中文摘要：

ROC分析方法已在各个领域有了广泛的应用,但主要应用于两类问题。在三类问题的推广上面临着分析空间高维化,难以理解,表示困难,计算复杂度高等问题。本文基于SVM（支持向量机）分类方法,提出一种新的降维方法,并运用到三类ROC分析中,在避免了上述不足的同时,也继承了ROC分析方法在两类问题中的优点。

英文摘要：

ROC（ Receiver Operating Characteristic ） analysis method has been widely used in various fields , but it is mainly ap-plied to two-class task.In the three-class task, it is difficult to show and understand , and the computation complexity is hardly to accept .This paper proposes a new dimension reduction method , which is based on SVM （ Support Vector Machine ） classifier , to exploit the ROC analysis method in three-class task, which avoids the above problems and inherits the advantages of ROC analysis method in two-class task.