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 Video

Updated: Jun 12, 2026

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

Discriminative semi-supervised feature selection via manifold regularization.

Zenglin Xu1, Irwin King, Michael Rung-Tsong Lyu

  • 1Cluster of Excellence, Saarland University, Max Planck Institute for Informatics, Saarbruecken 66123, Germany. zlxu@mpi-inf.mpg.de

IEEE Transactions on Neural Networks
|June 24, 2010
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

Optimized protocols for culturing and sectioning mouse intestinal organoids: enhancing efficiency and structural integrity.

MethodsX·2026
Same author

Epidemiological Characteristics of Coxsackievirus A6 in Baotou, Inner Mongolia, China, 2023-2024.

Viruses·2026
Same author

A three-gene signature (ABCE1, ATAD5, FUT4) for colorectal cancer prognosis: integrative analysis of transcriptomic, single-cell, and machine learning data.

Biochemical and biophysical research communications·2026
Same author

A Newborn with Systemic Hyperinflammation Caused by CDC42 Mutation: A Case Report.

QJM : monthly journal of the Association of Physicians·2026
Same author

The awakening effect of hyperbaric oxygen therapy combined with systematic auditory stimulation in comatose patients with craniocerebral injury and its influence on serum biomarkers.

Frontiers in neurology·2026
Same author

Serum microRNA-34a as a circulating biomarker for age-related macular degeneration and short-term anti-VEGF response in neovascular AMD.

BMC ophthalmology·2026

This study introduces a new semi-supervised feature selection method that leverages manifold regularization to effectively use unlabeled data. The approach enhances feature selection by maximizing classification margins and exploiting data distribution geometry.

Area of Science:

  • Data Mining
  • Machine Learning
  • Pattern Recognition

Background:

  • Semi-supervised feature selection (SSFS) is crucial when labeled data is scarce.
  • Unlabeled data holds valuable information for improving feature selection.
  • Existing SSFS methods struggle to fully utilize unlabeled data information.

Purpose of the Study:

  • To propose a novel discriminative semi-supervised feature selection method.
  • To effectively leverage unlabeled data in feature selection.
  • To improve the identification of discriminative features.

Main Methods:

  • Manifold regularization for semi-supervised feature selection.
  • Maximizing classification margin and exploiting data distribution geometry.
  • Formulating the problem as a convex-concave optimization task and using the level method for solution.

Related Experiment Videos

Last Updated: Jun 12, 2026

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

Main Results:

  • The proposed method is an embedded feature selection technique.
  • It identifies more discriminative features compared to previous algorithms.
  • Theoretical convergence rate proof for the level method is provided.

Conclusions:

  • The novel semi-supervised feature selection method effectively utilizes unlabeled data.
  • The approach demonstrates superior performance in empirical evaluations.
  • This method offers a promising direction for feature selection in data mining.