中文摘要：

针对传统的ε-不敏感支持向量回归机（e—insensitive support vector regression，ε-SVR）未充分考虑局部支持向量对回归预测结果的影响，不利于提高回归预测精度的问题，提出了一种ε—SVR预测误差校正方法。该方法以期望预测值与ε—SVR回归预测值及局部支持向量间的欧氏距离和最小为目标函数，以ε不敏感损失带（ε—tube）宽度为约束条件，通过利用高维特征空间中ε—tube边界上和边界外的局部支持向量对ε-SVR的回归预测值进行误差校正。利用人工产生的不同分布数据集和UCI数据集进行的仿真结果表明，与传统的ε-SVR相比，该文方法具有更高的预测精度和更强的泛化能力。

英文摘要：

The influence of the local support vector on the prediction results is not fully considered in the traditional e-insensitive support vector regression （ε-SVR）, which is not conducive to improve the predictive ac- curacy of regression problems. An error correction method is proposed for ε-SVR, in which the minimum sum of Euclidean distances between ideal values and e-SVR regression values and local support vectors are taken as the objective function, and the width of e-insensitive loss tube （ε-tube） is taken as constraint to correct the error in terms of local support vector on and out of the ε-tube boundary in high dimensional feature space. Simulation u- sing artificial datasets with different distributed and UCI benchmark data sets shows that the proposed method has higher prediction and generalization performance.