Learning SVM with weighted maximum margin criterion for classification of imbalanced data

Near-Bayesian Support Vector Machines for imbalanced data classification with equal or unequal misclassification costs

“…The slightly different Asymmetric Kernel Scaling (AKS), which also differently enlarges areas on both sides of the separating hyperplane so as to compensate for the data skew, was proposed by Maratea, Petrosino, and Manzo (2014) and later adapted for multi-class imbalanced problems by Zhang, Fu, Liu, and Chen (2014). Zhao, Zhong, and Zhao (2011) maximized the Weighted Maximum Margin Criterion (WMMC) to select the proper kernel for imbalanced datasets. Phoungphol (2013) discussed a modification of SVM which minimizes an approximation of the gmeans measure of Kubat et al (1997) along with margin maximization.…”

Research on Dynamic Cost-Sensitive SVM Classifier based on Chaos Particle Swarm Optimization Algorithm

“…1 .This paper proposes dynamic cost-sensitive SVM classifier based on chaos particle swarm optimization algorithm (CPDC_SVM), and STA_SVM [1], C_SVM [3], FUSSY_SVM [4] are the other algorithms for unbalanced data classification. The positive and negative samples are set as 1: 9, and initial dynamic cost use the artificial interval.…”

“…Mordelet proposed a new method for PU learning with a conceptually simple implementation based on bootstrap aggregating (bagging) techniques [2]. Zhao proposed a weighted maximum margin criterion to optimize the data-dependent kernel, which makes the minority class more clustered in the induced feature space [3]. The paper [4] proposed the structural imbalance SVM, [5] and [6] improved directly C-SVM model, and used the different penalty factors for the different classes.…”

Least squares one-class support vector machine on fuzzy set

“…One type mainly contains under-sampling from majority class [4,5] or over-sampling from minority class [6,7]. The other type is to modify the learning algorithms such as adjusting the cost method [8,9], kernel-based method [10], margin calibration [11]. One-class support vector machine (one-class SVM) is widely used in the heavily class imbalanced problems, such as the context of information retrieval [12], hidden information [13], outlier detection [14] and so on.…”