Repository logo
 
Publication

Kernel-function-based models for acoustic localization of underwater vehicles

2017-07Journal article Restricted access
Simple item page
dc.contributor.authorPinheiro, Breno C.
dc.contributor.authorMoreno, Ubirajara F.
dc.contributor.authorde Sousa, Joao T. B.
dc.contributor.authorRodríguez, Orlando
dc.date.accessioned2019-11-20T15:07:31Z
dc.date.available2019-11-20T15:07:31Z
dc.date.issued2017-07
dc.description.abstractThis paper proposes a novel design for the localization system of autonomous underwater vehicles (AUVs) using acoustic signals. The solution presented exploits models based on kernel functions with two main purposes: 1) to reject outliers; and 2) to correct or improve accuracy of measurements. The localization system discussed is based on well-established techniques such as support vector data description (SVDD) and autoassociative kernel regression (AAKR) derived from machine learning theory that utilizes heuristic models for classification and regression tasks, respectively. By coupling the algorithm to the navigation system, we seek to reduce the sensitivity of the localization scheme to the reflected acoustic waves or fluctuations of underwater channel properties without modifying the solution used for data fusion or overloading the algorithm embedded in the vehicle. Data collected in the field with a light underwater vehicle (LAUV) were used to demonstrate the advantages of the proposed approach.
dc.description.sponsorshipPrograma de Ciencia, Tecnologia e Inovação—PTI C&T + I from Fundação Parque Tecnológico Itaipu—Brasil, FPTI-BR and Programa CAPES/FCT/ ´ BEX-7828/12-8 of international cooperation—Brasil/Portugal
dc.identifier.doi10.1109/JOE.2016.2578218
dc.identifier.issn0364-9059
dc.identifier.urihttp://hdl.handle.net/10400.1/13075
dc.language.isoeng
dc.peerreviewedyes
dc.publisherIeee-Institute of Electrical and Electronics Engineers
dc.subjectNavigation system
dc.subjectRegression
dc.subjectAcoustic localization
dc.subjectUnderwater vehicles
dc.subjectStatistical learning theory
dc.subjectKernel-based models
dc.titleKernel-function-based models for acoustic localization of underwater vehicles
dc.typejournal article
dspace.entity.typePublication
oaire.citation.endPage618
oaire.citation.issue3
oaire.citation.startPage603
oaire.citation.titleIeee Journal of Oceanic Engineering
oaire.citation.volume42
person.familyNameRodríguez
person.givenNameOrlando
person.identifier465112
person.identifier.ciencia-id8E12-528F-49E5
person.identifier.orcid0000-0002-0375-1892
person.identifier.ridO-6589-2015
person.identifier.scopus-author-id7103218936
rcaap.rightsrestrictedAccess
rcaap.typearticle
relation.isAuthorOfPublicatione82c7fd0-c7ec-46c2-8209-2129a826e634
relation.isAuthorOfPublication.latestForDiscoverye82c7fd0-c7ec-46c2-8209-2129a826e634

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
13075 Kernel function.pdf
Size:
1.5 MB
Format:
Adobe Portable Document Format
Download

Collections

FCT2-Artigos (em revistas ou actas indexadas)