高维数据流形的低维嵌入及嵌入维数研究.pdfVIP

1000-9825/2005/16(08)1423 ©2005 Journal of Software Vol.16, No.8 ∗ 1+ 1 2 1 , , , 1( , 100044) 2(Faculty of Information Technology, University of Technology, Sydney, Australia) Study on the Low-Dimensional Embedding and the Embedding Dimensionality of Manifold of High-Dimensional Data 1+ 1 2 1 ZHAO Lian-Wei , LUO Si-Wei , ZHAO Yan-Chang , LIU Yun-Hui 1(School of Computer and Information Technology, Beijing Jiaotong University, Beijing 100044, China) 2(Faculty of Information Technology, University of Technology, Sydney, Australia) + Corresponding author: Phn: +86-10 E-mail: lw_zhao@, Received 2004-07-14; Accepted 2004-09-08 Zhao LW, Luo SW, Zhao YC, Liu YH. Study on the low-dimensional embedding and the embedding dimensionality of manifold of high-dimensional data. Journal of Software, 2005,16(8):1423−1430. DOI: 10.1360/jos161423 Abstract : Finding meaningful low-dimensional embedded in a high-dimensional space is a classical problem. Isomap is a nonlinear dimensionality reduction method proposed and based on the theory of manifold. It not only can reveal the meaningful low-dimensional structure hidden in the high-dimensional observation data, but can recover the underlying parameter of data lying on a low-dimensional submanifold. Based on the hypothesis that there is an isometric mapping between the data space and the parameter space, Isomap works, but this hypothesis has not been proved. In this paper, the existence of isometric mapping between the manifold in the high-dimensional data space and the parameter space is proved. By distinguishing