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

Autism Spectrum Disorder01:19

Autism Spectrum Disorder

981
Autism spectrum disorder (ASD) is a neurodevelopmental condition marked by persistent deficits in social communication and interaction alongside restrictive and repetitive behaviors or interests. ASD is sometimes accompanied by intellectual impairment.
These core symptoms manifest differently among individuals, ranging from mild to severe. The disorder's complexity extends beyond its clinical presentation, encompassing a diverse range of biological, cognitive, and sociocultural influences.
981

You might also read

Related Articles

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

Sort by
Same author

A comprehensive EEG dataset and performance assessment for Autism Spectrum Disorder.

Scientific reports·2025
Same author

DeSPPNet: A Multiscale Deep Learning Model for Cardiac Segmentation.

Diagnostics (Basel, Switzerland)·2025
Same author

Bioinformatics design of peptide binding to the human cardiac troponin I (cTnI) in biosensor development for myocardial infarction diagnosis.

PloS one·2024
Same author

The molecular interaction of six single-stranded DNA aptamers to cardiac troponin I revealed by docking and molecular dynamics simulation.

PloS one·2024
Same author

Transmission and Profile of COVID-19 in Children in North Sumatera, Indonesia.

Archives of Iranian medicine·2023
Same author

A Review on Multiscale-Deep-Learning Applications.

Sensors (Basel, Switzerland)·2022

Related Experiment Video

Updated: Jan 16, 2026

Conscious and Non-conscious Representations of Emotional Faces in Asperger's Syndrome
08:31

Conscious and Non-conscious Representations of Emotional Faces in Asperger's Syndrome

Published on: July 31, 2016

14.4K

Recognition of EEG Features in Autism Disorder Using SWT and Fisher Linear Discriminant Analysis.

Fahmi Fahmi1, Melinda Melinda2, Prima Dewi Purnamasari3

  • 1Department of Electrical Engineering, Universitas Sumatera Utara, Medan 20155, Indonesia.

Diagnostics (Basel, Switzerland)
|September 27, 2025
PubMed
Summary

This study introduces a novel EEG analysis pipeline using Stationary Wavelet Transform and Fisher's Linear Discriminant for accurate autism spectrum disorder (ASD) diagnosis, offering interpretable, band-specific insights.

Keywords:
Autism Spectrum Disorder (ASD)Fisher Linear Discriminant Analysis (FLDA)Stationary Wavelet Transform (SWT)confusion matrixelectroencephalogram (EEG)

More Related Videos

Electroencephalographic Signal Acquisition Framework for Neurodiverse: A Case Study of Dolphin-Assisted Therapy
07:21

Electroencephalographic Signal Acquisition Framework for Neurodiverse: A Case Study of Dolphin-Assisted Therapy

Published on: June 27, 2025

435
Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish
10:56

Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish

Published on: March 6, 2014

13.0K

Related Experiment Videos

Last Updated: Jan 16, 2026

Conscious and Non-conscious Representations of Emotional Faces in Asperger's Syndrome
08:31

Conscious and Non-conscious Representations of Emotional Faces in Asperger's Syndrome

Published on: July 31, 2016

14.4K
Electroencephalographic Signal Acquisition Framework for Neurodiverse: A Case Study of Dolphin-Assisted Therapy
07:21

Electroencephalographic Signal Acquisition Framework for Neurodiverse: A Case Study of Dolphin-Assisted Therapy

Published on: June 27, 2025

435
Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish
10:56

Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish

Published on: March 6, 2014

13.0K

Area of Science:

  • * Neuroscience
  • * Biomedical Engineering
  • * Machine Learning

Background:

  • * Diagnosing Autism Spectrum Disorder (ASD) using electroencephalography (EEG) is challenging due to signal non-stationarity, low signal-to-noise ratio (SNR), and limited dataset sizes.
  • * Existing methods often lack interpretability or require substantial computational resources, hindering clinical application in resource-constrained settings.

Purpose of the Study:

  • * To develop a compact and interpretable EEG analysis pipeline for ASD diagnosis.
  • * To leverage a shift-invariant Stationary Wavelet Transform (SWT) combined with Fisher's Linear Discriminant (FLDA) for robust feature extraction and classification.
  • * To provide band-level insights and subject-wise evaluation suitable for clinical settings.

Main Methods:

  • * EEG data from the KAU dataset (8 ASD, 8 controls) were processed using SWT (db4 wavelet).
  • * Features were extracted from specific frequency bands (γ, β, θ) corresponding to SWT levels 3, 4, and 6.
  • * FLDA was employed as a supervised projection method to create a low-dimensional discriminant subspace, followed by a linear decision rule.
  • * Performance was evaluated using a subject-wise 70/30 split, assessing accuracy, precision, recall, and F1 scores.

Main Results:

  • * The β band (Level 4) demonstrated the highest diagnostic performance with an accuracy, precision, recall, and F1 score of 0.95.
  • * The γ band achieved a performance of 0.92, and the θ band achieved 0.85.
  • * FLDA projection effectively maximized between-class separation, ensuring robust linear classification despite potential score overlap.

Conclusions:

  • * The proposed SWT-FLDA pipeline offers a stable and interpretable approach for ASD diagnosis from EEG, outperforming previous FLDA-only and wavelet-entropy-ANN methods.
  • * The method utilizes shift-invariant SWT to stabilize features and FLDA to address small-sample issues, providing clear, band-specific discriminative insights (β > γ/θ).
  • * This computationally efficient pipeline is reproducible, achieves competitive accuracy, and is suitable for low-resource clinical environments.