海军航空工程学院学报2016，Vol.31Issue(4)：415-422,8.DOI:10.7682/j.issn.1673-1522.2016.04.003
一种鲁棒的概率核主成分分析模型
A Robust Probabilistic Kernel Principal Component Analysis Model
杨芸 1李彪 2王帅磊1
作者信息
- 1. 海军航空工程学院 研究生管理大队，山东烟台264001
- 2. 海军航空工程学院 基础部，山东烟台264001
- 折叠
摘要
Abstract
The dimension of the processed data have become more and more higher, so dimensionality reduction becomes more and more important. The classical PCA (Principal component analysis) has proven to be an effective dimensionality reduction method. But its effect was poor when used it to disposing nonlinear, noise and outliers data set, so, a robust prob⁃abilistic kernel principal component analysis model (RPKPCA) was proposed. It combined kernel method with maximum likelihood frame based on Gaussian process latent variable model and used t-distribution as prior distribution to solve its three disadvantages at the same time. In addition, a mixtures of robust probabilistic kernel principal component analysis model (MRPKPCA), and it could be used directly to dimensions reduction and data mining of mixture and nonlinear data. The experimental results in different data set showed that the model of proposed in this paper had higher accuracy than the standard probabilistic kernel principal component analysis model.关键词
主成分分析/鲁棒降维/EM算法/聚类分析/核方法/隐变量模型Key words
principal component analysis/dimensionality reduction of robustness/EM algorithm/cluster analysis/kernel method/latent variable model分类
计算机与自动化引用本文复制引用
杨芸,李彪,王帅磊..一种鲁棒的概率核主成分分析模型[J].海军航空工程学院学报,2016,31(4):415-422,8.
