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

Scalable model-based clustering for large databases based on data summarization.

Huidong Jin1, Man-Leung Wong, K S Leung

  • 1Lingnan University, Tuen Mun, Hong Kong. Warren.Jin@csiro.au

IEEE Transactions on Pattern Analysis and Machine Intelligence
|November 16, 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

Compositional data modeling of high-dimensional single cell RNA-seq (CoDA-hd): its advantages over commonly used normalization approaches.

Journal of translational medicine·2025
Same author

Reproductive Toxicity and Multi/Transgenerational Effects of Emerging Pollutants on <i>C. elegans</i>.

Toxics·2024
Same author

CXCL1/IGHG1 signaling enhances crosstalk between tumor cells and tumor-associated macrophages to promote MC-LR-induced colorectal cancer progression.

Environmental pollution (Barking, Essex : 1987)·2024
Same author

Microcystin-leucine-arginine impairs bone microstructure and biomechanics by activating osteoimmune response and inhibiting osteoblasts maturation in developing rats.

Toxicology·2023
Same author

Mixed exposure effect of seminal metals on semen quality, mediation of total antioxidant capacity, and moderation of GSTM1/GSTT1 gene deletion in Chinese reproductive-aged men.

Environmental research·2023
Same author

Comparing the cooling effectiveness of operationalisable urban surface combination scenarios for summer heat mitigation.

The Science of the total environment·2023
Same journal

Benchmarking the Robustness of Autonomous Driving to Environmental Illusions: A Lane Perception Perspective.

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

Learning Topology-Aware Representations via Test-Time Adaptation for Anomaly Segmentation.

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

Two new scalable clustering algorithms, bEMADS and gEMADS, efficiently handle large datasets using Gaussian mixture models. These methods significantly outperform traditional expectation-maximization algorithms in speed with minimal impact on accuracy.

Area of Science:

  • Data Mining
  • Machine Learning
  • Computational Statistics

Background:

  • Scalability is a major challenge in data mining, particularly for large datasets with constrained computational resources.
  • Existing methods often struggle with memory and processing time limitations.
  • The Gaussian mixture model is a powerful tool for data clustering and density estimation.

Purpose of the Study:

  • To introduce two novel scalable clustering algorithms, bEMADS and gEMADS.
  • To address the limitations of existing methods in handling large-scale data.
  • To leverage the Gaussian mixture model for efficient data summarization and clustering.

Main Methods:

  • Development of the EMADS (Expectation-Maximization on Data Summaries) algorithm, which operates on summarized data.

Related Experiment Videos

  • Implementation of two variants: bEMADS and gEMADS, utilizing Gaussian mixture models.
  • Data summarization into subclusters to approximate aggregate behavior.

    • Main Results:

    • Both bEMADS and gEMADS demonstrate significant speed improvements, running orders of magnitude faster than expectation-maximization.
    • The proposed algorithms maintain high accuracy with minimal loss compared to traditional methods.
    • EMADS algorithm is proven to be convergent.

    Conclusions:

    • bEMADS and gEMADS offer a scalable and efficient solution for clustering large datasets.
    • These algorithms provide a practical alternative to existing methods when computational resources are limited.
    • The EMADS framework effectively approximates data behavior under Gaussian mixture models for improved scalability.