A novel and robust parameter training approach for HMMs under noisy and partial access to states

dc.citation.epage497en_US
dc.citation.spage490en_US
dc.citation.volumeNumber94en_US
dc.contributor.authorOzkan, H.en_US
dc.contributor.authorAkman, A.en_US
dc.contributor.authorKozat, S. S.en_US
dc.date.accessioned2016-02-08T11:00:54Z
dc.date.available2016-02-08T11:00:54Z
dc.date.issued2014-01en_US
dc.departmentDepartment of Electrical and Electronics Engineeringen_US
dc.description.abstractThis paper proposes a new estimation algorithm for the parameters of an HMM as to best account for the observed data. In this model, in addition to the observation sequence, we have partial and noisy access to the hidden state sequence as side information. This access can be seen as "partial labeling" of the hidden states. Furthermore, we model possible mislabeling in the side information in a joint framework and derive the corresponding EM updates accordingly. In our simulations, we observe that using this side information, we considerably improve the state recognition performance, up to 70%, with respect to the "achievable margin" defined by the baseline algorithms. Moreover, our algorithm is shown to be robust to the training conditions. © 2013 Elsevier B.V.en_US
dc.description.provenanceMade available in DSpace on 2016-02-08T11:00:54Z (GMT). No. of bitstreams: 1 bilkent-research-paper.pdf: 70227 bytes, checksum: 26e812c6f5156f83f0e77b261a471b5a (MD5) Previous issue date: 2014en
dc.identifier.doi10.1016/j.sigpro.2013.07.015en_US
dc.identifier.issn0165-1684
dc.identifier.urihttp://hdl.handle.net/11693/26516
dc.language.isoEnglishen_US
dc.publisherElsevier BVen_US
dc.relation.isversionofhttp://dx.doi.org/10.1016/j.sigpro.2013.07.015en_US
dc.source.titleSignal Processingen_US
dc.subjectHMMen_US
dc.subjectIncomplete dataen_US
dc.subjectML estimatoren_US
dc.subjectPartially observed statesen_US
dc.subjectEstimation algorithmen_US
dc.subjectState recognitionen_US
dc.subjectTraining conditionsen_US
dc.subjectElectrical engineeringen_US
dc.subjectSignal processingen_US
dc.subjectAlgorithmsen_US
dc.titleA novel and robust parameter training approach for HMMs under noisy and partial access to statesen_US
dc.typeArticleen_US

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
A novel and robust parameter training approach for HMMs under noisy and partial access to states.pdf
Size:
370.12 KB
Format:
Adobe Portable Document Format
Description:
Full printable version