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

被引：13

作者：

Nakayama, Yugo ^{[1
]}

Yata, Kazuyoshi ^{[2
]}

Aoshima, Makoto ^{[2
]}

机构：

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

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

来源：

JOURNAL OF MULTIVARIATE ANALYSIS | 2021年 / 185卷

关键词：

HDLSS; Non-linear PCA; PC score; Radial basis function kernel; Spherical data; STATISTICAL SIGNIFICANCE; GEOMETRIC REPRESENTATION; DATA CLASSIFICATION; PCA;

D O I：

10.1016/j.jmva.2021.104779

中图分类号：

O21 [概率论与数理统计]; C8 [统计学];

学科分类号：

020208 ; 070103 ; 0714 ;

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.

引用

页数：15

共 50 条

[31] Asymptotic properties of distance-weighted discrimination and its bias correction for high-dimension, low-sample-size data (vol 4, pg 821, 2021)
Egashira, Kento
Yata, Kazuyoshi
Aoshima, Makoto
JAPANESE JOURNAL OF STATISTICS AND DATA SCIENCE, 2022, 5 (02) : 717 - 718
[32] Comparison of principal component analysis algorithms for imputation in agrometeorological data in high dimension and reduced sample size
de Souza, Valter Cesar
Rodrigues, Sergio Augusto
Almeida Gabriel Filho, Luis Roberto
PLOS ONE, 2024, 19 (12):
[33] Improvement of Classification Performance in High-Dimension Low-Sample-Size Modeling by Sparse Functional Connectivity States in Subjects with Attention Deficit-Hyperactivity Disorder and Healthy Controls
Zolghadr, Zahra
Batouli, Seyed Amirhossein
Tehrani-Doost, Mehdi
Shafaghi, Lida
Hadjighassem, Mahmoudreza
Majd, Hamid Alavi
Mehrabi, Yadollah
ARCHIVES OF NEUROSCIENCE, 2023, 10 (02)
[34] Intrinsic Dimensionality Estimation of High-Dimension, Low Sample Size Data with D-Asymptotics
Yata, Kazuyoshi
Aoshima, Makoto
COMMUNICATIONS IN STATISTICS-THEORY AND METHODS, 2010, 39 (8-9) : 1511 - 1521
[35] Principal Component Analysis for High Dimension Stochastic Gaussian Process Model Fitting
Xuereb, M.
Huo, T. M.
Ng, S. H.
2019 IEEE INTERNATIONAL CONFERENCE ON INDUSTRIAL ENGINEERING AND ENGINEERING MANAGEMENT (IEEM), 2019, : 632 - 636
[36] Effect of dimension reduction by principal component analysis on clustering
Erisoglu, Murat
Erisoglu, Ulku
JOURNAL OF STATISTICS AND MANAGEMENT SYSTEMS, 2011, 14 (02) : 277 - 287
[37] Experimental Analysis of Feature Selection Stability for High-Dimension and Low-Sample Size Gene Expression Classification Task
Dernoncourt, David
Hanczar, Blaise
Zucker, Jean-Daniel
IEEE 12TH INTERNATIONAL CONFERENCE ON BIOINFORMATICS & BIOENGINEERING, 2012, : 350 - 355
[38] Sample size for principal component analysis in corn
Cargnelutti Filho, Alberto
Toebe, Marcos
PESQUISA AGROPECUARIA BRASILEIRA, 2021, 56
[39] Automatic Gaussian Bandwidth Selection for Kernel Principal Component Analysis
Shen, Kai
Wang, Haoyu
Chaudhuri, Arin
Asgharzadeh, Zohreh
KNOWLEDGE SCIENCE, ENGINEERING AND MANAGEMENT, PT I, KSEM 2023, 2023, 14117 : 15 - 26
[40] Gaussian Graphical Model Exploration and Selection in High Dimension Low Sample Size Setting
Lartigue, Thomas
Bottani, Simona
Baron, Stephanie
Colliot, Olivier
Durrleman, Stanley
Allassonniere, Stephanie
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2021, 43 (09) : 3196 - 3213

← 1 2 3 4 5 →