless Transmitter System
08:43

Long-term Continuous EEG Monitoring in Small Rodent Models of Human Disease Using the Epoch Wireless Transmitter System

Published on: July 21, 2015

25.5K
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.8K

Related Experiment Videos

Last Updated: Jun 11, 2025

Author Spotlight: Unraveling Seizure Dynamics and Novel Therapeutics for Status Epilepticus Using CMOS High-Density Microelectrode Array Systems
06:28

Author Spotlight: Unraveling Seizure Dynamics and Novel Therapeutics for Status Epilepticus Using CMOS High-Density Microelectrode Array Systems

Published on: September 27, 2024

2.2K
Long-term Continuous EEG Monitoring in Small Rodent Models of Human Disease Using the Epoch Wireless Transmitter System
08:43

Long-term Continuous EEG Monitoring in Small Rodent Models of Human Disease Using the Epoch Wireless Transmitter System

Published on: July 21, 2015

25.5K
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.8K

Area of Science:

  • Biomedical Engineering
  • Computational Neuroscience
  • Artificial Intelligence

Background:

  • Epileptic seizures require timely diagnosis and treatment, making automatic detection systems crucial for clinical practice.
  • Existing methods for electroencephalogram (EEG) based seizure detection often face challenges with computational efficiency and real-time performance on long-term recordings.

Purpose of the Study:

  • To develop a novel, lightweight model named Convolutional Neural Network-Reformer (CNN-Reformer) for reliable, real-time automatic detection of epileptic seizures from long-term EEG signals.
  • To enhance the computational efficiency and real-time capabilities of EEG-based seizure detection systems.

Main Methods:

  • The proposed CNN-Reformer model integrates a Data Reshaping (DR) module and an Efficient Attention and Concentration (EAC) module.
  • EEG signals are preprocessed using Discrete Wavelet Transform (DWT) for filtering, followed by DR for feature compression and EAC for feature extraction and classification.
  • Post-processing techniques including sliding window averaging, thresholding, and collar methods are applied to minimize false detections.

Main Results:

  • On the CHB-MIT dataset, the model achieved high segment-based performance (sensitivity 97.57%, accuracy 98.09%, specificity 98.11%) and event-based performance (sensitivity 96.81%, FDR 0.27/h, latency 17.81s).
  • On the SH-SDU dataset, segment-based results included sensitivity of 94.51%, specificity of 92.83%, and accuracy of 92.81%, with event-based sensitivity at 94.11%.
  • The model demonstrated exceptional computational speed, processing 1 hour of multi-channel EEG in an average of 1.92 seconds.

Conclusions:

  • The CNN-Reformer model presents a computationally efficient and high-performing solution for real-time epileptic seizure detection.
  • Its ability to maintain accuracy while reducing computational load highlights its potential for practical clinical application in epilepsy management.