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

Shared genetic architecture between Alzheimer's disease and brain morphology.

Alzheimer's research & therapy·2026
Same author

Trans-ethnic estimation and implications of genetic impact on continuous glycemic profiles.

Cell discovery·2026
Same author

Cost-effectiveness of DPYD genotyping prior to fluoropyrimidine-based treatment for colorectal cancer in Wales.

British journal of clinical pharmacology·2026
Same author

Local chemoarchitecture explains widespread lower cortical thickness associated with clinical high risk for psychosis.

Molecular psychiatry·2026
Same author

Human induced pluripotent stem cell-derived microglia with 1q21.1 deletion and duplication exhibit aberrant inflammatory response.

Genes & diseases·2026
Same author

A Feasibility Study of Navigating Emotional States Using Real-Time Representational Similarity Analysis fMRI Neurofeedback.

International journal of neural systems·2026
Same journal

UniOCTSeg++: Refined Hierarchical Prompt Strategy and Bi-directional Progressive Consistency Learning for Universal Retinal Layer Segmentation in OCT.

IEEE transactions on medical imaging·2026
Same journal

Volumetric Functional Ultrasound Imaging in Macaques.

IEEE transactions on medical imaging·2026
Same journal

MUST: Multi-style virtual staining with incomplete pairs.

IEEE transactions on medical imaging·2026
Same journal

BrainCL: Transformer-Based Brain Network Contrastive Learning with Multi-Order Topology and Salience Masking.

IEEE transactions on medical imaging·2026
Same journal

LLM-enhanced Neuron Segmentation and Reconstruction in Complex Mouse Brain Images.

IEEE transactions on medical imaging·2026
Same journal

Matrixed-Spectrum Decomposition Accelerated Linear Boltzmann Transport Equation Solver for Fast Scatter Correction in Multi-Spectral CT.

IEEE transactions on medical imaging·2026
See all related articles

Related Experiment Video

Updated: Jun 16, 2026

Simultaneous Data Collection of fMRI and fNIRS Measurements Using a Whole-Head Optode Array and Short-Distance Channels
08:19

Simultaneous Data Collection of fMRI and fNIRS Measurements Using a Whole-Head Optode Array and Short-Distance Channels

Published on: October 20, 2023

Random subspace ensembles for FMRI classification.

Ludmila I Kuncheva1, Juan J Rodriguez, Catrin O Plumpton

  • 1School of Computer Science, Bangor University, LL57 1UT Bangor, U.K. l.i.kuncheva@bangor.ac.uk

IEEE Transactions on Medical Imaging
|February 5, 2010
PubMed
Summary
This summary is machine-generated.

The random subspace (RS) ensemble method effectively classifies functional magnetic resonance imaging (fMRI) brain images. RS, using support vector machines (SVM), surpasses other machine learning ensembles for fMRI data analysis.

More Related Videos

Using Informational Connectivity to Measure the Synchronous Emergence of fMRI Multi-voxel Information Across Time
07:12

Using Informational Connectivity to Measure the Synchronous Emergence of fMRI Multi-voxel Information Across Time

Published on: July 1, 2014

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
14:27

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

Related Experiment Videos

Last Updated: Jun 16, 2026

Simultaneous Data Collection of fMRI and fNIRS Measurements Using a Whole-Head Optode Array and Short-Distance Channels
08:19

Simultaneous Data Collection of fMRI and fNIRS Measurements Using a Whole-Head Optode Array and Short-Distance Channels

Published on: October 20, 2023

Using Informational Connectivity to Measure the Synchronous Emergence of fMRI Multi-voxel Information Across Time
07:12

Using Informational Connectivity to Measure the Synchronous Emergence of fMRI Multi-voxel Information Across Time

Published on: July 1, 2014

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
14:27

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

Area of Science:

  • Neuroimaging
  • Machine Learning
  • Pattern Recognition

Background:

  • Functional magnetic resonance imaging (fMRI) classification presents challenges due to high feature-to-instance ratios.
  • Existing pattern recognition and machine learning methods require adaptation for fMRI data.

Purpose of the Study:

  • To investigate the efficacy of the random subspace (RS) ensemble method for fMRI image classification.
  • To establish guidelines for optimizing RS parameters: ensemble size and feature sample size.

Main Methods:

  • The random subspace (RS) method, which builds base classifiers on feature subsets.
  • Development of three criteria (usability, important feature coverage, diversity) to optimize RS parameters.
  • Testing RS with support vector machines (SVM) as base classifiers on three fMRI datasets.

Main Results:

  • RS with SVM base classifiers demonstrated superior performance compared to single classifiers and other ensembles (bagging, AdaBoost, random forest, rotation forest).
  • Kappa-error diagrams were utilized to analyze the performance and success of the RS method.
  • The closest performing methods were single SVM and bagging of SVM classifiers.

Conclusions:

  • The random subspace (RS) ensemble method is a highly suitable and effective approach for fMRI classification.
  • Optimizing RS parameters using feature set usability, important feature coverage, and diversity enhances classification accuracy.
  • RS offers a robust solution for the high-dimensional challenges in fMRI data analysis.