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

Research output: Contribution to journalJournal articleResearchpeer-review

Rosalba Calvini, Jose Manuel Amigo Rubio, Alessandro Ulrici

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).

Original languageEnglish
JournalAnalytica Chimica Acta
Volume967
Pages (from-to)33-41
Number of pages9
ISSN0003-2670
DOIs
Publication statusPublished - 2017

    Research areas

  • Green coffee, Hyperspectral imaging, Multispectral imaging, Multivariate classification, Sparse methods

ID: 176437958