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 similarity-based robust clustering method.

Miin-Shen Yang1, Kuo-Lung Wu

  • 1Department of Applied Mathematics, Chung Yuan Christian University, Chung-Li, Taiwan 32023, ROC. msyang@math.cycu.edu.tw

IEEE Transactions on Pattern Analysis and Machine Intelligence
|September 24, 2004
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

Federated Multi-View K-Means Clustering.

IEEE transactions on pattern analysis and machine intelligence·2025
Same author

Nonlinear strict distance and similarity measures for intuitionistic fuzzy sets with applications to pattern classification and medical diagnosis.

Scientific reports·2023
Same author

Fuzzy Gaussian Lasso clustering with application to cancer data.

Mathematical biosciences and engineering : MBE·2019
Same author

Suppressed fuzzy-soft learning vector quantization for MRI segmentation.

Artificial intelligence in medicine·2011
Same author

Alpha-cut implemented fuzzy clustering algorithms and switching regressions.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2008
Same author

Magnetic resonance imaging segmentation techniques using batch-type learning vector quantization algorithms.

Magnetic resonance imaging·2007
Same journal

TraGraph-GS: Trajectory Graph-based Gaussian Splatting for Arbitrary Large-Scale Scene Rendering.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

SWIFT: A Small-World Interaction Framework for Flow-Aware Trajectory Prediction in Autonomous Driving.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

HardFlow: Hard-Constrained Sampling for Flow-Matching Models Via Trajectory Optimization.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Industrial Brain: Self-Evolving Neuro-Symbolic Autonomy with Causal Resilience for Cyber-Physical Systems.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Adaptive Hardness-Driven Dictionary Distillation for Incomplete Streaming View Clustering.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Mixture of Global and Local Experts with Diffusion Transformer for Controllable Face Generation.

IEEE transactions on pattern analysis and machine intelligence·2026
See all related articles

This study introduces a robust similarity-based clustering method (SCM) that automatically determines cluster properties. SCM effectively handles noise and outliers, outperforming existing methods in data analysis.

Area of Science:

  • Data Science
  • Machine Learning
  • Statistical Modeling

Background:

  • Clustering algorithms often require pre-defined parameters or assumptions about data distribution.
  • Existing methods can be sensitive to initialization, cluster volume variations, and the presence of noise or outliers.

Purpose of the Study:

  • To introduce a novel alternating optimization clustering procedure named similarity-based clustering method (SCM).
  • To demonstrate SCM's ability to self-organize optimal cluster number and volumes without external validation or covariance matrices.
  • To evaluate SCM's robustness against initialization, varying cluster volumes, noise, and outliers.

Main Methods:

  • Developed an alternating optimization clustering procedure based on a total similarity objective function.

Related Experiment Videos

  • Utilized approximate density shape estimation principles.
  • Performed influence function and gross error sensitivity analysis to assess robustness.

    • Main Results:

    • SCM successfully self-organizes local optimal cluster number and volumes.
    • Demonstrated robustness to initialization, cluster volumes, noise, and outliers.
    • Experimental results on numerical and actual data show SCM's superiority over existing methods.

    Conclusions:

    • SCM offers a robust and effective clustering approach.
    • The method exhibits significant advantages in handling diverse data characteristics and challenging conditions.
    • SCM presents a promising alternative for data clustering applications.