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

Parallel and distributed methods for incremental frequent itemset mining.

Matthew Eric Otey1, Srinivasan Parthasarathy, Chao Wang

  • 1Computer and Information Science Department, The Ohio State University, Columbus, OH 43210, USA. otey@cis.ohio-state.edu

IEEE Transactions on Systems, Man, and Cybernetics. Part B, Cybernetics : a Publication of the IEEE Systems, Man, and Cybernetics Society
|December 29, 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

Assessment of Human Fetuses Undergoing Acute Pain: Validation of the Fetal-7 Scale.

The journal of pain·2024
Same author

Machine learning models exploring characteristic single-nucleotide signatures in yellow fever virus.

PloS one·2022
Same author

Prediction of SARS-CoV-2-positivity from million-scale complete blood counts using machine learning.

Communications medicine·2022
Same author

Early identification of ICU patients at risk of complications: Regularization based on robustness and stability of explanations.

Artificial intelligence in medicine·2022
Same author

Explainable death toll motion modeling: COVID-19 data-driven narratives.

PloS one·2022
Same author

Practical detection of spammers and content promoters in online video sharing systems.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2011

This study introduces efficient incremental data mining methods for dynamic and distributed datasets, crucial for modern big data challenges. These new algorithms reduce computational waste and communication overhead, enabling scalable knowledge discovery.

Area of Science:

  • Computer Science
  • Data Mining
  • Distributed Systems

Background:

  • Traditional data mining methods assume centralized, static data, which is increasingly untenable.
  • Dynamic and distributed data lead to wasted computational resources and excessive communication overhead.
  • Efficient incremental data mining is essential for scalability and knowledge discovery in modern data environments.

Purpose of the Study:

  • To address the limitations of traditional data mining for dynamic and distributed datasets.
  • To develop efficient incremental algorithms for frequent itemset mining.
  • To enable scalable and low-overhead knowledge discovery from distributed dynamic data.

Main Methods:

  • Developed an efficient incremental algorithm for dynamic frequent itemset mining without full dataset scans.

Related Experiment Videos

  • Proposed parallelization strategies for the incremental algorithm.
  • Introduced a distributed asynchronous algorithm with minimal communication overhead for distributed dynamic datasets.

    • Main Results:

    • The proposed algorithms efficiently maintain information during data updates.
    • Parallelization enhances the performance of incremental frequent itemset mining.
    • The distributed asynchronous algorithm effectively mines frequent itemsets from distributed dynamic data with low communication costs.
    • The approach supports generation of both local and global frequent itemset models, enabling high-contrast frequent itemset discovery.

    Conclusions:

    • Efficient incremental and distributed data mining methods are vital for handling modern data challenges.
    • The developed algorithms offer scalable and resource-efficient solutions for frequent itemset mining in dynamic and distributed environments.
    • The ability to generate local and global models facilitates deeper insights into data skew across distributed sites.