基于模型的聚类
Model-based Clustering
AI总结:
本文介绍基于模型的聚类,通过混合模型在概率框架内定义簇结构,并与启发式方法对比,讨论后处理及应用领域。
摘要:
混合模型扩展了数据分析师可用的聚类方法工具箱。它们允许在概率框架内明确定义簇形状和结构,并利用通常可用于统计模型的估计和推断技术。本章介绍了聚类分析,将基于模型的聚类与标准启发式聚类方法联系起来,并概述了指定聚类模型的不同方式。讨论了确定合适聚类、推断簇分布特征和验证聚类解决方案的后处理方法。通过概述不同的应用领域,说明了基于模型的聚类方法的多样性。
英文摘要:
Mixture models extend the toolbox of clustering methods available to the data analyst. They allow for an explicit definition of the cluster shapes and structure within a probabilistic framework and exploit estimation and inference techniques available for statistical models in general. In this chapter an introduction to cluster analysis is provided, model-based clustering is related to standard heuristic clustering methods and an overview on different ways to specify the cluster model is given. Post-processing methods to determine a suitable clustering, infer cluster distribution characteristics and validate the cluster solution are discussed. The versatility of the model-based clustering approach is illustrated by giving an overview on the different areas of applications.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。