一种改进的鲁棒模糊孪生支持向量机算法

doi:10.3778/j.issn.1002-8331.2204-0496

摘要/Abstract

摘要： 针对模糊孪生支持向量机算法（FTSVM）对噪声仍然敏感，容易过拟合以及不能有效区分支持向量和离群值等问题，提出了一种改进的鲁棒模糊孪生支持向量机算法（IRFTSVM）。将改进的[k]近邻隶属度函数和基于类内超平面的隶属度函数结合，构造了一种新的混合隶属度函数；在FTSVM算法的目标函数中引入正则化项和额外的约束条件，实现了结构风险最小化，避免了逆矩阵运算，且非线性问题可以像经典的SVM算法一样直接从线性问题扩展而来；将铰链损失函数替换为pinball损失函数，以此降低对噪声的敏感性。此外，在UCI数据集和人工数据集上对该算法进行评估，并与SVM、TWSVM、FTSVM、PTSVM和TBSVM五个算法进行比较。实验结果表明，该算法的分类结果是令人满意的。

关键词: 模糊孪生支持向量机算法（FTSVM）, pinball损失函数, 铰链损失函数, 混合隶属度函数

Abstract: Since the fuzzy twin support vector machine（FTSVM） algorithm is still sensitive to noise and prone to over fitting, as well as cannot effectively distinguish support vectors from outliers. This paper proposes an improved robust fuzzy twin support vector machine（IRFTSVM）. Firstly, a new kind of mixed membership function is constructed by combining the intra-class hyperplanemembership function and the improved [k]-nearest neighbor membership function. Secondly, a regularization term and the additional constraint are brought into the objective function to minimize the structural risk, avoid the computationof inverse matrix, and nonlinear problems can be directed from linear case as the classical SVM algorithm. Finally, the hinge loss function is replaced by the pinball loss function to reduce the noise sensitivity. In addition, the proposed algorithm is assessed and compared with SVM, TWSVM, FTSVM, PTSVM and TBSVM on some UCI datasets and an artificial dataset. The experimental results show that the proposed algorithm is satisfactory.

Key words: fuzzy twin support vector machine（FTSVM）, pinball loss function, hinge loss function, mixed membership function

周裕群, 张德生, 张晓. 一种改进的鲁棒模糊孪生支持向量机算法[J]. 计算机工程与应用, 2023, 59(1): 140-148.

ZHOU Yuqun, ZHANG Desheng, ZHANG Xiao. Improved Robust Fuzzy Twin Support Vector Machine Algorithm[J]. Computer Engineering and Applications, 2023, 59(1): 140-148.

参考文献

[1] CORTES C，VAPNIK V.Support vector machine[J].Machine learning，1995，20（3）：273-297.
[2] MANGASARIAN O，WILD E.Multi?surface proximal support vector machine classification via generalized eigenvalues[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2005，28（1）：69-74.
[3] KHEMCHANDANI R，CHANDRA S.Twin support vector machines for pattern classification[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2007，29（5）：905-910.
[4] LIN C，WANG S.Fuzzy support vector machines[J].IEEE Transactions on Neural Networks，2002，13（2）：464-471.
[5] NEOGY S K.Mathematical programming and game theory for decision making[M].Singapore：World Scientific，2008：131-142.
[6] SHAO Y，ZHANG C，WANG X，et al.Improvements on twin support vector machines[J].IEEE Transactions on Neural Networks，2011，22（6）：962-968.
[7] HUANG X，SHI L，SUYKENS J.Support vector machine classifier with pinball loss[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2014，36（5）：984-997.
[8] XU Y，YANG Z，PAN X.A novel twin support-vector machine with pinball loss[J].IEEE Transactions on Neural Networks and Learning Systems，2017，28（2）：359-370.
[9] TANVEER M，SHARMA S，MUHAMMAD K.Large-scale least squares twin SVM[J].ACM Transactions on Internet Technology（TOIT），2021，21（2）：1-19.
[10] HAZARIKA B B，GUPTA D.Density-weighted support vector machines for binary class imbalance learning[J].Neural Computing and Applications，2021，33（9）：4243-4261.
[11] CHEN S G，WU X J.A new fuzzy twin support vector machine for pattern classification[J].International Journal of Machine Learning and Cybernetics，2018，9（9）：1553-1564.
[12] 王伟，任建华，刘晓帅，等.基于混合隶属度的模糊简约双支持向量机研究[J].计算机工程与应用，2015，51（10）：36-41.
WANG W，REN J H，LIU X S，et al.Research on fuzzy simple twin support vector machine based on hybrid fuzzy membership [J].Computer Engineering and Applications，2015，51（10）：36-41.
[13] 张桂香，费岚，杜喆.基于类内超平面的模糊支持向量机[J].计算机工程与设计，2008，29（12）：3177-3179.
ZHANG G X，FEI L，DU Z.Fuzzy support vector machine based on cluster hyperplane[J].Computer Engineering and Design，2008，29（12）：3177-3179.
[14] 张波，张雪英，陈桂军，等.基于类内超平面距离度量模糊支持向量机的语音情感识别[J].现代电子技术，2018，41（16）：163-167.
ZHANG B，ZHANG X Y，CHEN G J，et al.Speech emotion recognition based on fuzzy support vector machine and measurement of distance to intra-class hyperplane[J].Modern Electronic Technology，2018，41（16）：163-167.
[15] 李凯，李洁.基于pinball损失的一对一加权孪生支持向量机[J].河北大学学报（自然科学版），2020，40（6）：647-656.
LI K，LI J.One-versus-one weighted twin support vector machine with pinball loss function[J].Journal of Hebei University（Natural Science Edition），2020，40（6）：647-656.
[16] 丁胜锋，孙劲光.基于混合模糊隶属度的模糊孪生支持向量机研究[J].计算机应用研究，2013，30（2）：432-435.
DING S F，SUN J G.Research on fuzzy twin support vector machine based on hybrid fuzzy membership[J].Application Research of Computers，2013，30（2）：432-435.
[17] RIPLEY B D.Pattern recognition and neural networks[J].People Post Press，2009，39（2）：233-234.
[18] 刘小生，章治邦.基于改进网格搜索法的SVM参数优化[J].江西理工大学学报，2019，40（1）：5-9.
LIX X S，ZHANG Z B.Parameter optimization of Support Vector Machine based on improved grid search method[J].Journal of Jiangxi University of Science and Technology，2019，40（1）：5-9.