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

Automatic seizure detection in EEG using logistic regression and artificial neural network.

Ahmet Alkan1, Etem Koklukaya, Abdulhamit Subasi

  • 1Department of Electrical and Electronics Engineering, Kahramanmaras Sutcu Imam University, 46050-9 Kahramanmaraş, Turkey. aalkan2004@yahoo.com

Journal of Neuroscience Methods
|July 19, 2005
PubMed
Summary

This study compared artificial neural networks (ANNs) and logistic regression (LR) for classifying electroencephalogram (EEG) signals in absence seizures. ANNs demonstrated superior accuracy in detecting epileptiform discharges for epilepsy diagnosis.

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

Alzheimer's and Parkinson's Detection with Video-Based Hybrid Deep Learning from Brain MRI.

Journal of imaging informatics in medicine·2026
Same author

Electromyography Signal Classification With Artificial Intelligence for Detection of Neuromuscular Disorders Using a Large Clinically-Acquired Database.

Muscle & nerve·2025
Same author

Estimation of Total Hemoglobin (SpHb) from Facial Videos Using 3D Convolutional Neural Network-Based Regression.

Biosensors·2025
Same author

Identifying Risk Factors of Substance Use in Finland: A Machine Learning Approach.

Substance use & misuse·2025
Same author

Novel Preprocessing-Based Sequence for Comparative MR Cervical Lymph Node Segmentation.

Journal of clinical medicine·2025
Same author

A Novel NICU Sleep State Stratification: Multiperspective Features, Adaptive Feature Selection and Ensemble Model.

IEEE transactions on bio-medical engineering·2025

Area of Science:

  • * Neuroscience and Biomedical Engineering
  • * Signal Processing and Machine Learning

Background:

  • * Accurate detection of epileptiform discharges in electroencephalogram (EEG) signals is crucial for diagnosing epilepsy.
  • * Absence seizures present unique challenges for EEG analysis.

Purpose of the Study:

  • * To compare the performance of artificial neural networks (ANNs) and logistic regression (LR) for classifying EEG signals in patients with absence seizures.
  • * To evaluate the accuracy of these classification models in identifying epileptiform discharges.

Main Methods:

  • * EEG power spectra were computed using Multiple Signal Classification (MUSIC), Autoregressive (AR), and periodogram methods.
  • * Classifiers were developed using logistic regression (LR) and multilayer perceptron neural networks (MLPNN).

Related Experiment Videos

  • * Performance was assessed using Receiver Operating Characteristic (ROC) curves and scalar metrics.

    • Main Results:

    • * The MLPNN-based classifier significantly outperformed the LR-based classifier in accuracy.
    • * ANNs demonstrated higher precision in classifying EEG signals compared to traditional statistical methods.
    • * MLPNN achieved greater accuracy within the same patient group.

    Conclusions:

    • * Artificial neural networks, specifically MLPNN, offer a more accurate approach for classifying EEG signals in absence seizures compared to logistic regression.
    • * This finding supports the use of advanced machine learning techniques for improved epilepsy diagnosis.
    • * The study highlights the potential of ANNs in enhancing the detection of epileptiform discharges.