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

Classifying brain states and determining the discriminating activation patterns: Support Vector Machine on functional

Janaina Mourão-Miranda1, Arun L W Bokde, Christine Born

  • 1Siemens Corporate Technology, Information and Communications, Munich, Germany.

Neuroimage
|November 9, 2005
PubMed
Summary

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

Model-based analysis of stop-signal data reveals robust neural and clinical correlates of evidence accumulation but not inhibition.

Neuropsychopharmacology : official publication of the American College of Neuropsychopharmacology·2026
Same author

Bullying victimization and brain development: a longitudinal structural magnetic resonance imaging study from adolescence to early adulthood.

Translational psychiatry·2026
Same author

A longitudinal DNA methylation atlas and its link to brain structure and mental health.

Molecular psychiatry·2026
Same author

Digital Twin Brain simulation and manipulation of a functional brain network underlying mental illness.

bioRxiv : the preprint server for biology·2026
Same author

Dimensional Associations Between Conduct Problems and Brain Structure Across 18 International Cohorts in ENIGMA.

Journal of the American Academy of Child and Adolescent Psychiatry·2026
Same author

Mapping developmental transitions in mental health from mid- to late-adolescence: Concurrent and longitudinal links to cognition.

JCPP advances·2026

Support Vector Machine (SVM) effectively classifies brain states from functional MRI (fMRI) data, outperforming Fisher Linear Discriminant (FLD). SVM offers robust spatial maps for distinguishing brain activity during attention tasks.

Area of Science:

  • Neuroimaging
  • Machine Learning
  • Cognitive Neuroscience

Background:

  • Functional magnetic resonance imaging (fMRI) is crucial for understanding brain activity.
  • Multivariate pattern analysis (MVPA) offers advanced methods for decoding brain states.
  • Previous methods often rely on pre-selected spatial features, potentially limiting analysis.

Purpose of the Study:

  • To apply Support Vector Machine (SVM) for multivariate classification of brain states using whole fMRI volumes.
  • To compare the performance and robustness of SVM against Fisher Linear Discriminant (FLD).
  • To evaluate the overlap of SVM-derived discrimination maps with traditional General Linear Model (GLM) analysis.

Main Methods:

  • Support Vector Machine (SVM) algorithm applied to whole fMRI volumes.

Related Experiment Videos

  • Comparative analysis with Fisher Linear Discriminant (FLD) classifier.
  • Application to multisubject attention experiments (face matching, location matching).

    • Main Results:

    • SVM demonstrated superior classification performance compared to FLD.
    • SVM yielded more robust spatial discrimination maps.
    • SVM discrimination maps showed greater concordance with GLM analysis results.

    Conclusions:

    • SVM is a powerful tool for brain state classification from fMRI data without feature pre-selection.
    • SVM offers advantages in classification accuracy and map robustness over FLD.
    • The findings support SVM's utility in neuroimaging research for decoding cognitive states.