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

K-complex detection using multi-layer perceptrons and recurrent networks

B H Jansen1, P R Desai

  • 1Department of Electrical and Computer Engineering, University of Houston, TX 77204-4793.

International Journal of Bio-Medical Computing
|November 1, 1994
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

Environmental factors shaping the gut microbiome in a Dutch population.

Nature·2022
Same author

Genetic Risk Scores Identify Genetic Aetiology of Inflammatory Bowel Disease Phenotypes.

Journal of Crohn's & colitis·2020
Same author

Classification of sleep patterns by means of markov modeling and correspondence analysis.

IEEE transactions on pattern analysis and machine intelligence·2011
Same author

A neural network model of normal and abnormal auditory information processing.

Neural networks : the official journal of the International Neural Network Society·2011
Same author

Monitoring and real-time interpretation I.

Methods of information in medicine·2011
Same author

Histamine H4 receptor: a novel therapeutic target for immune and allergic responses.

Mini reviews in medicinal chemistry·2010
Same journal

Commentary on a futuristic model of patient record systems and telemedicine.

International journal of bio-medical computing·1996
Same journal

Nonlinear eye movement detection method for drowsiness studies.

International journal of bio-medical computing·1996
Same journal

Segmentation of auditory brainstem response signals.

International journal of bio-medical computing·1996
Same journal

A comparison of neural network and Bayes recognition approaches in the evaluation of the brainstem trigeminal evoked potentials in multiple sclerosis.

International journal of bio-medical computing·1996
Same journal

Methodology for using the UMLS as a background knowledge for the description of surgical procedures.

International journal of bio-medical computing·1996
Same journal

An MLP-based model for identifying qEEG in depression.

International journal of bio-medical computing·1996
See all related articles

This study explored using neural networks for detecting K-complexes in electroencephalograms (EEGs). Both multi-layer perceptrons and Elman networks performed well on simulated data but failed on actual EEG signals.

Area of Science:

  • Neuroscience
  • Computational Neuroscience
  • Signal Processing

Background:

  • Electroencephalograms (EEGs) are crucial for diagnosing neurological conditions.
  • Identifying specific waveforms like K-complexes is vital for sleep stage analysis and clinical interpretation.
  • Automated detection of EEG waveforms can improve efficiency and consistency in analysis.

Purpose of the Study:

  • To evaluate the feasibility of using a multi-layer perceptron (MLP) and an Elman recurrent neural network (RNN) for detecting K-complexes in EEG signals.
  • To assess the performance of these networks irrespective of the waveform's location within the signal segment.
  • To investigate the reasons behind the networks' performance on simulated versus real-world EEG data.

Main Methods:

  • Simulated and actual electroencephalogram (EEG) data were used for experimentation.

Related Experiment Videos

  • A multi-layer perceptron (MLP) utilized magnitude and/or phase values from 10-second EEG intervals as input.
  • An Elman recurrent neural network (RNN) processed digitized EEG data samples directly.

    • Main Results:

    • Both the multi-layer perceptron (MLP) and Elman recurrent neural network (RNN) demonstrated effective performance on simulated EEG data.
    • Neither network achieved satisfactory performance when applied to actual electroencephalogram (EEG) recordings.
    • The study identified discrepancies in network performance between artificial and real-world biological signals.

    Conclusions:

    • While neural networks show promise for EEG waveform detection using simulated data, their direct application to complex, real-world EEG signals requires further refinement.
    • The differences in performance highlight the challenges posed by the inherent variability and noise in actual EEG recordings.
    • Further research is needed to adapt and improve these computational models for reliable clinical application in electroencephalogram (EEG) analysis.