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 Video

Updated: Mar 10, 2026

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

8.1K

Adaptive swarm cluster-based dynamic multi-objective synthetic minority oversampling technique algorithm for tackling

Jinyan Li1, Simon Fong1, Yunsick Sung2

  • 1Department of Computer and Information Science, University of Macau, Taipa, Macau, S.A.R. China.

Biodata Mining
|December 17, 2016
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

Spatial transcriptomics in cancer research: insights into tumorigenesis, diagnosis and therapeutics.

Cell death discovery·2026
Same author

The ArMAPK5-ArbHLH3-Ar4CL3 module is associated with salicylic acid-induced phenolic biosynthesis in Agastache rugosa.

Plant physiology and biochemistry : PPB·2026
Same author

A novel two-in-one Eu-MOFs integrates electrochemiluminescence and ratiometric fluorescence dual-mode sensor for tetracycline detection.

Biosensors & bioelectronics·2026
Same author

A heterozygous deletion and inversion at the NHEJ1‑IHH locus associated with shank length in Yunlong short-leg chicken.

BMC genomics·2026
Same author

Unified Modulation Matrix-Based Shared Control for Teleoperated Multi-Robot Formation and Obstacle Avoidance.

Sensors (Basel, Switzerland)·2026
Same author

Fusion attention-based nasopharyngeal carcinoma segmentation model in predicting the clinical outcome of cervical lymph node residue after IMRT.

BMC medical imaging·2026
This summary is machine-generated.

A novel class-balancing method, adaptive swarm cluster-based dynamic multi-objective synthetic minority oversampling technique (ASCB_DmSMOTE), improves classification accuracy in biomedical applications. This technique enhances prediction performance on imbalanced datasets by combining over-sampling and under-sampling.

Area of Science:

  • Biomedical data analysis
  • Machine learning in healthcare
  • Data science

Background:

  • Imbalanced datasets, common in biomedical applications, pose challenges for classification models due to rare minority classes.
  • Poor prediction performance arises from insufficient training data for the minority class in imbalanced datasets.
  • Medical anomalies, positive clinical tests, and rare diseases exemplify minority classes in biomedical data.

Purpose of the Study:

  • To introduce a novel class-balancing method, ASCB_DmSMOTE, for addressing imbalanced datasets in biomedical applications.
  • To enhance the prediction performance of classification models trained on imbalanced biomedical data.
  • To improve accuracy and credibility in classifying rare biomedical events.

Main Methods:

Keywords:
Biomedical dataClassificationDynamic Multi-objectiveImbalanced datasetSMOTESwarm optimisationUnder-sampling

Related Experiment Videos

Last Updated: Mar 10, 2026

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

8.1K
  • Developed adaptive swarm cluster-based dynamic multi-objective synthetic minority oversampling technique (ASCB_DmSMOTE).
  • Integrated under-sampling and over-sampling techniques within a swarm optimization algorithm.
  • Dynamically optimized SMOTE parameters and adaptively selected rebalancing parameters for clustered sub-datasets.

    • Main Results:

    • ASCB_DmSMOTE demonstrated significant improvements over existing SMOTE algorithms.
    • Achieved higher accuracy and credibility in classification tasks with imbalanced data.
    • Effectively synthesized a reasonable scale of minority class samples for clustered datasets.

    Conclusions:

    • The proposed ASCB_DmSMOTE method tactfully combines rebalancing techniques for superior performance.
    • Dynamically optimizing parameters and reallocating majority class data leads to better minority class synthesis.
    • ASCB_DmSMOTE overcomes conventional methods, attaining higher credibility and accuracy in imbalanced classification.