EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Improved Oversampling Algorithm for Imbalanced Data Based on K-Nearest Neighbor and Interpolation Process Optimization

Yiheng Chen, Jinbai Zou, Lihai Liu, Chuanbo Hu

Symmetry · 26.02.2024 · 16 (3) · 273

DOI: 10.3390/sym16030273 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Symmetry, online erschienen am 26.02.2024. Verfasst von Yiheng Chen und 3 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: China National Railway Group Co., Ltd. Technology Research and Development Program Project, Shanghai Science and Technology Commission—“Belt and Road” China-Laos Railway Project International Joint Laboratory, Shanghai Science and Technology Commission—Research on Key Technologies of Intelligent Operation and Maintenance of Rail Transit.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The problems of imbalanced datasets are generally considered asymmetric issues. In asymmetric problems, artificial intelligence models may exhibit different biases or preferences when dealing with different classes. In the process of addressing class imbalance learning problems, the classification model will pay too much attention to the majority class samples and cannot guarantee the classification performance of the minority class samples, which might be more valuable. By synthesizing the minority class samples and changing the data distribution, unbalanced datasets can be optimized. Traditional oversampling algorithms have problems of blindness and boundary ambiguity when synthesizing new samples. A modified reclassification algorithm based on Gaussian distribution is put forward. First, the minority class samples are reclassified by the KNN algorithm. Then, different synthesis strategies are selected according to the combination of the minority class samples, and the Gaussian distribution is used to replace the uniform random distribution for interpolation operation under certain classification conditions to reduce the possibility of generating noise samples. The experimental results indicate that the proposed oversampling algorithm can achieve a performance improvement of 2∼8% in evaluation metrics, including G-mean, F-measure, and AUC, compared to traditional oversampling algorithms.

Förderung

  • China National Railway Group Co., Ltd. Technology Research and Development Program Project
  • Shanghai Science and Technology Commission—“Belt and Road” China-Laos Railway Project International Joint Laboratory
  • Shanghai Science and Technology Commission—Research on Key Technologies of Intelligent Operation and Maintenance of Rail Transit

Zitieren

APA

Chen, Y., Zou, J., Liu, L., & Hu, C. (2024). Improved Oversampling Algorithm for Imbalanced Data Based on K-Nearest Neighbor and Interpolation Process Optimization. Symmetry, 16(3), 273. https://doi.org/10.3390/sym16030273

Vancouver

Chen Y, Zou J, Liu L, Hu C. Improved Oversampling Algorithm for Imbalanced Data Based on K-Nearest Neighbor and Interpolation Process Optimization. Symmetry. 2024;16(3):273. doi:10.3390/sym16030273

BibTeX
@article{Chen2024,
  author = {Chen, Yiheng and Zou, Jinbai and Liu, Lihai and Hu, Chuanbo},
  title = {Improved Oversampling Algorithm for Imbalanced Data Based on K-Nearest Neighbor and Interpolation Process Optimization},
  journal = {Symmetry},
  year = {2024},
  volume = {16},
  number = {3},
  pages = {273},
  doi = {10.3390/sym16030273}
}
Kostenlos starten →