Mi DSpace
Usuario
Contraseña
Please use this identifier to cite or link to this item: http://hdl.handle.net/UCSP/15761
Full metadata record
DC FieldValueLanguage
dc.contributor.authorLudeña Choez, Jimmy Diestin-
dc.contributor.authorChoquehuanca Zevallos, Juan José-
dc.contributor.authorMayhua López, Efraín Tito-
dc.date.accessioned2019-01-29T22:19:49Z-
dc.date.available2019-01-29T22:19:49Z-
dc.date.issued2018-
dc.identifier.issn1681699es_PE
dc.identifier.urihttp://repositorio.ucsp.edu.pe/handle/UCSP/15761-
dc.description.abstractNowadays, Wireless Sensor Networks (WSN) are widely been employed to solve agricultural problems related to the optimization of scarce farming resources, decision making support, and land monitoring. However, the small sensing devices that are part of WSNs – known as sensor nodes – suffer from degradation and so producing erroneous measurements. In this paper, a machine learning method based on Non-Negative Matrix Factorization (NMF) is applied to the spectral representation of data acquired by a WSN to extract features that model the normal behavior of sensor node readings leading to a good representation of data using a low number of features. This procedure is accompanied by a classifier that decides if there is a set of features that deviates from the normal ones. Experiments on soil moisture data show that NMF achieves good results detecting flaws in readings from sensors. Results are compared with other method based on Principal Component Analysis (PCA), the Multi-scale PCA (MSPCA) algorithm. © 2018 Elsevier B.V.es_PE
dc.description.uriTrabajo de investigaciónes_PE
dc.language.isoenges_PE
dc.publisherElsevier B.V.es_PE
dc.relation.urihttps://www.scopus.com/inward/record.uri?eid=2-s2.0-85049352598&doi=10.1016%2fj.compag.2018.06.033&partnerID=40&md5=7ab1a19e2a2ccab9fad064a73e6e47c2es_PE
dc.rightsinfo:eu-repo/semantics/restrictedAccesses_PE
dc.sourceRepositorio Institucional - UCSPes_PE
dc.sourceUniversidad Católica San Pabloes_PE
dc.sourceScopuses_PE
dc.subjectAgriculturees_PE
dc.subjectDecision makinges_PE
dc.subjectDiscrete wavelet transformses_PE
dc.subjectFactorizationes_PE
dc.subjectFault detectiones_PE
dc.subjectLearning systemses_PE
dc.subjectMatrix algebraes_PE
dc.subjectPrincipal component analysises_PE
dc.subjectSoil moisturees_PE
dc.subjectWireless sensor networkses_PE
dc.subjectDecision making supportes_PE
dc.subjectMachine learning methodses_PE
dc.subjectMulti-scalees_PE
dc.subjectNonnegative matrix factorizationes_PE
dc.subjectNormal behaviores_PE
dc.subjectPrincipal componentses_PE
dc.subjectanalysises_PE
dc.subjectSensing deviceses_PE
dc.subjectSpectral representationses_PE
dc.subjectSensor nodeses_PE
dc.titleSensor nodes fault detection for agricultural wireless sensor networks based on NMFes_PE
dc.typeinfo:eu-repo/semantics/articlees_PE
dc.identifier.doihttps://doi.org/10.1016/j.compag.2018.06.033es_PE
dc.subject.ocdehttps://purl.org/pe-repo/ocde/ford#2.02.01es_PE
Appears in Collections:Artículos - Ingeniería Electrónica y de Telecomunicaciones

Files in This Item:
There are no files associated with this item.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.