| 高维异方差高斯混合罚模型聚类 |
| |
| 引用本文： | 李沐雨,王星.高维异方差高斯混合罚模型聚类[J].数学的实践与认识,2013,43(5). |
| |
| 作者姓名： | 李沐雨 王星 |
| |
| 作者单位： | 1. 中国人民大学应用统计科学研究中心,北京,100872
2. 中国人民大学统计学院,北京,100872 |
| |
| 基金项目： | 中国人民大学科学研究基金(中央高校基本科研业务费专项资金资助)项目成果;编号10XNI014;"人文社会科学成果评价指标体系" |
| |
| 摘 要： | 罚模型聚类实现了在聚类过程中精简变量的目标,同时如何识别聚类的有效变量成了一个新的问题.在这个问题上,已有的研究有成对罚模型,模型处理了各类数据同方差的情况.考察了异方差情况下的变量选择问题,针对异方差数据提出了两种新的模型,并给出模型的解和算法.模拟数据分析结果表明,异方差数据上两个新模型都有更好的表现.
|
| 关 键 词： | 高维异方差数据 EM算法 高斯混合模型 罚似然 |
High-dimensional Heteroskedasticity Penalized Gaussian Mixture Model-Based Clustering |
| |
| LI Mu-yu
,
WANG Xing.High-dimensional Heteroskedasticity Penalized Gaussian Mixture Model-Based Clustering[J].Mathematics in Practice and Theory,2013,43(5). |
| |
| Authors: | LI Mu-yu WANG Xing |
| |
| Abstract: | Penalized model based clustering achieved the goal of deleting variables in the process of clustering,while how to recognize the clustering function of those undeleted variables becoming a new problem.Researches on this problem include the pairwise penalized model which dealt with the situation of hombscedasticity data.This paper investigated the problem of variables selection under the heteroscedasticity situation,and proposed two new models and their solution & algorithm respectively for the heteroscedasticity data.Simulation data analysis indicate that both two models perform better on the heteroscedasticity data. |
| |
| Keywords: | high dimensional heteroscedasticity data EM algorithm gaussian mixture model penalized likelihood |
| 本文献已被 万方数据 等数据库收录！ |
|
