Show simple item record

dc.contributor.authorAr, C.en_US
dc.contributor.authorAksoy, S.en_US
dc.contributor.authorArıkan, Orhanen_US
dc.date.accessioned2016-02-08T09:45:51Z
dc.date.available2016-02-08T09:45:51Z
dc.date.issued2012en_US
dc.identifier.issn0031-3203
dc.identifier.urihttp://hdl.handle.net/11693/21405
dc.description.abstractGaussian mixture models (GMM), commonly used in pattern recognition and machine learning, provide a flexible probabilistic model for the data. The conventional expectationmaximization (EM) algorithm for the maximum likelihood estimation of the parameters of GMMs is very sensitive to initialization and easily gets trapped in local maxima. Stochastic search algorithms have been popular alternatives for global optimization but their uses for GMM estimation have been limited to constrained models using identity or diagonal covariance matrices. Our major contributions in this paper are twofold. First, we present a novel parametrization for arbitrary covariance matrices that allow independent updating of individual parameters while retaining validity of the resultant matrices. Second, we propose an effective parameter matching technique to mitigate the issues related with the existence of multiple candidate solutions that are equivalent under permutations of the GMM components. Experiments on synthetic and real data sets show that the proposed framework has a robust performance and achieves significantly higher likelihood values than the EM algorithm. © 2012 Elsevier Ltd. All rights reserved.en_US
dc.language.isoEnglishen_US
dc.source.titlePattern Recognitionen_US
dc.relation.isversionofhttp://dx.doi.org/10.1016/j.patcog.2011.12.023en_US
dc.subjectCovariance parametrizationen_US
dc.subjectExpectation – maximizationen_US
dc.subjectGaussian mixture modelsen_US
dc.subjectIdentifiabilityen_US
dc.subjectMaximum likelihood estimationen_US
dc.subjectParticle swarm optimizationen_US
dc.subjectStochastic searchen_US
dc.subjectIdentifiabilityen_US
dc.titleMaximum likelihood estimation of Gaussian mixture models using stochastic searchen_US
dc.typeArticleen_US
dc.departmentDepartment of Electrical and Electronics Engineeringen_US
dc.departmentDepartment of Computer Engineeringen_US
dc.citation.spage2804en_US
dc.citation.epage2816en_US
dc.citation.volumeNumber45en_US
dc.citation.issueNumber7en_US
dc.identifier.doi10.1016/j.patcog.2011.12.023en_US
dc.publisherElsevier BVen_US
dc.contributor.bilkentauthorArıkan, Orhan


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record