Anti-Noise Nonparallel Support Vector Machine with Margin Distribution

LIU Li-ming; LI Ping; CHU Mao-xiang; CAI Hong-bin

doi:10.12263/DZXB.20220268

您当前的位置：

首页 >

文章列表页 >

Anti-Noise Nonparallel Support Vector Machine with Margin Distribution

PAPERS | 更新时间：2025-12-08

- Anti-Noise Nonparallel Support Vector Machine with Margin Distribution
- ACTA ELECTRONICA SINICA Vol. 51, Issue 7, Pages: 1889-1897(2023)
- 作者机构：
  
  辽宁科技大学电子与信息工程学院，辽宁鞍山 114051
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China(61673199);Natural Science Foundation of Liaoning Province(2022-MS-353);Basic Scientific Research Project of Education Department of Liaoning Province(LJKMZ20220640);Natural Science Foundation of Liaoning Province(2021-BS-246)
- DOI：10.12263/DZXB.20220268
  CLC： TP18
- Received：14 March 2022，
  
  Revised：2022-10-16，
  
  Published：25 July 2023
- 稿件说明：
移动端阅览
刘历铭,李平,储茂祥等.具有间隔分布的抗噪声非平行支持向量机[J].电子学报,2023,51(07):1889-1897.

LIU Li-ming,LI Ping,CHU Mao-xiang,et al.Anti-Noise Nonparallel Support Vector Machine with Margin Distribution[J].ACTA ELECTRONICA SINICA,2023,51(07):1889-1897.
刘历铭,李平,储茂祥等.具有间隔分布的抗噪声非平行支持向量机[J].电子学报,2023,51(07):1889-1897. DOI： 10.12263/DZXB.20220268.

LIU Li-ming,LI Ping,CHU Mao-xiang,et al.Anti-Noise Nonparallel Support Vector Machine with Margin Distribution[J].ACTA ELECTRONICA SINICA,2023,51(07):1889-1897. DOI： 10.12263/DZXB.20220268.

摘要

针对非平行支持向量机（NonParallel Support Vector Machine，NPSVM）对噪声敏感和忽略了数据分布结构的问题，提出了一种具有间隔分布的抗噪声非平行支持向量机（Anti-Noise NPSVM with Margin Distribution， MD-ANPSVM）分类模型.在MD-ANPSVM模型中，每个优化问题同时最小化两类样本的基于L1范数的绝对损失和改进的铰链损失，这可以保证模型的稳定性，减小噪声和异常值的影响.此外，在MD-ANPSVM模型中，采用一阶和二阶统计量来描述训练数据的间隔分布信息，并试图同时最大化间隔均值和最小化间隔方差，这进一步提高了模型的泛化性能.最终，我们在不同的数据集上进行了对比实验.实验结果显示，MD-ANPSVM模型具有较强的泛化能力和强鲁棒性.

Abstract

Because nonparallel support vector machine (NPSVM) is sensitive to noise and ignores the distributing structure of data

an anti-noise NPSVM with margin distribution (MD-ANPSVM) model is proposed. In MD-ANPSVM

each optimization problem simultaneously minimizes the L1-norm loss and improved hinge loss

which can ensure the stability of the model and reduce the adverse impact of noise and outliers. In addition

in MD-ANPSVM

the margin distribution described by the first- and second-order statistics is introduced. Each optimization problem simultaneously maximizes the margin mean and minimizes the margin variance

which results in better generalization performance. The experimental results on the UCI datasets and steel surface defects dataset show that MD-ANPSVM can achieve better generalization ability and strong robustness.

关键词

Keywords

references

VAPNIK V N . The Nature of Statistical Learning Theory [M]. Berlin : Springer Science & Business Media , 1999 .

DENG N , TIAN Y , ZHANG C . Support Vector Machines: Optimization Based Theory, Algorithms, and Extensions [M]. Boca Raton : CRC Press , 2012 .

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 .

DING S , HUA X , YU J . An overview on nonparallel hyperplane support vector machine algorithms [J]. Neural Computing and Applications , 2014 , 25 ( 5 ): 975 - 982 .

TIAN Y , QI Z , JU X , et al . Nonparallel support vector machines for pattern classification [J]. IEEE Transactions on Cybernetics , 2013 , 44 ( 7 ): 1067 - 1079 .

HUANG X , SHI L , SUYKENS J A K . Support vector machine classifier with pinball loss [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2013 , 36 ( 5 ): 984 - 997 .

李凯 , 李慧 . 基于 pinball 损失的结构模糊孪生支持向量机 [J]. 电子学报 , 2019 , 47 ( 10 ): 2221 - 2227 .

LI Kai , LI Hui . Structural fuzzy twin support vector machine with pinball loss [J]. Acta Electronica Sinica , 2019 , 47 ( 10 ): 2221 - 2227 . (in Chinese)

YEUNG D S , WANG D , NG W W Y , et al . Structured large margin machines: Sensitive to data distributions [J]. Machine Learning , 2007 , 68 ( 2 ): 171 - 200 .

TANG L , TIAN Y , LI W , et al . Structural improved regular simplex support vector machine for multiclass classification [J]. Applied Soft Computing , 2020 , 91 : 106235 .

ZHANG T , ZHOU Z H . Large margin distribution machine [C]// Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining . NY : ACM , 2014 : 313 - 322 .

PENG X , XU D , KONG L , et al . L1-norm loss based twin support vector machine for data recognition [J]. Information Sciences , 2016 , 340 : 86 - 103 .

袁亚湘 , 孙文瑜 . 最优化理论与方法 [M]. 北京 : 科学出版社 , 1997 .

DENG N , TIAN Y , ZHANG C . Support Vector Machines: Optimization Based Theory, Algorithms, and Extensions [M]. Boca Raton : CRC Press , 2012 .

SCHOLKOPF B , SMOLA A J . Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond [M]. Cambridge : MIT Press , 2018 .

LIN C F , WANG S D . Fuzzy support vector machines [J]. IEEE Transactions on Neural Networks , 2002 , 13 ( 2 ): 464 - 471 .

DUA D , TANISKIDOU E K . UCI machine learning repository, 2017 [OL]. [ 2022-10-16 ]. http://archive.ics.uci.edu/ml/ http://archive.ics.uci.edu/ml/ .

The Math Works (MATLAB 2016 b), Inc [OL]. [2022-10-16] . http://www.mathworks.com http://www.mathworks.com .

DEMSAR J . Statistical comparisons of classifiers over multiple data sets [J]. The Journal of Machine Learning Research , 2006 , 7 : 1 - 30 .

HE Y , SONG K , MENG Q , et al . An end-to-end steel surface defect detection approach via fusing multiple hierarchical features [J]. IEEE Transactions on Instrumentation and Measurement , 2019 , 69 ( 4 ): 1493 - 1504 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Multi-Graph Learning Based on Structure-Aware

High Correct Recognition Rate Classifier Design with Appropriate Rejection Mechanism

A Survey on Visible-infrared Cross-modality Person Re-identification

A Theoretical Result on the Generalized Optimal Set of Statistically Uncorrelated Discriminant Vectors

Related Author

FU Dong-lai

GAO Ze-an

YANG Guo-wei

WAN Ming-hua

LAI Zhi-hui

ZHANG Fan-long

WONG Wai-keung

LI Zhi-yong

Related Institution

School of Software， North University of China

School of Electronic Information, Qingdao University

School of Information Engineering, Nanjing Audit University

School of Computer Science and Software Engineering, Shenzhen University

Hong Kong Polytechnic University, Kowloon

⁰