A weighted twin support vector regression

A weighted twin support vector regression
复制标题

加权孪生支持向量回归

DOI:
10.1016/j.knosys.2012.03.013
复制
发表时间:
2012-09
影响因子:
8.8
通讯作者:
Wang, Laisheng
Wang, Laisheng
中科院分区:
计算机科学1区
文献类型:
--
作者:
Xu, Yitian;Wang, Laisheng

文献摘要

参考文献

被引文献

相似文献

双支持向量回归(TSVR)是一种新的回归算法,旨在为训练点寻找对ε不敏感的上下界函数。为了做到这一点,人们需要解决一对较小的二次规划问题(QPP),而不是一个单一的大的经典SVR。然而,对TSVR中的样品给予相同的惩罚。实际上,不同位置的样本对边界函数的影响是不同的。然后,我们提出了一个加权TSVR在本文中,在不同的位置的样本提出了不同的惩罚。最终的回归量可以在一定程度上避免过拟合问题,并具有很强的泛化能力。在一个人工数据集和九个基准数据集上的数值实验证明了该算法的可行性和有效性。
Twin support vector regression (TSVR) is a new regression algorithm, which aims at finding ϵ-insensitive up- and down-bound functions for the training points. In order to do so, one needs to resolve a pair of smaller-sized quadratic programming problems (QPPs) rather than a single large one in a classical SVR. However, the same penalties are given to the samples in TSVR. In fact, samples in the different positions have different effects on the bound function. Then, we propose a weighted TSVR in this paper, where samples in the different positions are proposed to give different penalties. The final regressor can avoid the over-fitting problem to a certain extent and yield great generalization ability. Numerical experiments on one artificial dataset and nine benchmark datasets demonstrate the feasibility and validity of our proposed algorithm.
DOI: 10.1016/j.knosys.2008.03.044
发表时间: 2008-12
期刊: Knowl. Based Syst.
影响因子: --
作者:
Wen Zhang;Taketoshi Yoshida;Xijin J. Tang
通讯作者: Wen Zhang;Taketoshi Yoshida;Xijin J. Tang
DOI: 10.1016/j.ins.2007.12.012
发表时间: 2008-05
期刊: Inf. Sci.
影响因子: --
作者:
Junhua Zhang;Yuanyuan Wang
通讯作者: Junhua Zhang;Yuanyuan Wang
DOI: 10.1016/j.spl.2011.11.007
发表时间: 2012-03
影响因子: 0.8
作者:
Yitian Xu
通讯作者: Yitian Xu
DOI: 10.1007/s00500-006-0130-2
发表时间: 2007-02
期刊: Soft Computing
影响因子: 4.1
作者:
Jayadeva;Reshma Khemchandani;S. Chandra
通讯作者: Jayadeva;Reshma Khemchandani;S. Chandra
DOI: 10.1016/j.ins.2010.06.039
发表时间: 2010-10
期刊: Inf. Sci.
影响因子: --
作者:
X. Peng
通讯作者: X. Peng