Bandwidth selection for kernel density estimation using fourier domain constraints

buir.contributor.authorArıkan, Orhan
buir.contributor.authorÇetin, A. Enis
buir.contributor.orcidArıkan, Orhan|0000-0002-3698-8888
buir.contributor.orcidÇetin, A. Enis|0000-0002-3449-1958
dc.citation.epage283en_US
dc.citation.issueNumber3en_US
dc.citation.spage280en_US
dc.citation.volumeNumber10en_US
dc.contributor.authorSuhre, A.en_US
dc.contributor.authorArıkan, Orhanen_US
dc.contributor.authorÇetin, A. Enisen_US
dc.date.accessioned2018-04-12T10:47:33Z
dc.date.available2018-04-12T10:47:33Z
dc.date.issued2016en_US
dc.departmentDepartment of Electrical and Electronics Engineeringen_US
dc.description.abstractKernel density estimation (KDE) is widely-used for non-parametric estimation of an underlying density from data. The performance of KDE is mainly dependent on the bandwidth parameter of the kernel. This study presents an alternative method of estimating the bandwidth by incorporating sparsity priors in the Fourier transform domain. By using cross-validation (CV) together with an l1 constraint, the proposed method significantly reduces the under-smoothing effect of traditional CV methods. A solution for all free parameters in the minimisation is proposed, such that the algorithm does not need any additional parameter tuning. Simulation results indicate that the new approach is able to outperform classical and more recent approaches over a set of distributions of interest.en_US
dc.description.provenanceMade available in DSpace on 2018-04-12T10:47:33Z (GMT). No. of bitstreams: 1 bilkent-research-paper.pdf: 179475 bytes, checksum: ea0bedeb05ac9ccfb983c327e155f0c2 (MD5) Previous issue date: 2016en
dc.identifier.doi10.1049/iet-spr.2015.0076en_US
dc.identifier.issn1751-9675
dc.identifier.urihttp://hdl.handle.net/11693/36663
dc.language.isoEnglishen_US
dc.publisherInstitution of Engineering and Technologyen_US
dc.relation.isversionofhttp://dx.doi.org/10.1049/iet-spr.2015.0076en_US
dc.source.titleIET Signal Processingen_US
dc.subjectBandwidthen_US
dc.subjectStatisticsen_US
dc.subjectBandwidth parametersen_US
dc.subjectBandwidth selectionsen_US
dc.subjectCross validationen_US
dc.subjectKernel Density Estimationen_US
dc.subjectNon-parametric estimationsen_US
dc.subjectParameter-tuningen_US
dc.subjectSmoothing effectsen_US
dc.subjectSparsity priorsen_US
dc.subjectParameter estimationen_US
dc.titleBandwidth selection for kernel density estimation using fourier domain constraintsen_US
dc.typeArticleen_US

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Bandwidth selection for kernel density estimation using Fourier domain constraints.pdf
Size:
254.45 KB
Format:
Adobe Portable Document Format
Description:
Full Printable Version