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

Matrix-Weighted Networks for Modeling Multidimensional Dynamics: Theoretical Foundations and Applications to Network Coherence.

Physical review letters·2025
Same author

Swarm systems as a platform for open-ended evolutionary dynamics.

Philosophical transactions. Series A, Mathematical, physical, and engineering sciences·2025
Same author

Self-Reproduction and Evolution in Cellular Automata: 25 Years After Evoloops.

Artificial life·2024
Same author

Editorial: Special Issue "The Distributed Ghost"-Cellular Automata, Distributed Dynamical Systems, and Their Applications to Intelligence.

Artificial life·2024
Same author

Collective group drift in a partial-differential-equation-based opinion dynamics model with biased perception kernels.

Physical review. E·2024
Same author

GaitNet+ARL: A Deep Learning Algorithm for Interpretable Gait Analysis of Chronic Ankle Instability.

IEEE journal of biomedical and health informatics·2024

Related Experiment Video

Updated: Mar 13, 2026

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

16.4K

Brain response pattern identification of fMRI data using a particle swarm optimization-based approach.

Xinpei Ma1, Chun-An Chou2, Hiroki Sayama1

  • 1Department of Systems Science & Industrial Engineering, Binghamton University, the State University of New York, Binghamton, USA.

Brain Informatics
|October 18, 2016
PubMed
Summary

This study introduces a new machine learning framework for multi-voxel pattern analysis (MVPA) in functional magnetic resonance imaging (fMRI) to better understand cognitive processes. The approach enhances classification accuracy for brain neural responses.

Keywords:
Brain functional connectivityBrain response patternFeature selectionInteraction selectionParticle swarm optimizationPattern classification

More Related Videos

Brain Imaging Investigation of the Neural Correlates of Observing Virtual Social Interactions
10:45

Brain Imaging Investigation of the Neural Correlates of Observing Virtual Social Interactions

Published on: July 6, 2011

12.3K
Correlating Behavioral Responses to fMRI Signals from Human Prefrontal Cortex: Examining Cognitive Processes Using Task Analysis
10:33

Correlating Behavioral Responses to fMRI Signals from Human Prefrontal Cortex: Examining Cognitive Processes Using Task Analysis

Published on: June 20, 2012

13.4K

Related Experiment Videos

Last Updated: Mar 13, 2026

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

16.4K
Brain Imaging Investigation of the Neural Correlates of Observing Virtual Social Interactions
10:45

Brain Imaging Investigation of the Neural Correlates of Observing Virtual Social Interactions

Published on: July 6, 2011

12.3K
Correlating Behavioral Responses to fMRI Signals from Human Prefrontal Cortex: Examining Cognitive Processes Using Task Analysis
10:33

Correlating Behavioral Responses to fMRI Signals from Human Prefrontal Cortex: Examining Cognitive Processes Using Task Analysis

Published on: June 20, 2012

13.4K

Area of Science:

  • Neuroscience
  • Cognitive Science
  • Machine Learning

Background:

  • Functional magnetic resonance imaging (fMRI) is widely used to study brain neural responses linked to cognition.
  • Traditional univariate analysis has limitations; multi-voxel pattern analysis (MVPA) using machine learning offers a more effective approach for fMRI data.
  • MVPA addresses a multi-objective pattern classification challenge by selecting informative, interacting voxels to optimize response patterns.

Purpose of the Study:

  • To propose a novel feature interaction detection framework for voxel selection in MVPA.
  • To enhance the accuracy of classifying cognitive stimulus conditions using fMRI data.
  • To identify informative voxels and their connectivity for robust brain response pattern detection.

Main Methods:

  • Integration of hierarchical heterogeneous particle swarm optimization with support vector machines for voxel selection.
  • A two-stage approach: first, selecting the most informative voxels, then identifying response patterns based on voxel connectivity.
  • Validation using Haxby's dataset for object-level representations.

Main Results:

  • The proposed framework achieved higher classification accuracy compared to existing feature selection methods (e.g., forward and backward selection).
  • Extracted response patterns demonstrated improved performance in classifying cognitive states.
  • Effective identification of informative voxels and their interconnections for MVPA.

Conclusions:

  • The proposed feature interaction detection framework significantly improves MVPA performance in neuroscience research.
  • This method offers a more accurate way to decode cognitive states from fMRI data.
  • The approach advances the application of machine learning in analyzing complex brain neural responses.