Prediction Of The Distillation Temperatures Of Crude Oils Using H-1 Nmr And Support Vector Regression With Estimated Confidence Intervals

dc.creatorFilgueiras
dc.creatorPaulo R.; Terra
dc.creatorLuciana A.; Castro
dc.creatorEustaquio V. R.; Oliveira
dc.creatorLize M. S. L.; Dias
dc.creatorJulio C. M.; Poppi
dc.creatorRonei J.
dc.date2015-SEP
dc.date2016-06-07T13:21:16Z
dc.date2016-06-07T13:21:16Z
dc.date.accessioned2018-03-29T01:41:09Z
dc.date.available2018-03-29T01:41:09Z
dc.identifier
dc.identifierPrediction Of The Distillation Temperatures Of Crude Oils Using H-1 Nmr And Support Vector Regression With Estimated Confidence Intervals. Elsevier Science Bv, v. 142, p. 197-205 SEP-2015.
dc.identifier0039-9140
dc.identifierWOS:000356997700028
dc.identifier10.1016/j.talanta.2015.04.046
dc.identifierhttp://www.sciencedirect.com/science/article/pii/S0039914015002957
dc.identifierhttp://repositorio.unicamp.br/jspui/handle/REPOSIP/243057
dc.identifier.urihttp://repositorioslatinoamericanos.uchile.cl/handle/2250/1306755
dc.descriptionConselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)
dc.descriptionThis paper aims to estimate the temperature equivalent to 10% (T10%), 50% (T50%) and 90% (T90%) of distilled volume in crude oils using H-1 NMR and support vector regression (SVR). Confidence intervals for the predicted values were calculated using a boosting-type ensemble method in a procedure called ensemble support vector regression (eSVR). The estimated confidence intervals obtained by eSVR were compared with previously accepted calculations from partial least squares (PLS) models and a boostingtype ensemble applied in the PLS method (ePLS). By using the proposed boosting strategy, it was possible to identify outliers in the T10% property dataset. The eSVR procedure improved the accuracy of the distillation temperature predictions in relation to standard PLS, ePLS and SVR. For T10%, a root mean square error of prediction (RMSEP) of 11.6 degrees C was obtained in comparison with 15.6 degrees C for PLS, 15.1 degrees C for ePLS and 28.4 degrees C for SVR. The RMSEPs for T50% were 24.2 degrees C, 23.4 degrees C, 22.8 degrees C and 14.4 degrees C for PLS, ePLS, SVR and eSVR, respectively. For 190%, the values of RMSEP were 39.0 degrees C, 39.9 degrees C and 39.9 degrees C for PLS, ePLS, SVR and eSVR, respectively. The confidence intervals calculated by the proposed boosting methodology presented acceptable values for the three properties analyzed; however, they were lower than those calculated by the standard methodology for PLS. (C) 2015 Elsevier B.V. All rights reserved.
dc.description142
dc.description
dc.description
dc.description197
dc.description205
dc.descriptionConselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)
dc.descriptionConselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)
dc.descriptionCNPq [proc. 146807/2011-1, proc. 307838/2013-7]
dc.description
dc.description
dc.description
dc.languageen
dc.publisherELSEVIER SCIENCE BV
dc.publisher
dc.publisherAMSTERDAM
dc.relationTALANTA
dc.rightsembargo
dc.sourceWOS
dc.subjectNear-infrared Spectroscopy
dc.subjectMultivariate Calibration Models
dc.subjectLeast-squares Regression
dc.subjectQuality Parameters
dc.subjectVariable Selection
dc.subjectBootstrap Methods
dc.subjectPetroleum
dc.subjectNmr
dc.subjectSpectra
dc.subjectFigures
dc.titlePrediction Of The Distillation Temperatures Of Crude Oils Using H-1 Nmr And Support Vector Regression With Estimated Confidence Intervals
dc.typeArtículos de revistas


Este ítem pertenece a la siguiente institución