The paper presents an empirical study concerning the use of Convolutional Neural Networks (CNN) for hyperspectral data classification. The type and the size of input data have been analyzed to both optimize accuracy and training time. An entropy-based method for selecting the number of CNN input features has also been adopted; for fixed operational setup, it allows to preserve accuracy rate, while greatly decreasing the training time. Experimental results refer to source spectra and their reduced version through principal components analysis (PCA) and show that a proper selection of principal components allows to greatly reduce the computing time, while still guaranteeing high classification accuracies.

An entropy-based speed up for hyperspectral data classification via CNN / Bruni, V.; Monteverde, G.; Vitulano, D.. - 2022-September:(2022), pp. 1-5. (Intervento presentato al convegno Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing (WHISPERS) tenutosi a Roma) [10.1109/WHISPERS56178.2022.9955127].

An entropy-based speed up for hyperspectral data classification via CNN

Bruni V.
;
Monteverde G.;Vitulano D.
2022

Abstract

The paper presents an empirical study concerning the use of Convolutional Neural Networks (CNN) for hyperspectral data classification. The type and the size of input data have been analyzed to both optimize accuracy and training time. An entropy-based method for selecting the number of CNN input features has also been adopted; for fixed operational setup, it allows to preserve accuracy rate, while greatly decreasing the training time. Experimental results refer to source spectra and their reduced version through principal components analysis (PCA) and show that a proper selection of principal components allows to greatly reduce the computing time, while still guaranteeing high classification accuracies.
2022
Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing (WHISPERS)
hyperspectral image; convolutional neural networks; principal components analysis; differential entropy; training time
04 Pubblicazione in atti di convegno::04b Atto di convegno in volume
An entropy-based speed up for hyperspectral data classification via CNN / Bruni, V.; Monteverde, G.; Vitulano, D.. - 2022-September:(2022), pp. 1-5. (Intervento presentato al convegno Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing (WHISPERS) tenutosi a Roma) [10.1109/WHISPERS56178.2022.9955127].
File allegati a questo prodotto
File Dimensione Formato  
Bruni_Entropy-based_2022.pdf

solo gestori archivio

Tipologia: Documento in Post-print (versione successiva alla peer review e accettata per la pubblicazione)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 334.6 kB
Formato Adobe PDF
334.6 kB Adobe PDF   Contatta l'autore

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11573/1671777
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? ND
social impact