摘要
现有的一分类支持向量机算法基于优化最小间隔的思想,只考虑了样本靠近空间原点一侧的噪声,对噪声信息较为敏感。针对该问题,通过优化间隔分布思想,同时考虑样本靠近空间原点和远离空间原点两侧的噪声,提高一分类支持向量机算法的抗噪声能力。为此,提出了一种基于最优间隔分布的一分类学习方法(one-class optimal margin distribution machine,OCODM),该方法通过最大化间隔的均值和最小化间隔方差的方式来优化间隔分布。实验结果表明,相比于现有的一分类支持向量机算法,该方法具有更好的鲁棒性,是现有一分类支持向量机方法的有益补充,能够增强现有方法的抗噪声能力。
The existing one-class support vector machine algorithms are based on the idea of minimum margin.They consider only the noise close to the space origin and are sensitive to noise.To improve the anti-noise ability of the one-class support vector machine through the idea of optimal margin distribution,which considers both of the noise close to the space origin and that far from the space origin,this paper proposed a novel OCODM method.This method maximized the margin and minimized the margin variance to optimize the margin distribution.The experimental results show that compared to the existing one-class support vector machine algorithms,this method has better robustness,and it is a supplement of the existing one-class support vector machine algorithms and can enhance the anti-noise ability of existing methods.
作者
林钧涛
肖燕珊
刘波
Lin Juntao;Xiao Yanshan;Liu Bo(School of Computers,Guangdong University of Technology,Guangzhou 510000,China;School of Automation,Guangdong University of Technology,Guangzhou 510000,China)
出处
《计算机应用研究》
CSCD
北大核心
2023年第9期2749-2754,共6页
Application Research of Computers
基金
国家自然科学基金资助项目(62076074)。
关键词
一分类学习
间隔分布
一分类支持向量机
one-class classification learning
margin distribution
one-class support vector machine
