Parameter estimation of Gaussian mixture model utilizing boundary data

Masako Omachi, Shinichiro Omachi, Hirotomo Aso, Tsuneo Saito

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Gaussian mixture model is a statistical model that represents a distribution of data correctly, which can be used for prediction, monitoring, segmentation, discrimination, clustering, recognition, etc. The parameters of the Gaussian mixture model are usually estimated from given sample data by the Expectation Maximization algorithm. However, when the number of attributes of the data is large, the parameters cannot be estimated correctly. In this paper, we propose a novel approach for estimating the parameters of the Gaussian mixture model by utilizing the sample data located on the boundary of regions defined by the component density functions. The effectiveness of the proposed method is confirmed by some experiments.

Original languageEnglish
Title of host publication38th International Conference on Computers and Industrial Engineering 2008
Pages291-297
Number of pages7
Publication statusPublished - 2008 Dec 1
Event38th International Conference on Computers and Industrial Engineering 2008 - Beijing, China
Duration: 2008 Oct 312008 Nov 2

Publication series

Name38th International Conference on Computers and Industrial Engineering 2008
Volume1

Other

Other38th International Conference on Computers and Industrial Engineering 2008
CountryChina
CityBeijing
Period08/10/3108/11/2

Keywords

  • Gaussian mixture model
  • Parameter estimation
  • Pattern recognition
  • Probabilistic model
  • Statistical model

ASJC Scopus subject areas

  • Industrial and Manufacturing Engineering

Fingerprint Dive into the research topics of 'Parameter estimation of Gaussian mixture model utilizing boundary data'. Together they form a unique fingerprint.

  • Cite this

    Omachi, M., Omachi, S., Aso, H., & Saito, T. (2008). Parameter estimation of Gaussian mixture model utilizing boundary data. In 38th International Conference on Computers and Industrial Engineering 2008 (pp. 291-297). (38th International Conference on Computers and Industrial Engineering 2008; Vol. 1).