作　　者： ; ;

机构地区： 暨南大学计算机科学系

出　　处： 《计算机应用》 2005年第6期1327-1329,共3页

摘　　要： 探讨了核Fisher判决分析算法(KernelFisherDiscriminantAnalysis,KFDA),并提出了一种基于KFDA的高性能多类分类算法。在进行多类分类时,首先通过一个非线性映射将训练样本映射到一个高维的核空间中,建立一个KFDA子空间,在该高维空间中,不同类别的样本之间的差异增大,同类样本聚集在一起,因此,在这个高维核空间中,就可以利用简单的最近邻法进行多类分类。实验结果表明,该算法在保证分类精度的条件下提高了分类器的训练和分类的速度。 In the paper, theorys of Kernel Fisher Discriminant Analysis (KFDA) were researched and analysed. After applying KFDA in feature extracting, the performance of KFDA and that of Linear Fisher Discriminant Analysis (FDA) feature extracting algorithms were compared. Finally, a fast and simple multiclass classification algorithm of KFDA-based was proposed. The algorithm can classify multiclass fast and simply. First of all, multiclass samples were mapped into a high dimension kernel space. In the space, the same class samples were assembled together, the different class samples were perfectly separated. So the multiclass samples can be separate easily. Comparing with One-to-One algorithm and One-to-All algorithm, the experiment results indicate that our algorithm is certainly faster and simpler in classification than other two algorithms.

关 键 词： 核 判决分析 核函数 核空间 支持向量机 多类分类

领　　域： [自动化与计算机技术] [自动化与计算机技术]