Clustering by principal component analysis with Gaussian kernel in high-dimension, low-sample-size settings

JOURNAL OF MULTIVARIATE ANALYSIS

卷:185

Article

Nakayama, Yugo¹  Yata, Kazuyoshi²  Aoshima, Makoto² 

[1] Kyoto Univ, Grad Sch Informat, Kyoto, Japan

[2] Univ Tsukuba, Inst Math, Tsukuba, Ibaraki 3058571, Japan

关键词: HDLSS;    Non-linear PCA;    PC score;    Radial basis function kernel;    Spherical data;   

DOI  :  10.1016/j.jmva.2021.104779

来源: Elsevier

【 摘 要 】

In this paper, we consider clustering based on the kernel principal component analysis (KPCA) for high-dimension, low-sample-size (HDLSS) data. We give theoretical reasons why the Gaussian kernel is effective for clustering high-dimensional data. In addition, we discuss a choice of the scale parameter yielding a high performance of the KPCA with the Gaussian kernel. Finally, we test the performance of the clustering by using microarray data sets. (C) 2021 The Author(s). Published by Elsevier Inc.

【 授权许可】

Free