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

Unsupervised clustering algorithm for N-dimensional data.

Erwin B Montgomery1, He Huang, Amir Assadi

  • 1Department of Neurology, National Primate Research Center, University of Wisconsin-Madison, 600 Highland Ave., Madison, WI 53792, USA. montgomery@neurology.wisc.edu

Journal of Neuroscience Methods
|April 26, 2005
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

Author Correction: Emergence of structures in neuronal network activities.

Scientific reports·2025
Same author

Emergence of structures in neuronal network activities.

Scientific reports·2025
Same author

Spectrum dependency to rate and spike timing in neuronal spike trains.

Journal of neuroscience methods·2022
Same author

Challenges for future theories of Parkinson pathophysiology.

Neuroscience research·2021
Same author

Debugging Adaptive Deep Brain Stimulation for Parkinson's Disease.

Movement disorders : official journal of the Movement Disorder Society·2020
Same author

A Point Process Model-based Framework Reveals Reinforcement Mechanisms in Striatum during High Frequency STN DBS.

Proceedings of the ... IEEE Conference on Decision & Control. IEEE Conference on Decision & Control·2020

This study introduces an automated algorithm for cluster analysis, eliminating the need for manual estimation of cluster number and location. This method enhances data classification, especially for high-dimensional datasets.

Area of Science:

  • Data science
  • Computational statistics
  • Machine learning

Background:

  • Cluster analysis is crucial for data classification.
  • Existing methods like k-means and k-median require manual input for the number and location of clusters.
  • Manual estimation is often based on prior knowledge or data visualization, which is challenging for high-dimensional data.

Purpose of the Study:

  • To present a novel algorithm for automated cluster analysis.
  • To overcome the limitations of existing methods that require user-defined parameters.
  • To enable automatic estimation of cluster number and location without human intervention.

Main Methods:

  • Development of a new algorithm for cluster analysis.
  • The algorithm automatically estimates the number of clusters.

Related Experiment Videos

  • The algorithm automatically estimates the location of clusters within the parameter space.
  • The method is independent of the data's dimensionality.

    • Main Results:

    • The algorithm successfully provides estimates for cluster number and location automatically.
    • It functions effectively regardless of the dataset's dimensionality.
    • It removes the need for a priori user estimations.

    Conclusions:

    • The developed algorithm offers an automated solution for cluster analysis.
    • It addresses the limitations of traditional methods, particularly for complex, high-dimensional datasets.
    • This approach enhances the objectivity and efficiency of data classification.