Mixture Density Estimation Based on Maximum Likelihood and Sequential Test Statistics

Vlassis, NA; Papakonstantinou, G; Tsanakas, P

dc.contributor.author	Vlassis, NA	en
dc.contributor.author	Papakonstantinou, G	en
dc.contributor.author	Tsanakas, P	en
dc.date.accessioned	2014-03-01T01:14:48Z
dc.date.available	2014-03-01T01:14:48Z
dc.date.issued	1999	en
dc.identifier.issn	1370-4621	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/13230
dc.subject	Gaussian mixtures	en
dc.subject	Nonstationary distributions	en
dc.subject	Number of mixing components	en
dc.subject	PNN	en
dc.subject	Semi-parametric estimation	en
dc.subject	Stationary distributions	en
dc.subject	Test statistics	en
dc.subject.classification	Computer Science, Artificial Intelligence	en
dc.subject.classification	Neurosciences	en
dc.subject.other	Approximation theory	en
dc.subject.other	Iterative methods	en
dc.subject.other	Maximum likelihood estimation	en
dc.subject.other	Pattern recognition	en
dc.subject.other	Statistical tests	en
dc.subject.other	Time series analysis	en
dc.subject.other	Mixture density estimation	en
dc.subject.other	Sequential test statistics	en
dc.subject.other	Probability density function	en
dc.title	Mixture Density Estimation Based on Maximum Likelihood and Sequential Test Statistics	en
heal.type	journalArticle	en
heal.identifier.primary	10.1023/A:1018624029058	en
heal.identifier.secondary	http://dx.doi.org/10.1023/A:1018624029058	en
heal.language	English	en
heal.publicationDate	1999	en
heal.abstract	We address the problem of estimating an unknown probability density function from a sequence of input samples. We approximate the input density with a weighted mixture of a finite number of Gaussian kernels whose parameters and weights we estimate iteratively from the input samples using the Maximum Likelihood (ML) procedure. In order to decide on the correct total number of kernels we employ simple statistical tests involving the mean, variance, and the kurtosis, or fourth moment, of a particular kernel. We demonstrate the validity of our method in handling both pattern classification (stationary) and time series (nonstationary) problems.	en
heal.publisher	KLUWER ACADEMIC PUBL	en
heal.journalName	Neural Processing Letters	en
dc.identifier.doi	10.1023/A:1018624029058	en
dc.identifier.isi	ISI:000078809200007	en
dc.identifier.volume	9	en
dc.identifier.issue	1	en
dc.identifier.spage	63	en
dc.identifier.epage	76	en