一种基于距离惩罚的混合模型分量数估计算法
n Algorithm for Estimating Number of Components of Gaussian Mixture Model Based on Penalized Distance
EM算法是对有限混合模型进行参数估计的通用算法，然而标准EM算法所需的混合分量数实际上往往是未知的。为解决这个问题，本文研究了一种惩罚性最小匹配距离估计混合分量数的方法，在Greedy EM算法的框架下，提出一种在混合模型参数估计的同时，快速、准确估计高斯混合模型分量数的算法。通过仿真实验，验证了该算法的有效性
he EM algorithm is a popular tool for parameter estimation of finite mixture model. A drawback of this approach is that the number of components of finite mixture model is not known in advance, nevertheless, it is a key issue for EM algorithms. In this paper, a penalized minimum matching distance-guided EM algorithm is discussed. Under the framework of Greedy EM, a fast and accurate algorithm for estimating the number of components is proposed. The performance of this algorithm is validated via simulate experiments of univariate and bivariate Gaussian mixture models
张大明、符茂胜、罗斌
计算技术、计算机技术
有限混合模型混合模型分量数惩罚性最小匹配距离贪婪EMParzen窗
Finite mixture modelNumber of componentsPenalized minimum matching distanceGreedy EMParzen Window
张大明,符茂胜,罗斌.一种基于距离惩罚的混合模型分量数估计算法[EB/OL].(2008-04-07)[2025-08-11].http://www.paper.edu.cn/releasepaper/content/200804-208.点此复制
评论