Due to the differences in terms of both price and quality, the availability of effective instrumentation to discriminate between Arabica and Robusta coffee is extremely important. To this aim, the use of multispectral imaging systems could provide reliable and accurate real-time monitoring at relatively low costs. However, in practice the implementation of multispectral imaging systems is not straightforward: the present work investigates this issue, starting from the outcome of variable selection performed using a hyperspectral system. Multispectral data were simulated considering four commercially available filters matching the selected spectral regions, and used to calculate multivariate classification models with Partial Least Squares-Discriminant Analysis (PLS-DA) and sparse PLS-DA. Proper strategies for the definition of the training set and the selection of the most effective combinations of spectral channels led to satisfactory classification performances (100% classification efficiency in prediction of the test set).

Transferring results from NIR-hyperspectral to NIR-multispectral imaging systems: A filter-based simulation applied to the classification of Arabica and Robusta green coffee / Calvini, Rosalba; Amigo, Jose Manuel; Ulrici, Alessandro. - In: ANALYTICA CHIMICA ACTA. - ISSN 0003-2670. - 967:(2017), pp. 33-41. [10.1016/j.aca.2017.03.011]

Transferring results from NIR-hyperspectral to NIR-multispectral imaging systems: A filter-based simulation applied to the classification of Arabica and Robusta green coffee

CALVINI, ROSALBA;ULRICI, Alessandro
2017

Abstract

Due to the differences in terms of both price and quality, the availability of effective instrumentation to discriminate between Arabica and Robusta coffee is extremely important. To this aim, the use of multispectral imaging systems could provide reliable and accurate real-time monitoring at relatively low costs. However, in practice the implementation of multispectral imaging systems is not straightforward: the present work investigates this issue, starting from the outcome of variable selection performed using a hyperspectral system. Multispectral data were simulated considering four commercially available filters matching the selected spectral regions, and used to calculate multivariate classification models with Partial Least Squares-Discriminant Analysis (PLS-DA) and sparse PLS-DA. Proper strategies for the definition of the training set and the selection of the most effective combinations of spectral channels led to satisfactory classification performances (100% classification efficiency in prediction of the test set).
2017
21-mar-2017
967
33
41
Transferring results from NIR-hyperspectral to NIR-multispectral imaging systems: A filter-based simulation applied to the classification of Arabica and Robusta green coffee / Calvini, Rosalba; Amigo, Jose Manuel; Ulrici, Alessandro. - In: ANALYTICA CHIMICA ACTA. - ISSN 0003-2670. - 967:(2017), pp. 33-41. [10.1016/j.aca.2017.03.011]
Calvini, Rosalba; Amigo, Jose Manuel; Ulrici, Alessandro
File in questo prodotto:
File Dimensione Formato  
1-s2.0-S0003267017302891-main.pdf

Accesso riservato

Tipologia: Versione pubblicata dall'editore
Dimensione 2.69 MB
Formato Adobe PDF
2.69 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
POST PRINT_Transferring results from NIR-hyperspectral to NIR-multispectral imaging systems.pdf

Open access

Tipologia: Versione dell'autore revisionata e accettata per la pubblicazione
Dimensione 4.83 MB
Formato Adobe PDF
4.83 MB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

Licenza Creative Commons
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11380/1131624
Citazioni
  • ???jsp.display-item.citation.pmc??? 3
  • Scopus 35
  • ???jsp.display-item.citation.isi??? 28
social impact