Vis enkel innførsel

dc.contributor.authorMikalsen, Karl Øyvind
dc.contributor.authorBianchi, Filippo Maria
dc.contributor.authorSoguero-Ruiz, Cristina
dc.contributor.authorJenssen, Robert
dc.date.accessioned2018-08-23T14:00:53Z
dc.date.available2018-08-23T14:00:53Z
dc.date.embargoEndDate2019-12-07
dc.date.issued2017-12-06
dc.description.abstract<p>Similarity-based approaches represent a promising direction for time series analysis. However, many such methods rely on parameter tuning, and some have shortcomings if the time series are multivariate (MTS), due to dependencies between attributes, or the time series contain missing data. In this paper, we address these challenges within the powerful context of kernel methods by proposing the robust time series cluster kernel (TCK). The approach taken leverages the missing data handling properties of Gaussian mixture models (GMM) augmented with informative prior distributions. An ensemble learning approach is exploited to ensure robustness to parameters by combining the clustering results of many GMM to form the final kernel.</p> <p>We evaluate the TCK on synthetic and real data and compare to other state-of-the-art techniques. The experimental results demonstrate that the TCK is robust to parameter choices, provides competitive results for MTS without missing data and outstanding results for missing data.en_US
dc.description.sponsorshipThe Spanish Governmenten_US
dc.descriptionAccepted manuscript version. Published version available at <a href=https://doi.org/10.1016/j.patcog.2017.11.030> https://doi.org/10.1016/j.patcog.2017.11.030</a>. Accepted manuscript version, licensed <a href=http://creativecommons.org/licenses/by-nc-nd/4.0/> CC BY-NC-ND 4.0.</a>en_US
dc.identifier.citationMikalsen, K.Ø., Bianchi, F.M., Soguero-Ruiz, C. & Jenssen, R. (2017). Time series cluster kernel for learning similarities between multivariate time series with missing data. <i>Pattern Recognition</i>, 76, 569-581. https://doi.org/10.1016/j.patcog.2017.11.030en_US
dc.identifier.issn0031-3203
dc.identifier.issn1873-5142
dc.identifier.otherFRIDAID 1537526
dc.identifier.otherhttps://doi.org/10.1016/j.patcog.2017.11.030
dc.identifier.urihttps://hdl.handle.net/10037/13578
dc.language.isoengen_US
dc.publisherElsevieren_US
dc.relation.ispartofThe final version of this article is part of<p> Mikalsen, K.Ø. (2019). Advancing Unsupervised and Weakly Supervised Learning with Emphasis on Data-Driven Healthcare. (Doctoral thesis). <a href=http://hdl.handle.net/10037/14659>http://hdl.handle.net/10037/14659. </a>
dc.relation.journalPattern Recognition
dc.relation.projectIDinfo:eu-repo/grantAgreement/RCN/FRIPRO/239844/Norway/Next Generation Learning Machines//en_US
dc.relation.urihttps://www.sciencedirect.com/science/article/pii/S0031320317304843
dc.rights.accessRightsembargoedAccessen_US
dc.subjectVDP::Matematikk og naturvitenskap: 400::Matematikk: 410::Statistikk: 412en_US
dc.subjectVDP::Mathematics and natural scienses: 400::Mathematics: 410::Statistics: 412en_US
dc.subjectMaskinlæringen_US
dc.subjectMachine learningen_US
dc.subjectMultivariate time seriesen_US
dc.subjectSimilarity measuresen_US
dc.subjectKernel methodsen_US
dc.subjectMissing dataen_US
dc.subjectGaussian mixture modelsen_US
dc.subjectEnsemble learningen_US
dc.titleTime series cluster kernel for learning similarities between multivariate time series with missing dataen_US
dc.typeJournal articleen_US
dc.typeTidsskriftartikkelen_US
dc.typePeer revieweden_US


Tilhørende fil(er)

Denne innførselen finnes i følgende samling(er)

Vis enkel innførsel