Density-weighted intuitionistic fuzzy least squares twin support vector machines for class imbalance learning

Abstract

The existing models generated by twin support vector machines cannot effectively deal with datasets containing noises and outliers and often do not consider the inherent distribution of data when tackling the class imbalance data. To moderate the above problems, we propose a density-weighted intuitionistic fuzzy least squares twin support vector machines for class imbalance learning. Firstly, the density-weighted values of each data point based on data inherent distribution are calculated by the k-nearest neighbor method, the values of density-weighted are introduced into the intuitionistic fuzzy twin support vector machines (IFTSVM), and thus the density-weighted IFTSVM are proposed for class imbalance learning. Besides, to avoid the issue of overfitting, a regularization term is added to the objective function of the density-weighted IFTSVM. Finally, to improve the computational efficiency of the density-weighted IFTSVM, we use least squares instead of quadratic programming to solve it and the algorithm DW-IFLSTSVM-CIL is proposed. The experimental results and corresponding statistical analyses on some benchmark class imbalance datasets verify that the proposed algorithm can obtain better performance because the proposed method fully takes the inherent distribution of the training datasets into account.