.: Marcos Gestal :.     -----
Principal
Trabajo
Publicaciones
Docencia
Enlaces
Blog
GaleriaFotos
Contacto


Visitas:

Datos de la Publicación:


Autores:
Carlos Fernandez-Lozano, Francisco Abel Cedrón, Daniel Rivero, Julián Dorado, José Manuel Andrade, Alejandro Pazos, Marcos Gestal
Título: Using Genetic Algorithms to improve Support Vector Regression in the analysis of Atomic spectra of Lubricant Oils
Revista: Engineering Computations
ISSN: 0264-4401
Volumen: 33(4)
Páginas: 995-1005
Editorial: Emerald Group Publishing Limited
Fecha Publicación: Mayo 2016
Factor de Impacto: 1.495
doi: 10.1108/EC-03-2015-0062
Categorías WoS: Engineering, Multidisciplinary - Cuartil: Q1 - Tercil: - Posición 21 de 85
Computer Science, Interdisciplinary Applications - Cuartil: Q2 - Tercil: - Posición 42 de 102
Mathematics, Interdisciplinary Applications - Cuartil: Q2 - Tercil: - Posición 27 de 99
Mechanics - Cuartil: Q2 - Tercil: - Posición 58 de 137

Abstract:

To assess the quality of commercial lubricant oils a spectroscopic method was used in combination with multivariate regression techniques like multivariate multiple regression (MLR), Principal Components Regression (PCR) or Support Vector Machines for Regression,(SVR). The rationale behind the use of SVR was the fuzzy characteristics of the signal and its inherent ability to find nonlinear, global solutions in highly complex dimensional input spaces. Thus, SVR allows extracting useful information from calibration samples that makes it possible to characterize physical-chemical properties of the lubricant oils. The use of Genetic Algorithms coupled to SVR was considered in order to reduce the time needed to find the optimal parameters required to get a suitable prediction model.

Download