[1]袁秋云,张仕光,刘士琴,等.基于高斯噪声的孪生近端最小二乘支持向量回归模型研究及应用[J].南京师范大学学报(工程技术版),2022,22(04):019-28.[doi:10.3969/j.issn.1672-1292.2022.04.003]
　Yuan Qiuyun,Zhang Shiguang,Liu Shiqin,et al.Research and Application of Twin Proximal Least Squares Support Vector Regression Model Based on Gaussian Noise[J].Journal of Nanjing Normal University(Engineering and Technology),2022,22(04):019-28.[doi:10.3969/j.issn.1672-1292.2022.04.003]
点击复制

基于高斯噪声的孪生近端最小二乘支持向量回归模型研究及应用
分享到：

南京师范大学学报（工程技术版）[ISSN:1006-6977/CN:61-1281/TN]

卷:
22卷
期数:
2022年04期
页码:
019-28
栏目:
计算机科学与技术
出版日期:
2022-12-15

文章信息/Info

Title:
Research and Application of Twin Proximal Least Squares Support Vector Regression Model Based on Gaussian Noise
文章编号:
1672-1292(2022)04-0019-10
作者:
袁秋云1; 张仕光2; 刘士琴3; 郭双乐4
(1.商丘工学院信息与电子工程学院,河南 商丘 476000)
(2.山东管理学院信息工程学院,山东 济南 250357)
(3.衡水学院数学与计算机学院,河北 衡水 053000)
(4.滨州学院 信息工程学院,山东 滨州 256600)
Author(s):
Yuan Qiuyun1; Zhang Shiguang2; Liu Shiqin3; Guo Shuangle4
(1.School of Information and Electronic Engineering,Shangqiu Institute of Technology,Shangqiu 476000,China)
(2.School of Information Engineering,Shandong Management University,Jinan 250357,China)
(3.College of Mathematics and Computer science,Hengshui University,Hengshui 053000,China)
(4.School of Information Engineering,Binzhou University,Binzhou 256600,China)
关键词:
孪生近端最小二乘支持向量回归机; 高斯噪声; 风速预测; 等式约束
Keywords:
twin proximal least squares support vector regression; Gaussian noise; wind speed prediction; equality constraint
分类号:
TP301
DOI:
10.3969/j.issn.1672-1292.2022.04.003
文献标志码:
A
摘要:
孪生近端最小二乘支持向量回归机(twin proximal least squares support vector regression,TPLSSVR)是在PLSSVR模型的理论基础上结合TSVR模型的双超平面理念而设计的一种新的回归模型. 本文利用TPLSSVR模型框架构建了基于高斯噪声的孪生近端最小二乘支持向量回归模型. 该模型利用最小二乘方法,分别加入正则化项b21、b22,将一个不等式约束问题转化为两个更简单的等式约束问题,提高了模型的泛化能力,有效提升了预测精度. 为解决模型的参数选择问题,选用收敛速度快、鲁棒性好的粒子群优化算法对模型参数进行优化选择. 将新构建的模型应用于人工数据集和风速数据集,实验结果显示该模型有较好的预测效果.
Abstract:
Twin proximal least squares support vector regression(TPLSSVR)is a new regression model designed on the basis of PLSSVR model and TSVR model's double hyperplane concept. In this paper,we use the above model framework to build the twin proximal least squares support vector regression model based on Gaussian noise. The least square method is introduced and the regularization terms b21 and b22 are added respectively. It transforms an inequality constraint problem into two simpler equality constraint problems,which not only improves the generalization ability,but also effectively improves the prediction accuracy. In order to solve the parameter selection problem of the model,the particle swarm optimization algorithm with fast convergence speed and good robustness is selected to optimize its parameters. The new model is applied to artificial data set and wind speed data set,the experimental results show that the model has better prediction effect.

参考文献/References:

[1]VAPNIK V N. The Nature of Statistical Learning Theory[M]. New York,USA:Springer NY,1995.
[2]CORTES C,VAPNIK V. Support-vector networks[J]. Machine Learning,1995,20(3):273-297.
[3]SUYKENS J A K,VANDEWALLE J. Least squares support vector machine classifiers[J]. Neural Processing Letters,1999,9(3):293-300.
[4]FUNG G,MANGASARIAN O L. Proximal support vector machine classifiers[C]//Proceedings of the 7th ACM SIGKDD International Conference on Knowlege Discovery and Data Mining. San Francisco,USA:ACM,2001.
[5]JAYADEVA,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.
[6]PENG X J. TSVR:an efficient twin support vector machine for regression[J]. Neural Networks,2010,23(3):365-372.
[7]PENG X J,CHEN D. PTSVRs:regression models via projection twin support vector machine[J]. Information Sciences,2018,435:1-14.
[8]杨晓敏. 改进灰狼算法优化支持向量机的网络流量预测[J]. 电子测量与仪器学报,2021,35(3):211-217.
[9]叶黎明,陈素根. 基于粒子群算法的投影孪生支持向量机[J]. 淮北师范大学学报(自然科学版),2021,42(1):29-35.
[10]顾吉峰,王蓓. 基于改进粒子群算法的孪生支持向量机[J]. 计算机工程与设计,2020,41(11):3078-3082.
[11]DING S F,ZHANG X K,YU J Z. Twin support vector machines based on fruit fly optimization algorithm[J]. International Journal of Machine Learning and Cybernetics,2016,7(2):193-203.
[12]DING S F,AN Y X,ZHANG X K,et al. Wavelet twin support vector machines based on glowworm swarm optimization[J]. Neurocomputing,2017,225:157-163.
[13]张谢锴,丁世飞. 基于马氏距离的孪生多分类支持向量机[J]. 计算机科学,2016,43(3):49-53.
[14]SARTAKHTI J S,AFRABANDPEY H,SARAEE M. Simulated annealing least squares twin support vector machine(SA-LSTSVM)for pattern classification[J]. Soft Computing,2017,21(15):4361-4373.
[15]黄宏运,吴礼斌,李诗争. GA优化的SVM在量化择时中的应用[J]. 南京师范大学学报(工程技术版),2017,17(1):72-79.
[16]WANG K N,PEI H M,DING X S,et al. Robust proximal support vector regression based on maximum correntropy criterion[J]. Scientific Programming,2019(3):7102946.
[17]张仕光,周婷,刘超,等. 高斯噪声特性区间ν-支持向量回归机[J]. 山西大学学报(自然科学版),2020,43(4):880-884.
[18]余乐安. 基于最小二乘近似支持向量回归模型的电子商务信用风险预警[J]. 系统工程理论与实践,2012,32(3):508-514.
[19]HU Q H,ZHANG S G,YU M,et al. Short-term wind speed or power forecasting with heteroscedastic support vector regression[J]. IEEE Transactions on Sustainable Energy,2016,7(1):241-249.

备注/Memo

备注/Memo:
收稿日期:2022-08-08.
基金项目:山东省自然科学基金面上项目(ZR2022MF242)、河南省高等学校重点科研项目(21A520020).
通讯作者:郭双乐,博士,副教授,研究方向:模式识别. E-mail:guoshuangle@aliyun.com
更新日期/Last Update: 2022-12-15