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

New support vector-based design method for binary hierarchical classifiers for multi-class classification problems.

Yu-Chiang Frank Wang1, David Casasent

  • 1Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA 15213, USA. ycwang@cmu.edu

Neural Networks : the Official Journal of the International Neural Network Society
|January 12, 2008
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

Describe, Spot and Explain: Interpretable Representation Learning for Discriminative Visual Reasoning.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2023
Same author

Joint Feature Disentanglement and Hallucination for Few-Shot Image Classification.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2021
Same author

Learning of 3D Graph Convolution Networks for Point Cloud Analysis.

IEEE transactions on pattern analysis and machine intelligence·2021
Same author

A Multi-domain and Multi-modal Representation Disentangler for Cross-Domain Image Manipulation and Classification.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2019
Same author

Transfer Neural Trees: Semi-Supervised Heterogeneous Domain Adaptation and Beyond.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2019
Same author

Edge-Preserving Depth Map Upsampling by Joint Trilateral Filter.

IEEE transactions on cybernetics·2017
Same journal

Dynamic analysis and reliable mechanical optimization application of ring HNN effected with a memristive neuron.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

DAFF-Net: A detection and search method for small-scale low surface brightness galaxies.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Quasi-synchronization for complex networks with hybrid pinning intermittent control.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Physics-encoded convolutional neural operators for parametric PDEs: A convergence-guaranteed framework via pre-computed kernel fields.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Exploiting audio-visual modalities in videos: Object detection via multi-stage bilateral coupling network.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Reliability-aware modality completion with cross-modal distillation for federated learning with missing modalities.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles

We introduce weighted support vector (WSV) k-means clustering for binary hierarchical classification. This novel method automatically selects classes for separation and visualizes high-dimensional data, outperforming standard approaches.

Area of Science:

  • Machine Learning
  • Data Science
  • Computer Vision

Background:

  • Hierarchical classification structures are essential for organizing complex data.
  • Existing methods lack automated class selection and visualization for high-dimensional support vector data.
  • Standard Support Vector Machines (SVMs) struggle with generalization and rejection of unseen data.

Purpose of the Study:

  • To propose a novel hierarchical design method for binary classification.
  • To enable automatic selection of classes for separation at each hierarchical node.
  • To allow visualization of high-dimensional support vector data clusters.

Main Methods:

  • Weighted Support Vector (WSV) k-means clustering algorithm for hierarchical design.
  • Support Vector Representation and Discrimination Machine (SVRDM) classifier utilized at each node.

Related Experiment Videos

  • Investigation into the efficacy of Gaussian kernels for data rejection.

    • Main Results:

    • The proposed WSV k-means clustering method successfully designs binary hierarchical classification structures.
    • The SVRDM classifier demonstrates superior generalization and rejection capabilities compared to standard SVMs.
    • Empirical results on an infrared (IR) database show the method outperforms standard one-vs-rest and SVM classifiers.

    Conclusions:

    • The WSV k-means clustering offers a significant advancement in hierarchical classification design.
    • The SVRDM classifier provides enhanced performance in recognition and rejection tasks.
    • This approach addresses limitations in existing hierarchical designs for high-dimensional data visualization and classification.