NLDR methods for high dimensional NIRS dataset: application to vineyard soils characterization

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.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [11 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01148868
Contributor : Ludovic Journaux <>
Submitted on : Tuesday, May 5, 2015 - 3:24:54 PM
Last modification on : Friday, December 21, 2018 - 1:46:01 PM
Document(s) archivé(s) le : Monday, September 14, 2015 - 7:16:15 PM

File

esann2015_Delion.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01148868, version 1

Citation

Clément Delion, Ludovic Journaux, Aurore Payen, Lucile Sautot, Emmanuel Chevigny, et al.. NLDR methods for high dimensional NIRS dataset: application to vineyard soils characterization. 23 th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN'15), Michel Verleysen, Apr 2015, Bruges, Belgium. ⟨hal-01148868⟩

Share

Metrics

Record views

1029

Files downloads

281