DG-SMOTE: A Distance-Angle-Based Genetic Synthetic Minority Over-Sampling Technique for Unbalanced Data Learning

Created by W.Langdon from gp-bibliography.bib Revision:1.8344

@Article{Pei:TEVC,

• author = "Wenbin Pei and Yuyang Cui and Bing Xue and Mengjie Zhang and Jiqing Zhang and Yaqing Hou and Guangyu Zou and Zhang Qiang",
• title = "{DG-SMOTE:} A Distance-Angle-Based Genetic Synthetic Minority Over-Sampling Technique for Unbalanced Data Learning",
• journal = "IEEE Transactions on Evolutionary Computation",
• note = "Early access",
• keywords = "genetic algorithms, genetic programming, Evolutionary computation, Sampling methods, Noise measurement, Meteorology, Contracts, Standards, Noise, Nearest neighbour methods, Ensemble learning, Unbalanced data classification, Oversampling",
• ISSN = "1941-0026",
• DOI = "doi:10.1109/TEVC.2024.3515485",
• abstract = "Many real-world applications often generate unbalanced data. Learning from such data may lead to biased classifiers that perform poorly on the class of interest. Oversampling methods have been shown to be effective in re-balancing unbalanced data to help classifiers avoid performance bias. However, many existing oversampling methods rely on a pre-designed linear model structure and the neighbourhood information of an original instance. This may lead to the generation of noisy instances when the original data has noise. In this study, we develop a novel oversampling method in which genetic programming is introduced to automatically select good-quality instances and evolve a model structure that combines the selected instances to create a new instance. In the proposed oversampling method, an individual is used to represent a generated instance, which is evaluated by the fitness function designed based on the Euclidean distance and cosine theorem. In the experiments, we examine the effectiveness of the proposed oversampling method in assisting different types of classifiers to solve the issue of class imbalance, and compare it with popular sampling methods in unbalanced classification. The results have been analysed comprehensively, indicating that the new method successfully addressed the class imbalance issue by generating a group of good-quality instances for the minority class and outperformed the compared sampling methods in almost all cases.",
• notes = "Also known as \cite{10793073}",

}

Genetic Programming entries for Wenbin Pei Yuyang Cui Bing Xue Mengjie Zhang Jiqing Zhang Yaqing Hou Guangyu Zou Zhang Qiang

Citations