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

Local dimensionality reduction and supervised learning within natural clusters for biomedical data analysis.

Mykola Pechenizkiy1, Alexey Tsymbal, Seppo Puuronen

  • 1Department of Computer Science and Information Systems, University of Jyväskylä, Finland. mpechen@cs.jyu.fi

IEEE Transactions on Information Technology in Biomedicine : a Publication of the IEEE Engineering in Medicine and Biology Society
|July 29, 2006
PubMed
Summary

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

Evolving Plasticity for Autonomous Learning under Changing Environmental Conditions.

Evolutionary computation·2021
Same author

EEG-based classification of epilepsy and PNES: EEG microstate and functional brain network features.

Brain informatics·2020
Same author

Apriori Versions Based on MapReduce for Mining Frequent Patterns on Big Data.

IEEE transactions on cybernetics·2017
Same author

Mining Context-Aware Association Rules Using Grammar-Based Genetic Programming.

IEEE transactions on cybernetics·2017
Same author

Speeding-Up Association Rule Mining With Inverted Index Compression.

IEEE transactions on cybernetics·2016
Same author

Clinical evaluation of semi-automatic landmark-based lesion tracking software for CT-scans.

Cancer imaging : the official publication of the International Cancer Imaging Society·2015

Applying dimensionality reduction within natural clusters improves supervised learning for antibiotic resistance data. This approach enhances data representation compared to global methods, aiding in medical domain applications.

Area of Science:

  • Medical Informatics
  • Machine Learning
  • Computational Biology

Background:

  • Inductive learning systems are valuable in medicine but require data preprocessing.
  • Multidimensional, heterogeneous data pose challenges for learning algorithms.
  • Dimensionality reduction (DR) is a common preprocessing step.

Purpose of the Study:

  • To investigate the impact of natural clustering on DR for supervised learning (SL) in antibiotic resistance.
  • To compare data-mining strategies using feature extraction/selection with DR and SL.
  • To evaluate the effectiveness of local versus global DR on microbiological data.

Main Methods:

  • Applied several data-mining strategies incorporating DR (feature extraction/selection).
  • Utilized supervised learning (SL) on microbiological data.

Related Experiment Videos

  • Compared local DR within natural clusters versus global DR on the entire dataset.

    • Main Results:

    • Local DR within natural clusters yielded better data representation for SL.
    • This contrasts with the performance of global DR applied to the whole dataset.
    • Natural clustering enhances DR effectiveness for antibiotic resistance prediction.

    Conclusions:

    • Natural clustering, guided by expert knowledge, improves DR for supervised learning in antibiotic resistance.
    • Local DR within clusters is more effective than global DR for this specific domain.
    • This strategy offers a promising approach for preprocessing complex medical data.