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

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.