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

You might also read

Related Articles

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

Sort by
Same author

Epileptic-Dyskinetic Encephalopathy in Snijders Blok-Campeau Syndrome: Expanding the Phenotypic Spectrum.

Movement disorders clinical practice·2026
Same author

Does genetic diagnosis influence long-term seizure and developmental outcomes in childhood developmental and epileptic encephalopathies? A longitudinal audit.

Seizure·2026
Same author

Impact of valproate discontinuation on seizure control in women of reproductive age.

Epileptic disorders : international epilepsy journal with videotape·2026
Same author

Neuroimaging spectrum of GATOR1-related epilepsy (GATORopathies).

Neuroradiology·2026
Same author

Do classical semiology ("5As") predict the post-operative seizure outcome in patients with temporal lobe epilepsy?

Epileptic disorders : international epilepsy journal with videotape·2026
Same author

Long term surgical outcome and its predictors in lesional posterior cortex epilepsy.

Epilepsy research·2026

Related Experiment Video

Updated: Jan 14, 2026

Cortical Source Analysis of High-Density EEG Recordings in Children
09:32

Cortical Source Analysis of High-Density EEG Recordings in Children

Published on: June 30, 2014

21.9K

Real-Time Classification for EEG Data in Children With ASD Using Deep Learning Techniques.

Lekshmylal P L1, Suresh Kumar E1, Ashalatha Radhakrishnan2

  • 1Department of Electronics and Communication Engineering, College of Engineering Trivandrum, APJ Abdul Kalam Technological University, Thiruvananthapuram, Kerala, India.

Developmental Neurobiology
|October 21, 2025
PubMed
Summary
This summary is machine-generated.

This study introduces a deep learning framework for real-time electroencephalography (EEG) classification in children with autism spectrum disorder (ASD), improving diagnostic accuracy. The hybrid CNN-LSTM model effectively analyzes complex EEG data for timely interventions.

Keywords:
autism spectrum disorderdeep learningelectroencephalography (EEG) datagrid search optimizationindependent component analysisshort‐time Fourier transform

More Related Videos

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants
11:14

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants

Published on: October 4, 2015

11.4K
Eye Tracking Young Children with Autism
09:03

Eye Tracking Young Children with Autism

Published on: March 27, 2012

46.4K

Related Experiment Videos

Last Updated: Jan 14, 2026

Cortical Source Analysis of High-Density EEG Recordings in Children
09:32

Cortical Source Analysis of High-Density EEG Recordings in Children

Published on: June 30, 2014

21.9K
A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants
11:14

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants

Published on: October 4, 2015

11.4K
Eye Tracking Young Children with Autism
09:03

Eye Tracking Young Children with Autism

Published on: March 27, 2012

46.4K

Area of Science:

  • Neuroscience and Artificial Intelligence
  • Developmental Neuroscience
  • Biomedical Engineering

Background:

  • Autism spectrum disorder (ASD) diagnosis and treatment are complex, requiring advanced methods to understand neurophysiological underpinnings.
  • Real-time electroencephalography (EEG) classification in children with ASD is challenging due to signal variability, hindering algorithm development.
  • Innovative deep learning approaches are needed to improve the accuracy and timeliness of ASD diagnosis through EEG analysis.

Purpose of the Study:

  • To develop and validate a deep learning framework for real-time EEG classification in children with ASD.
  • To enhance diagnostic accuracy and facilitate early interventions for ASD.
  • To address the challenges posed by EEG signal variability in children with ASD.

Main Methods:

  • A dataset of EEG recordings from 60 children (30 with ASD, 30 typically developing) was utilized.
  • Pre-processing involved segmentation, short-time Fourier transform (STFT), and independent component analysis (ICA) to remove noise and artifacts.
  • A hybrid convolutional neural network (CNN)-long short-term memory (LSTM) model was developed and optimized using grid search optimization (GSO).

Main Results:

  • The hybrid CNN-LSTM model achieved 87.5% accuracy, 85.0% precision, 90.0% recall, and 87.5% F1 score.
  • A baseline ResNet model showed slightly higher accuracy (89.1%) but lacked essential temporal modeling capabilities.
  • The CNN-LSTM model was favored for its superior ability to capture temporal dynamics crucial for EEG interpretation in ASD.

Conclusions:

  • The developed deep learning framework, particularly the hybrid CNN-LSTM model, shows significant promise for real-time EEG classification in children with ASD.
  • The model's ability to integrate spatial and temporal feature extraction enhances its utility for understanding neurophysiological mechanisms in ASD.
  • Future research directions include real-time feedback systems, mobile applications, and expanded longitudinal data analysis.