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  

Research and Application of Twin Proximal Least Squares Support Vector Regression Model Based on Gaussian Noise

作　　者：袁秋云 张仕光 刘士琴[3] 郭双乐[4] Yuan Qiuyun;Zhang Shiguang;Liu Shiqin;Guo Shuangle(School of Information and Electronic Engineering,Shangqiu Institute of Technology,Shangqiu 476000,China;School of Information Engineering,Shandong Management University,Jinan 250357,China;College of Mathematics and Computer science,Hengshui University,Hengshui 053000,China;School of Information Engineering,Binzhou University,Binzhou 256600,China)

机构地区：[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

出　　处：《南京师范大学学报（工程技术版）》2022年第4期19-28,共10页Journal of Nanjing Normal University(Engineering and Technology Edition)

基　　金：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).

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b_(1)^(2)、b_(2)_(2),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.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 b_(1)^(2)andb_(2)_(2)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.

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 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]