改进的支持向量机分类算法

Improved algorithm for support vector machines

在研究了标准SVM分类算法后,本文提出了一种快速的支持向量机分类方法。该方法通过解决两类相关的SVM问题,找到两个非平行的平面,其中每个平面靠近其相应的类样本点,远离另一类样本点,最后通过这两个平面找到一个将两类样本分开的最优平面。在处理非线性情况下,引入一种快速核函数分类方法。使用该算法可以使分类的速度得到很大提高,针对实际数据集的实验表明了该算法的有效性。

A new effective approach to optimize the SVM classifier is proposed after the research on SVM classifier is researched. By solving two related SVM-type problems, each of which is much smaller, find two unparallel planes, then gain one plane through the two planes. Effectiveness of this algorithm is much faster than the standard SVM classification method. Numerical experiments demonstrate the effectiveness of the method over convertional methods.