基于一类分类的线性规划支持向量回归算法  

Linear Programming Support Vector Regression Method Based on One-class Classification

作　　者：孙德山[1] 赵君[1] 高釆葵 郑平[1] 刘小菲[1] 

机构地区：[1]辽宁师范大学数学学院,大连116029

出　　处：《计算机科学》2014年第4期230-232,243,共4页Computer Science

基　　金：国家自然科学基金项目(61105059)资助

摘　　要：根据一类分类思想,提出一种基于线性规划的支持向量回归算法,该算法揭示了一类分类和回归之间的关系。实验在一个正弦函数、一个混沌时间序列和一个实际的数据上进行。实验结果表明,所给算法的泛化性能优于标准的支持向量回归算法(ε-SVR)、线性规划支持向量回归算法(LP-SVR)和最小二乘支持向量回归算法(LS-SVR),实验结果也说明了所给算法的有效性和可行性。A new support vector regression algorithm based on linear programming was proposed according to one-class classification,which can more uncover the relation between one-class classification and regression.The tests were perform on sine function,chaos time series and real world data sets.Experiments show that the new method has comparable or better generalization performance than e-insensitive Support Vector Regression （e-SVR）,Linear Programming Support Vector Regression （LP-SVR） and Least squares support vector regression （LS-SVR）,and also show that the proposed method is feasible and valid.

关 键 词：一类分类 支持向量机 回归算法 核函数 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]