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 Video

Updated: May 28, 2026

Interictal High Frequency Oscillations Detected with Simultaneous Magnetoencephalography and Electroencephalography as Biomarker of Pediatric Epilepsy
10:22

Interictal High Frequency Oscillations Detected with Simultaneous Magnetoencephalography and Electroencephalography as Biomarker of Pediatric Epilepsy

Published on: December 6, 2016

Comparative machine learning for accurate EEG-based epileptic seizure state classification using sub-band analysis.

Esraa Omran1, Amro A Nour2, Kosai Dabbour3

  • 1Computer Science Department, Gulf University of Science and Technology, Mubarak Al-Abdullah, Kuwait.

Journal of Medical Engineering & Technology
|May 27, 2026
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

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

Sort by
Same author

RETRACTED: Enhancing IoT cybersecurity through lean-based hybrid feature selection and ensemble learning: A visual analytics approach to intrusion detection.

PloS one·2025
Same author

Rule-Based Detection of False Data Injections Attacks against Optimal Power Flow in Power Systems.

Sensors (Basel, Switzerland)·2021
Same author

BioNetApp: An interactive visual data analysis platform for molecular expressions.

PloS one·2019
Same author

Healthcare chains - enabling application and data privacy controls for healthcare information systems.

Studies in health technology and informatics·2010

Machine learning models effectively classify epileptic seizure states from EEG data. Tree-based algorithms like XGBoost and Random Forest showed the best performance in this comparative study.

Area of Science:

  • Neuroscience
  • Machine Learning
  • Signal Processing

Background:

  • Epileptic seizure identification from electroencephalogram (EEG) signals is crucial for clinical management.
  • Developing automated tools for EEG-based seizure state classification can enhance diagnostic accuracy and patient monitoring.

Purpose of the Study:

  • To compare the performance of various machine learning algorithms for classifying EEG-based epileptic seizure states.
  • To evaluate the effectiveness of sub-band analysis and statistical descriptors for EEG seizure detection.

Main Methods:

  • EEG signals from the Bonn University dataset were decomposed into delta, theta, alpha, beta, and gamma frequency bands.
  • Lightweight statistical descriptors were extracted from each sub-band.
  • Classifiers including SVM, Random Forest, XGBoost, CatBoost, MLP, k-NN, and Logistic Regression were trained and evaluated.
Keywords:
EEG signal analysisEpileptic seizure classificationictal/interictal EEGmachine learning classifierssub-band analysis

More Related Videos

Microstate and Omega Complexity Analyses of the Resting-state Electroencephalography
06:40

Microstate and Omega Complexity Analyses of the Resting-state Electroencephalography

Published on: June 15, 2018

Related Experiment Videos

Last Updated: May 28, 2026

Interictal High Frequency Oscillations Detected with Simultaneous Magnetoencephalography and Electroencephalography as Biomarker of Pediatric Epilepsy
10:22

Interictal High Frequency Oscillations Detected with Simultaneous Magnetoencephalography and Electroencephalography as Biomarker of Pediatric Epilepsy

Published on: December 6, 2016

Microstate and Omega Complexity Analyses of the Resting-state Electroencephalography
06:40

Microstate and Omega Complexity Analyses of the Resting-state Electroencephalography

Published on: June 15, 2018

Main Results:

  • Tree-based models, specifically XGBoost, CatBoost, and Random Forest, demonstrated superior performance in multi-class EEG seizure state classification.
  • Performance was assessed using metrics such as ROC analysis, precision, recall, F1-score, and accuracy.

Conclusions:

  • Machine learning, particularly tree-based methods, shows significant potential for accurate EEG-based epileptic seizure state classification.
  • Further validation on larger, diverse datasets (e.g., CHB-MIT, Siena Scalp EEG) is necessary for real-world clinical deployment.