J
Joan Vila-Francés
Researcher at University of Valencia
Publications - 60
Citations - 2222
Joan Vila-Francés is an academic researcher from University of Valencia. The author has contributed to research in topics: Neurocognitive & Medicine. The author has an hindex of 16, co-authored 51 publications receiving 1929 citations.
Papers
More filters
Journal ArticleDOI
Composite kernels for hyperspectral image classification
Gustau Camps-Valls,Luis Gómez-Chova,Jordi Muñoz-Marí,Joan Vila-Francés,Javier Calpe-Maravilla +4 more
TL;DR: This framework of composite kernels demonstrates enhanced classification accuracy as compared to traditional approaches that take into account the spectral information only, flexibility to balance between the spatial and spectral information in the classifier, and computational efficiency.
Journal ArticleDOI
Improved Fraunhofer Line Discrimination Method for Vegetation Fluorescence Quantification
Luis Alonso,Luis Gómez-Chova,Joan Vila-Francés,Julia Amorós-López,Luis Guanter,J. Calpe,Jose Moreno +6 more
TL;DR: This letter presents a modification to the established Fraunhofer line discrimination method for improving the accuracy of the solar-induced chlorophyll fluorescence retrieval over terrestrial vegetation by introducing two correction coefficients that relate the values of the fluorescence and the reflectance inside and outside the absorption band.
Journal ArticleDOI
BELM: Bayesian Extreme Learning Machine
Emilio Soria-Olivas,Juan Gómez-Sanchis,José D. Martín,Joan Vila-Francés,M. Martinez,Jose R. Magdalena,Antonio J. Serrano +6 more
TL;DR: A Bayesian approach to ELM is proposed, which presents some advantages over other approaches: it allows the introduction of a priori knowledge; obtains the confidence intervals (CIs) without the need of applying methods that are computationally intensive, e.g., bootstrap; and presents high generalization capabilities.
Journal ArticleDOI
Retrieval of oceanic chlorophyll concentration with relevance vector machines
Gustavo Camps-Valls,Luis Gómez-Chova,Jordi Muñoz-Marí,Joan Vila-Francés,Julia Amorós-López,Javier Calpe-Maravilla +5 more
TL;DR: Results suggest that RVMs offer an excellent trade-off between accuracy and sparsity of the solution, and become less sensitive to the selection of the free parameters.
Journal ArticleDOI
Neural networks for analysing the relevance of input variables in the prediction of tropospheric ozone concentration
Juan Gómez-Sanchis,José D. Martín-Guerrero,Emilio Soria-Olivas,Joan Vila-Francés,José L. Carrasco,Secundino del Valle-Tascón +5 more
TL;DR: In this article, the authors used Artificial Neural Networks (ANNs) to predict ozone levels in a small town near Valencia (Spain) in three different time windows: all the time of study (April of 1997, 1999 and 2000), one month (April 1999), and finally, an hourly analysis.