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

Toward ultimate miniaturization of high Q silicon traveling-wave microresonators.

Optics express·2010
Same author

Mathematical modeling of degradation for bulk-erosive polymers: applications in tissue engineering scaffolds and drug delivery systems.

Acta biomaterialia·2010
Same author

[Effect of electroacupuncture on lipid metabolism in metabolic syndrome].

Zhongguo zhen jiu = Chinese acupuncture & moxibustion·2010
Same author

STK39 is an independent risk factor for male hypertension in Han Chinese.

International journal of cardiology·2010
Same author

Molecular analysis, developmental function and heavy metal-induced expression of ABCC5 in zebrafish.

Comparative biochemistry and physiology. Part B, Biochemistry & molecular biology·2010
Same author

[Effects of acupuncture combined with diet adjustment and aerobic exercise on weight and waist-hip ratio in simple obesity patients].

Zhongguo zhen jiu = Chinese acupuncture & moxibustion·2010

Related Experiment Video

Updated: Dec 29, 2025

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

7.9K

Comparison of feature selection methods based on discrimination and reliability for fMRI decoding analysis.

Wenyan Xu1, Qing Li1, Xingyu Liu2

  • 1School of Artificial Intelligence, Engineering Research Center of Intelligent Technology and Educational Application, Ministry of Education, Beijing Normal University, Beijing, 100875, China.

Journal of Neuroscience Methods
|February 1, 2020
PubMed
Summary
This summary is machine-generated.

Feature selection for brain state decoding using fMRI data is crucial. Discrimination-based features outperform reliability-based features for classification, though reliability ensures stability.

Keywords:
DecodingFMRIFeature selectionMachine learning

More Related Videos

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

16.1K
Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

43.5K

Related Experiment Videos

Last Updated: Dec 29, 2025

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

7.9K
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

16.1K
Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

43.5K

Area of Science:

  • Neuroscience
  • Machine Learning
  • Data Science

Background:

  • Feature selection is vital for machine learning-based fMRI brain state decoding.
  • Current methods rely on feature discrimination or reliability, with unclear suitability for fMRI data.

Purpose of the Study:

  • To compare the efficacy of discrimination-based versus reliability-based feature selection for fMRI brain state decoding.
  • To investigate the influence of subject and feature numbers on these selection methods.

Main Methods:

  • Utilized ANOVA and Kendall's concordance coefficient as proxies for discrimination and reliability, respectively.
  • Compared method performance across varying numbers of subjects and features.
  • Analyzed data from 987 subjects in the Human Connectome Project (HCP).

Main Results:

  • Discrimination-based features showed superior classification performance for distinguishing brain states.
  • Reliability-based features demonstrated greater stability across analyses.
  • Feature properties (discernment and stability) were influenced by subject and feature counts.
  • Increased feature extraction led to expanded brain region representation, from occipital to association areas.

Conclusions:

  • Provides empirical guidance for optimizing feature selection in predicting individual brain states from fMRI data.
  • Highlights the trade-offs between feature discrimination and reliability in fMRI analysis.