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 Video

Updated: Jul 16, 2026

STFEEG-Tool: A Spatial-Temporal-Frequency EEG Analysis Tool for Motor Imagery Brain-Computer Interfaces
05:36

STFEEG-Tool: A Spatial-Temporal-Frequency EEG Analysis Tool for Motor Imagery Brain-Computer Interfaces

Published on: March 10, 2026

Enhancing EEG based cognitive state classification using graph Fourier transform.

Shweta Sharma1, Ayushi Kotwal1, Rajneet Kaur Bijral1

  • 1Department of Computer Science & IT, University of Jammu, Jammu & Kashmir, India.

AIMS Neuroscience
|July 15, 2026
PubMed
Summary

Graph signal processing (GSP) offers a lightweight alternative for electroencephalography (EEG) cognitive state classification. GSP-based graph Fourier transform (GFT) features achieved 99% accuracy, outperforming raw signals.

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

Proton beam therapy in nonmetastatic rhabdomyosarcoma: Outcome, prognostic factors and the effect of timing of radiation therapy.

International journal of radiation oncology, biology, physics·2026
Same author

Post-Vaccination COVID-19 Infection among Health Care Workers: Description, Determinants, and Event-History Analysis.

Indian journal of community medicine : official publication of Indian Association of Preventive & Social Medicine·2026
Same author

Surveillance Outcomes in an Australian Cohort Undergoing Piecemeal Polypectomy for Conventional Adenomas and Serrated Lesions.

Digestive diseases and sciences·2026
Same author

Comment on "Industry guidance on container closure integrity strategies for difficult-to-test parenteral products (DTPs)".

Journal of pharmaceutical sciences·2026
Same author

Advance sensing of high energy explosive: A DFT-Based study of C<sub>5</sub>N framework performance.

Journal of molecular graphics & modelling·2026
Same author

Letter to the editor: Urinary incontinence is common among people attending pulmonary rehabilitation, yet pulmonary rehabilitation has a small effect on urinary symptoms: A multicenter prospective cohort study.

Pulmonology·2026

Area of Science:

  • Neuroscience
  • Signal Processing
  • Machine Learning

Background:

  • Deep learning models for electroencephalography (EEG) cognitive state classification require substantial computational resources and large datasets.
  • Graph Signal Processing (GSP) presents a promising, lightweight alternative by analyzing spatial dependencies across EEG channels.

Purpose of the Study:

  • To investigate the efficacy of GSP-based graph Fourier transform (GFT) features for cognitive state classification using EEG data.
  • To compare the performance of GFT features against raw EEG signals and evaluate various machine learning classifiers.

Main Methods:

  • Utilized the publicly available EEG Mental Arithmetic Task (EEGMAT) dataset.
  • Applied GSP-based GFT to extract spatial-spectral features, modeling EEG channels as graph nodes.
Keywords:
EEGSHAPgraph Fourier transform (GFT)graph signal processing (GSP)machine learning

More Related Videos

Microstate and Omega Complexity Analyses of the Resting-state Electroencephalography
06:40

Microstate and Omega Complexity Analyses of the Resting-state Electroencephalography

Published on: June 15, 2018

Related Experiment Videos

Last Updated: Jul 16, 2026

STFEEG-Tool: A Spatial-Temporal-Frequency EEG Analysis Tool for Motor Imagery Brain-Computer Interfaces
05:36

STFEEG-Tool: A Spatial-Temporal-Frequency EEG Analysis Tool for Motor Imagery Brain-Computer Interfaces

Published on: March 10, 2026

Microstate and Omega Complexity Analyses of the Resting-state Electroencephalography
06:40

Microstate and Omega Complexity Analyses of the Resting-state Electroencephalography

Published on: June 15, 2018

  • Employed 5-fold cross-validation and evaluated classifiers including Random Forest (RF), XGBoost (XGB), Decision Tree (DT), and Logistic Regression (LR).

    • Main Results:

    • GFT features demonstrated statistically significant improvements over raw EEG signals for classification.
    • Random Forest (RF) classifier achieved the highest accuracy, reaching approximately 99%.
    • Shapley Additive Explanations (SHAP) analysis indicated that frontal and central brain regions were key contributors to classification.

    Conclusions:

    • GSP-based GFT features provide an effective and computationally efficient method for EEG cognitive state classification.
    • The findings align with cognitive neuroscience principles, highlighting the importance of frontal and central brain activity.
    • This approach offers a viable alternative to resource-intensive deep learning models in EEG analysis.