Model selection for mixture model via integrated nested Laplace approximation

Research output: Contribution to journalArticle

Abstract

To cluster or partition data/signal, expectation-and-maximisation or variational approximation with a mixture model (MM), which is a parametric probability density function represented as a weighted sum of K densities, is often used. However, model selection to find the underlying K is one of the key concerns in MMclustering, since the desired clusters can be obtained only when K is known. A new model selection algorithm to explore K in a Bayesian framework is proposed. The proposed algorithm builds the density of the model order which information criterion such as AIC and BIC or other heuristic algorithms basically fail to reconstruct. In addition, this algorithm reconstructs the density quickly as compared with the time-consuming Monte Carlo simulation using integrated nested Laplace approximation.

Original languageEnglish
Pages (from-to)484-486
Number of pages3
JournalElectronics Letters
Volume51
Issue number6
DOIs
Publication statusPublished - 2015 Mar 19

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Model selection for mixture model via integrated nested Laplace approximation'. Together they form a unique fingerprint.

  • Cite this