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

A new method for independent component analysis with priori information based on multi-objective optimization.

Yuhu Shi1, Weiming Zeng1, Nizhuan Wang1

  • 1Lab of Digital Image and Intelligent Computation, Shanghai Maritime University, 1550 Harbor Avenue, Pudong, Shanghai, 201306, China.

Journal of Neuroscience Methods
|April 2, 2017
PubMed
Summary
This summary is machine-generated.

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

MOF-ionic liquid engineered polymer electrolyte for advanced solid-state sodium metal batteries.

Chemical communications (Cambridge, England)·2026
Same author

Developmental transition of brown adipose tissue from a thermogenic to a lipogenic phenotype in neonatal goats revealed by single-nucleus transcriptomics.

Zoological research·2026
Same author

Imagined Speech Brain-Computer Interface: A Task-Oriented Review of Neural Decoding.

Sensors (Basel, Switzerland)·2026
Same author

Discovery of Dual A<sub>2A</sub>/A<sub>2B</sub> Adenosine Receptor Antagonist and Clinical Candidate INCB106385.

Journal of medicinal chemistry·2026
Same author

Dental pulp stem cell exosomes promote angiogenesis via the PI3K/Akt signaling pathway to treat androgenetic alopecia.

Stem cell research & therapy·2026
Same author

Poor Sleep Quality Associated with Impaired Postoperative Outcomes and Frailty Incidence in Elderly Patients After Total Hip Arthroplasty: A Severity Matched Case-Control Study.

Journal of multidisciplinary healthcare·2026

This study introduces a novel multi-objective optimization approach for independent component analysis (ICA) using reference signals. The new method improves source recovery and functional connectivity detection without needing threshold parameters.

Area of Science:

  • Neuroimaging
  • Signal Processing
  • Machine Learning

Background:

  • Independent Component Analysis (ICA) is crucial for analyzing complex data, particularly in neuroimaging.
  • Incorporating prior information into ICA traditionally uses constrained ICA, which requires difficult-to-set threshold parameters.
  • Existing constrained ICA methods face challenges in determining optimal constraint thresholds for reference signals.

Purpose of the Study:

  • To develop a new model for ICA that effectively integrates prior information as a reference signal.
  • To overcome the limitations of threshold selection in traditional constrained ICA methods.
  • To enhance the performance of source signal recovery and functional connectivity analysis.

Main Methods:

  • A novel ICA model was established using a multi-objective optimization framework.
Keywords:
Adaptive weighted summation methodFixed-point learning algorithmIndependent component analysisMulti-objective optimizationPriori information

Related Experiment Videos

  • An adaptive weighted summation method was employed to address the multi-objective problem.
  • A fixed-point learning algorithm was utilized for model optimization.

    • Main Results:

    • The proposed method demonstrated superior performance in recovering both spatial sources and time courses on single-subject fMRI data (hybrid and task-related).
    • Group-level analysis of resting-state fMRI data showed higher correlation of group independent components with subject-level components compared to traditional methods.
    • T-tests confirmed the statistical significance of improved component correlation.

    Conclusions:

    • The new ICA model successfully incorporates prior information without requiring threshold parameter selection.
    • The method significantly enhances functional connectivity detection capabilities compared to existing approaches.
    • This approach offers a more robust and user-friendly alternative for ICA with prior information.