基于样本权重的v -支持向量机

doi:10.3969/j.issn.1000-1565.2018.02.011

河北大学学报(自然科学版) ›› 2018, Vol. 38 ›› Issue (2): 185-193.DOI: 10.3969/j.issn.1000-1565.2018.02.011

基于样本权重的v -支持向量机

李凯¹,翟璐璐¹,崔丽娟²

收稿日期:2017-08-30 出版日期:2018-03-25 发布日期:2018-03-25
作者简介:李凯(1963—),男,河北保定人,河北大学教授,博士,主要从事机器学习、数据挖掘和模式识别研究. E-mail:likai@hbu.edu.cn
基金资助:
国家自然科学基金资助项目(61375075);河北省自然科学基金资助项目(F2018201060);河北大学自然科学研究计划项目(799207217074)

v-Support vector machine with weight of samples

LI Kai¹,ZHAI Lulu¹,CUI Lijuan²

1.School of Cyber Security and Computer, Hebei University, Baoding 071002, China; 2.Library, Hebei University, Baoding 071002, China

Received:2017-08-30 Online:2018-03-25 Published:2018-03-25

摘要/Abstract

摘要： v〓 -支持向量机克服了传统支持向量机选取参数的困难问题,然而,该方法并未考虑不同样本在训练中的作用,从而导致该方法对噪声或孤立点具有较强的敏感性,使得训练易出现过拟合现象.为了解决这些问题,针对不同样本的作用,通过引入样本的权重,获得了一种改进的v〓 -支持向量机模型,使用Lagrange方法对该模型求解,获得了一种支持向量机分类器.实验中选取来自于UCI数据库的10个标准数据集,针对2种不同的确定样本权重的方法,验证了提出方法的有效性,并与C-SVM和v〓 -SVM进行了性能比较.

关键词: 支持向量机, v-支持向量机, 权重, 模糊聚类, 核策略

Abstract: The v-support vector machine(v-SVM)overcomes the difficult problem with selection of parameter for the traditional support vector machine.However,this method does not take into account the effect of different samples in the process of training,which leads to a strong sensitivity to noise or outlier points so that training is easy to be over-fit.In order to solve this problem,an improved v-SVM model is obtained by introducing the weight of the samples for the effect of different samples.A Lagrange method is used to solve the model,and a support vector machine classifier is obtained.To show the effectiveness of the presented method,the experiments are conducted using at two kinds of methods for determining weights of samples on 10 standard data sets from UCI repository,and compared with the performance of C-SVM and v-SVM.

Key words: support vector machine, v-fuzzy support vector machine, weight, fuzzy clustering, kernel track

中图分类号:

TP319

李凯,翟璐璐,崔丽娟. 基于样本权重的v -支持向量机[J]. 河北大学学报(自然科学版), 2018, 38(2): 185-193.

LI Kai,ZHAI Lulu,CUI Lijuan. v-Support vector machine with weight of samples[J]. Journal of Hebei University (Natural Science Edition), 2018, 38(2): 185-193.

