基于支持向量机的数据库学习算法

文中介绍了一个利用数据库中的大量数据进行决策的方法。对于仅涉及数据库中部分数据的问题，对数据库中与当前问题相关的数据采用具有强泛化能力的支持向量机方法学习分类规则和回归函数，完成对当前问题的分类和估值。支持向量机算法用非线性映射把数据映射到一个高维特征空间，在高维特征空间进行线性分类和线性回归，将原问题转化为一个凸次优化问题。上述算法实现了一个隧道工程支护设计系统，并取得了较好的效果。

DATABASE LEARNING ALGORITHMS BASED ON SUPPORT VECTOR MACHINE

A decision making method using large amount of data in databases is introduced in this paper. For the problems concerning a part of data in a database only, the support vector machine with high generalization ability is adopted to learn classification rule and regression function from the relative data to current problem in the database, in order to perform the classification and evaluation tasks. In the support vector machine, the data are mapped into a high dimensional feature space with a nonlinear mapping, in which linear classification and regression are performed. This is a convex quadratic optimization problem. With the above algorithms introduced, a tunnel engineering supporting design system is realized and a good result is obtained.