LDAMSS: Fast and efficient undersampling method for imbalanced learning

LDAMSS: Fast and efficient undersampling method for imbalanced learning
复制标题

LDAMSS:快速高效的不平衡学习欠采样方法

DOI:
10.1007/s10489-021-02780-x
复制
发表时间:
2021-09
期刊:
Applied Intellligence
影响因子:
--
通讯作者:
曾京京
曾京京
中科院分区:
其他
文献类型:
--
作者:
梁廷;徐婕;邹斌;王展;曾京京

文献摘要

参考文献

相似文献

提出了一种基于线性判别分析(LDA)和马尔可夫选择采样(MSS)的欠采样方法。该方法包括两个阶段。第一阶段是根据LDA分类器的G均值多次调整分类边界的位置。第二阶段是通过MSS从当前多数类中提取“重要”训练样本。我们将所提出的欠采样方法应用于Xgboost并研究其学习性能。在二进制数据集上的实验结果表明,与其他方法相比,基于LDAMSS的Xgboost(X-LDAMSS)不仅在三个度量(F-measure、G-mean和AUC)上具有更好的性能,而且总时间更短。我们还将X-LDAMSS应用于多分类问题,并给出了一些有益的讨论。
In this article, a novel undersampling method based on linear discriminant analysis (LDA) and Markov selective sampling (MSS) is proposed. This method contains two stages. The first stage is to adjust the position of classification boundary according to the G-mean of LDA classifier for many times. The second stage is to extract the “important” training samples from the current majority class by MSS. We apply the proposed undersampling method to Xgboost and study its learning performance. The experimental results of binary class datasets show that compared to other methods, Xgboost based on LDAMSS (X-LDAMSS) not only has better performance in three metrics (F-measure, G-mean, and AUC), but also has less total time. We also apply X-LDAMSS to multi-classification problem and present some useful discussions.
DOI: --
发表时间: 1997
期刊: --
影响因子: --
作者:
M. Kubát;S. Matwin
通讯作者: M. Kubát;S. Matwin
DOI: --
发表时间: 2010
期刊: --
影响因子: --
作者:
Mohammed Khalilia;S. Chakraborty;M. Popescu
通讯作者: Mohammed Khalilia;S. Chakraborty;M. Popescu
DOI: 10.1007/978-3-642-19315-6_13
发表时间: 2010-11
期刊: --
影响因子: --
作者:
Chen Change Loy;T. Xiang;S. Gong
通讯作者: Chen Change Loy;T. Xiang;S. Gong
DOI: 10.1016/j.eswa.2008.06.108
发表时间: 2009-04
期刊: Expert Syst. Appl.
影响因子: --
作者:
Show-Jane Yen;Yue-Shi Lee
通讯作者: Show-Jane Yen;Yue-Shi Lee
DOI: 10.1109/tip.2019.2905081
发表时间: 2019-07-01
影响因子: 10.6
作者:
Kang, Byeongkeun;Nguyen, Truong Q.
通讯作者: Nguyen, Truong Q.