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

Discriminant analysis in pairwise kernel learning for SVM classification.

Hao Jiang1, Wai-Ki Ching, Delin Chu

  • 1Department of Mathematics, University of Hong Kong, Hong Kong. haohao@hkusuc.hku.hk

International Journal of Bioinformatics Research and Applications
|September 11, 2012
PubMed
Summary

This study introduces a new framework for multiple kernel learning in Support Vector Machines (SVM). The method effectively determines kernel coefficients for classifying heterogeneous data, showing promise for future applications.

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

Dual modification of BiVO<sub>4</sub> photoanode by enriching bulk and surface oxygen vacancies for enhanced photoelectrochemical performance.

Journal of colloid and interface science·2022
Same author

A Progressive Hierarchical Alternating Least Squares Method for Symmetric Nonnegative Matrix Factorization.

IEEE transactions on pattern analysis and machine intelligence·2022
Same author

A Fast Frequent Directions Algorithm for Low Rank Approximation.

IEEE transactions on pattern analysis and machine intelligence·2018
Same author

Sequential Anaerobic/Aerobic Digestion for Enhanced Carbon/Nitrogen Removal and Cake Odor Reduction.

Water environment research : a research publication of the Water Environment Federation·2016
Same author

BlueDetect: An iBeacon-Enabled Scheme for Accurate and Energy-Efficient Indoor-Outdoor Detection and Seamless Location-Based Service.

Sensors (Basel, Switzerland)·2016
Same author

[Dasatinib treatment based on BCR- ABL mutation detection in imatinib- resistant patients with chronic myeloid leukemia].

Zhonghua xue ye xue za zhi = Zhonghua xueyexue zazhi·2016

Area of Science:

  • Computational Biology
  • Machine Learning
  • Bioinformatics

Background:

  • Multiple kernel learning (MKL) is crucial for integrating data from heterogeneous sources.
  • Support Vector Machines (SVM) benefit from MKL for enhanced classification.
  • Accurate determination of kernel coefficients is key in MKL.

Purpose of the Study:

  • To develop a novel framework for learning coefficients in pairwise kernel learning for SVM.
  • To demonstrate the effectiveness of the proposed method on biological datasets.

Main Methods:

  • A new framework for determining coefficients in pairwise kernel learning was developed.
  • The method was applied to Support Vector Machines (SVM).
  • Experimental evaluation was performed on gene expression data.

Related Experiment Videos

Main Results:

  • The proposed method successfully predicted stemness membership genes in mouse embryonic stem cells (mESCs).
  • The framework showed strong discrimination power on DNA repair gene data.
  • The formulation for learning coefficients in pairwise kernel learning proved effective.

Conclusions:

  • The developed framework offers a novel perspective for multiple kernel learning.
  • The method demonstrates significant potential for applications involving heterogeneous biological data.
  • This research advances the application of MKL in bioinformatics and computational biology.