Adaptive split-merge algorithm for Gaussian mixture models to solve the Kolmogorov equation

Kumar Vishwajeet, Puneet Singla

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

Abstract

Number of components in a Gaussian mixture model plays an important role in its accuracy and computational complexity. New adaptive split-merge technique is introduced in this paper based on the minimization of error in the solution of Fokker Planck Kolmogorov Equation. We also discuss the effect of splitting/merging of few components on the weights of other components. A single Gaussian component at initial time is split over time to account for the change in the probability density function of the states of the system.

Original languageEnglish (US)
Title of host publicationAstrodynamics 2013 - Advances in the Astronautical Sciences
Subtitle of host publicationProceedings of the AAS/AIAA Astrodynamics Specialist Conference
PublisherUnivelt Inc.
Pages977-988
Number of pages12
ISBN (Print)9780877036050
StatePublished - 2014
Event2013 AAS/AIAA Astrodynamics Specialist Conference, Astrodynamics 2013 - Hilton Head Island, SC, United States
Duration: Aug 11 2013Aug 15 2013

Publication series

NameAdvances in the Astronautical Sciences
Volume150
ISSN (Print)0065-3438

Other

Other2013 AAS/AIAA Astrodynamics Specialist Conference, Astrodynamics 2013
Country/TerritoryUnited States
CityHilton Head Island, SC
Period8/11/138/15/13

All Science Journal Classification (ASJC) codes

  • Aerospace Engineering
  • Space and Planetary Science

Fingerprint

Dive into the research topics of 'Adaptive split-merge algorithm for Gaussian mixture models to solve the Kolmogorov equation'. Together they form a unique fingerprint.

Cite this