参考文献

[1] VAPNIK V N.The nature of statistical learning theory [M].New York: Springer,1995.
[2] SCHOLKOPF B,SMOLA A J,WILLIAMSON R C,et al.New support vector algorithms [J].Neural Computation,2000,12(5): 1207-1245.DOI: 10.1162/089976600300015565.
[3] BLOOM V,GRIVA L,KWON B,et al.Exterior-point method for support vector machines[J].IEEE Transactions on Neural Networks and Learning Systems,2014,25(7): 1390-1393.
[4] LIN C F,WANG S D.Fuzzy support vector machines [J].IEEE Transaction on Neural Networks,2002,13(2): 464-471.DOI: 10.1109/72.991432.
[5] YANG X W,ZHANG G Q,LU J.A kernel fuzzy c-means clustering-based fuzzy support vector machine algorithm for classification problems with outliers or noises [J].IEEE Transactions on Fuzzy Systems,2011,19(1): 105-115.
[6] XU Y T.A rough margin-based linear υ support vector regression [J].Statistics and Probability Letters,2012,82(3):528-534.
[7] CHEN D G,HE Q,WANG X Z. FRSVMs: Fuzzy rough set based support vector machines [J].Fuzzy Sets and Systems,2010,161: 596-607.
[8] PLATT J.Fast training of support vector machines using sequential minimal optimization[C] //SCHÖLKOPF B,BURGES C J C,SMOLA A J(Eds.).Advances in Kernel Methods—Support Vector Learning.MIT Press,Cambridge,MA,1999:185-208.
[9] JOACHIMS T.Making large-scale SVM learning practical[C] //SCHÖLKOPF B,BURGES C J C,SMOLA A J(Eds.).Advances in Kernel Methods: Support Vector Machine.MIT Press,Cambridge,MA,1999,169-184.
[10] YEUNG D,WANG D,NG W,et al.Structured large margin machines: sensitive to data distributions [J].Machine Learning,2007,68(2):171-200.
[11] XUE H,CHEN S C,YANG Q.Structural regularized support vector machine: a framework for structural large margin classifier[J].IEEE Transactions on Neural Networks,2011,22(4):573-587.
[12] ZHANG L,ZHOU W D.Fisher-regularized support vector machine[J].Information Sciences,2016,343-344:79-93.
[13] CHAPELLE O.Training a Support Vector Machine in the Primal[J].Neural Computation,2007,19(5):1155-1178.
[14] SUYKENS J,VANDEWALLE J.Least squares support vector machine classifiers [J].Neural Processing Letters,1999,9(3): 293-300.DOI: 10.1023/ A: 1018628609742.
[15] BLAKE C,MERZ C J.UCI Repository for machine learning databases[EB/OL].(1998-01-12)[2014-09-06].IrvineCA:University of California,Department of Information and Computer Sciences.http://www.ics.uci.edu/mlearn/MLRep.

基于样本权重的v -支持向量机

v-Support vector machine with weight of samples

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	郭亮,郭子雪,贾洪涛,范若禹. 基于皮尔逊相关系数与SVM的居民窃电识别[J]. 河北大学学报(自然科学版), 2023, 43(4): 357-363.
[2]	黄元生,田立霞,孙仕泽,邓佳佳,赵恒凤. 基于改进支持向量机的轨道交通光伏发电预测[J]. 河北大学学报(自然科学版), 2021, 41(3): 238-244.
[3]	杨森,张青,高立艾. 风-光-抽水蓄能联合发电系统的优化运行[J]. 河北大学学报(自然科学版), 2021, 41(1): 106-112.
[4]	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.
[5]	董斌,王云涛,贾立男,王娅南. 改进的PSO优化SVM的病理图像分类算法[J]. 河北大学学报(自然科学版), 2020, 40(5): 543-551.
[6]	翟俊海, 田石, 张素芳, 王谟瀚, 宋丹丹. 基于MapReduce和Spark的大数据模糊K-means算法比较[J]. 河北大学学报(自然科学版), 2020, 40(4): 433-440.
[7]	贾玲,黄丽华,刘雪飞,韩璟琳,唐巍. 基于模糊理论和组合权重的光伏组件健康状况评估[J]. 河北大学学报(自然科学版), 2020, 40(1): 95-103.
[8]	鲁淑霞,张罗幻, 蔡莲香,孙丽丽. 带有方差减小的加权零阶随机梯度下降算法[J]. 河北大学学报(自然科学版), 2019, 39(5): 536-546.
[9]	郭子雪,林鹏. 属性权重未知情形下的区间直觉模糊多属性决策方法[J]. 河北大学学报(自然科学版), 2019, 39(1): 1-5.
[10]	杜瑞忠,赵芳华. 云环境下密文策略的权重属性多中心加密方案[J]. 河北大学学报(自然科学版), 2017, 37(5): 531-536.
[11]	司文静,封喜波,耿立艳,张占福. 基于ADPSO算法优化LSSVM的高速公路交通量预测方法[J]. 河北大学学报(自然科学版), 2017, 37(3): 302-308.
[12]	高学伟,付忠广,孙力,张刚. 基于Hadoop分布式支持向量机球磨机大数据建模[J]. 河北大学学报(自然科学版), 2017, 37(3): 309-315.
[13]	李凯,顾丽凤,张雷. 引入结构信息的模糊支持向量机[J]. 河北大学学报(自然科学版), 2017, 37(2): 187-193.
[14]	鲁淑霞,佟乐,朱晨旭. 添加Universum数据的最小二乘投影双支持向量机[J]. 河北大学学报(自然科学版), 2016, 36(1): 94-99.
[15]	陈昀,毕海岩. 基于多特征融合的中文评论情感分类算法[J]. 河北大学学报(自然科学版), 2015, 35(6): 651-656.