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

Ranking-based kernels in applied biomedical diagnostics using a support vector machine.

Vilen Jumutc1, Pawel Zayakin, Arkady Borisov

  • 1Riga Technical University, Meža 1/4 Riga, LV-1658, Latvia. jumutc@gmail.com

International Journal of Neural Systems
|December 2, 2011
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

Liver progenitor cells perform wound healing in a scratch assay by concerted bistable circuits.

NPJ systems biology and applications·2026
Same author

HSP90 inhibition potentiates oxidant-based antimelanoma action of novel thioquercetin derivatives by compromising AhR/CYP1A1 pathway.

Apoptosis : an international journal on programmed cell death·2026
Same author

Resistance of BRAF<sup>V600E</sup>-mutant melanoma to Vemurafenib: a senescence-induced swing from differentiation to blastulation followed by proliferation.

Cancer letters·2026
Same author

Multispectral imaging and autofluorescence photobleaching combined in a multi-head neural network for skin cancer classification.

Frontiers in medicine·2026
Same author

The phenotypic spectrum of <i>PTCD3</i> deficiency.

JIMD reports·2024
Same author

sRNAflow: A Tool for the Analysis of Small RNA-Seq Data.

Non-coding RNA·2024

Ranking-based kernels enhance the analysis of high-dimensional biomedical data for clinical diagnostics. These kernels, when used with Support Vector Machines (SVM), significantly improve classification accuracy and predictive power.

Area of Science:

  • Biomedical data analysis
  • Machine learning in diagnostics
  • High-dimensional data processing

Background:

  • Biomedical data is often high-dimensional and noisy, posing challenges for accurate analysis.
  • Traditional methods may struggle with the complexity of clinical diagnostic data.
  • Support Vector Machines (SVM) are a powerful classification technique but can be further optimized.

Purpose of the Study:

  • To introduce and evaluate ranking-based kernels for analyzing high-dimensional biomedical data.
  • To assess the performance improvement of SVM when combined with ranking-based kernels.
  • To explore the broader applicability of these kernels in computer-aided diagnostic tasks.

Main Methods:

  • Development and application of novel ranking-based kernels.

Related Experiment Videos

  • Integration of these kernels with Support Vector Machine (SVM) classification.
  • Experimental validation on high-dimensional biomedical and microarray datasets.
  • Theoretical generalization bound analysis.

    • Main Results:

    • Ranking-based kernels significantly improve classification rates and predictive power compared to traditional SVM kernels.
    • The proposed method demonstrates superior performance on high-dimensional biomedical and microarray data.
    • Effectiveness shown in enhancing the wrapper method, e.g., SVM.

    Conclusions:

    • Ranking-based kernels offer a significant advancement for analyzing complex biomedical data.
    • This approach enhances the capabilities of SVM for clinical diagnostics.
    • The kernels show potential for applications beyond classification, including novelty detection and clustering.