EE-SMOTE: An oversampling method in conjunction with information entropy for imbalanced learning

Jiajing Huang, Teng Li, Yanzhe Xu, Teresa Wu, Hyunsoo Yoon, Jennifer R. Charlton, Kevin M. Bennett

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Imbalanced learning attracts great attention in various research fields. Existing literature-reported methodologies in imbalanced learning have shown drawbacks including over-generation or noisy/wrong samples generations. This paper presents EE-SMOTE, an oversampling technique based on information entropy, to support the imbalance classifications. Specifically, we propose a metric, Eigen-Entropy (EE), to identify homogenous samples from minority classes for oversampling technique, specifically, SMOTE to reach data balances for classification. Experiments on public dataset and real-world datasets demonstrate the efficacy and effectiveness of the proposed EE-SMOTE in imbalanced learning.

Original languageEnglish (US)
Title of host publicationIISE Annual Conference and Expo 2022
EditorsK. Ellis, W. Ferrell, J. Knapp
PublisherInstitute of Industrial and Systems Engineers, IISE
ISBN (Electronic)9781713858072
StatePublished - 2022
EventIISE Annual Conference and Expo 2022 -
Duration: Jan 1 2022 → …

Publication series

NameIISE Annual Conference and Expo 2022

Conference

ConferenceIISE Annual Conference and Expo 2022
Period1/1/22 → …

Keywords

  • Eigenvalues
  • Homogeneity
  • Imbalanced learning
  • Information entropy
  • Oversampling

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Industrial and Manufacturing Engineering

Fingerprint

Dive into the research topics of 'EE-SMOTE: An oversampling method in conjunction with information entropy for imbalanced learning'. Together they form a unique fingerprint.

Cite this