WBSWK: weighted bi-directional sampling based on wk-means method for imbalanced datasets
Peng Zhou · Third International Conference on Electronics and Communication; Network and Computer Technology (ECNCT 2021) · 2022
Traditional classification algorithms tend to cause minority classes to be misclassified when classifying imbalanced data sets. In this paper, we propose an over-sampling and under-sampling algorithm based on WK-means clustering. Our method firstly uses WK-means to cluster the whole datasets, then oversamples the datasets in some regions with a large number of minority class according to the imbalance ratio by different weights of each cluster, avoids the generation of noise and effectively overcomes imbalances between and within classes. Finally, undersampling the clusters with a large number of minority class to balance the sample number of the whole datasets. The experimental results obtained from 11 datasets show that the proposed method is superior to other methods under different classifiers and evaluation criteria.