PROBLEM TO BE SOLVED: To provide a kernel main component analysis method capable of reducing a calculation amount, and capable of reducing lowering of calculation precision getting low in accompaniment to the reduction of the calculation amount, compared with conventional one.;SOLUTION: This main component analysis method includes a selection step for selecting the m-number of sample vectors {y1, y2 to ym} from n-number of sample vectors {x1, x2 to xn}, a design step for calculating the r-number of eigenvectors {z1, z2 to zr}, by solving a generalized eigenvalue problem KxyTKxyz=Kyz, and an evaluation step for calculating a feature vector y=[z1, z2 to zr]Tx of an evaluation-objective vector x.;COPYRIGHT: (C)2011,JPO&INPIT
展开▼
机译:解决的问题:提供一种内核主成分分析方法,该方法能够减少计算量,并且与传统方法相比,能够减少随着计算量的减少而降低的计算精度。成分分析方法包括一个选择步骤,用于从n-个样本向量中选择m个样本向量{y 1 Sub>,y 2 Sub>至y m Sub>}样本向量{x 1 Sub>,x 2 Sub>至x n Sub>}的数量,用于计算特征向量{z <通过解决广义特征值问题K xy Sub> T Sub> 1 Sub>,z 2 Sub>到z r Sub>}。 Sup> K xy Sub> z = K y Sub> z,以及计算特征向量y = [z 1 Sub>,z 的评估步骤评估目标向量x的2 Sub>到z r Sub>] T Sup> x ; COPYRIGHT:(C)2011,JPO&INPIT
展开▼