NLDR methods for high dimensional NIRS dataset: application to vineyard soils characterizationReportar como inadecuado




NLDR methods for high dimensional NIRS dataset: application to vineyard soils characterization - Descarga este documento en PDF. Documentación en PDF para descargar gratis. Disponible también para leer online.

1 AgroSup Dijon - Institut National Supérieur des Sciences Agronomiques, de l-Alimentation et de l-Environnement 2 Le2i - Laboratoire Electronique, Informatique et Image 3 AgroParisTech 4 BGS - Biogéosciences Dijon 5 ARTeHiS - Archéologie, Terre, Histoire, Sociétés Dijon 6 Agroécologie

Abstract : In the context of vineyard soils characterizationn this paper explores and compare dierent recent Non Linear Dimensionality Reduction NLDR methods on a high-dimensional Near InfraRed Spectroscopy NIRS dataset. NLDR methods are based on k-neighborhood criterion and Euclidean and fractional distances metrics are tested. Results show that Multiscale Jensen-Shannon Embedding Ms JSE coupled with eu-clidean distance outperform all over methods. Application on data is made at global scale and at dierent scale of depth of soil.

Keywords : reduction dimension Near InfraRed Spectroscopy Soil Clustering Analysis nonlinear dimension reduction





Autor: Clément Delion - Ludovic Journaux - Aurore Payen - Lucile Sautot - Emmanuel Chevigny - Pierre Curmi -

Fuente: https://hal.archives-ouvertes.fr/



DESCARGAR PDF




Documentos relacionados