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

Automated seizure detection using a self-organizing neural network

A J Gabor1, R R Leach, F U Dowla

  • 1Department of Neurology, University of California, Davis Medical Center, Sacramento 95817, USA. ajgabor@ucdavis.edu

Electroencephalography and Clinical Neurophysiology
|September 1, 1996
PubMed
Summary
This summary is machine-generated.

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

Achievement of Target Gain Larger than Unity in an Inertial Fusion Experiment.

Physical review letters·2024
Same author

Lawson Criterion for Ignition Exceeded in an Inertial Fusion Experiment.

Physical review letters·2022
Same author

Optimal field-scale groundwater remediation using neural networks and the genetic algorithm.

Environmental science & technology·2011
Same author

Seizure detection using a self-organizing neural network: validation and comparison with other detection strategies.

Electroencephalography and clinical neurophysiology·1998
Same author

Enhancement of the amplitude of somatosensory evoked potentials following magnetic pulse stimulation of the human brain.

Electroencephalography and clinical neurophysiology·1993
Same author

Automated interictal EEG spike detection using artificial neural networks.

Electroencephalography and clinical neurophysiology·1992

Automated seizure detection using self-organizing map (SOM) neural networks (NN) achieved 90% accuracy. Enhancing sensitivity increased detection to 98%, demonstrating a promising approach for epilepsy monitoring.

Area of Science:

  • Neuroscience
  • Artificial Intelligence
  • Signal Processing

Background:

  • Epilepsy monitoring relies on accurate seizure detection from electroencephalogram (EEG) data.
  • Automated seizure detection systems aim to improve efficiency and consistency in clinical practice.
  • Traditional methods often struggle with the complexity and variability of EEG signals.

Purpose of the Study:

  • To develop and evaluate an automated seizure detection algorithm using a self-organizing map (SOM) neural network (NN).
  • To assess the algorithm's performance in detecting seizures from long-term scalp EEG recordings.
  • To investigate the utility of wavelet transform and contextual features in enhancing detection accuracy.

Main Methods:

  • Utilized a SOM neural network with unsupervised training on 98 seizure examples from 24 long-term EEG recordings.

Related Experiment Videos

  • Employed wavelet transform to create time-frequency representations (spectrograms) of EEG epochs.
  • Integrated rule-based contextual features with NN outputs for seizure detection.

    • Main Results:

    • The algorithm detected 90% (56/62) of seizures with an average of 0.71 +/- 0.79 false positives per hour.
    • Increasing detection sensitivity resulted in 98% seizure detection.
    • False positive rates remained below 1.0 per hour for most records.

    Conclusions:

    • The combination of rule-based contextual criteria and unsupervised NN training for time-frequency pattern recognition shows significant promise for automated seizure detection.
    • This approach offers a robust method for analyzing complex EEG data.
    • Further development could lead to improved epilepsy diagnosis and patient management.