SBICafé
Biblioteca do Café

Classification of the maturity stage of coffee cherries using comparative feature and machine learning

Show simple item record

dc.contributor.author Velásquez, Sebastián
dc.contributor.author Franco, Arlet Patricia
dc.contributor.author Peña, Néstor
dc.contributor.author Bohórquez, Juan Carlos
dc.contributor.author Gutiérrez, Nelson
dc.date.accessioned 2021-09-15T10:16:35Z
dc.date.available 2021-09-15T10:16:35Z
dc.date.issued 2021
dc.identifier.citation VELÁSQUEZ, S. et al. Classification of the maturity stage of coffee cherries using comparative feature and machine learning. Coffee Science, Lavras, v. 16, p. 1-11, 2021. pt_BR
dc.identifier.issn 1984-3909
dc.identifier.uri https://doi.org/10.25186/.v16i.1710 pt_BR
dc.identifier.uri http://www.sbicafe.ufv.br/handle/123456789/12798
dc.description.abstract This work presents the use of multiple techniques (i.e., physicochemical and spectral) applied to harvested coffee cherries for the postharvest classification of the maturity stage. The moisture content (MC), total soluble solids (TSS), bulk density, fruits’ hardness, CIEL*a*b parameters and the dielectric spectroscopy methods were applied on coffee cherries at seven maturity stages. These maturity stages were assessed according to the days after flowering (DAF) and the physical appearance as traditionally performed by growers. An increase of the green-to-red ratio (i.e., a*) parameter was perceived, accompanied by a monotonic response for the hardness, TSS and bulk density with a maximum moisture content at stage 5. In the case of the dielectric spectroscopy technique, the loss parameter presented higher losses for unripe stages at the ionic conduction region. To compare the individual performance of each of the techniques, three machine learning methods were used: random forest (RF), support vector machine (SVM) and k-nearest neighbours (k-NN). The meta-parameters for these techniques were optimized for each case to achieve the best performance possible. Furthermore, as the dielectric response is of spectral nature, recursive feature selection was applied and the 500 MHz to 1.3 GHz frequency range selected for the task. The highest performance was obtained for the colorimetric (75.1%) and hardness (72.5%) responses, while the lowest was obtained for the moisture content (45.5%). The dielectric spectroscopy response presented a promising response (56.8%), that achieved a clear separation of unripe from ripe stages, except for stage 5 in which some of the samples were classified as stage 2. Most techniques studied are compatible with field conditions, and the dielectric technique shows potential to be transferred based on available software-radio defined platforms. pt_BR
dc.format pdf pt_BR
dc.language.iso en pt_BR
dc.publisher Editora UFLA pt_BR
dc.relation.ispartofseries Coffee Science:v.16;
dc.rights Open Access pt_BR
dc.subject Dielectric spectroscopy pt_BR
dc.subject Coffee maturity pt_BR
dc.subject Postharvest classification pt_BR
dc.subject Physicochemical analysis pt_BR
dc.subject.classification Cafeicultura::Colheita, pós-colheita e armazenamento pt_BR
dc.title Classification of the maturity stage of coffee cherries using comparative feature and machine learning pt_BR
dc.type Artigo pt_BR

Files in this item

Files Size Format View
Coffee Science_v. 16_1710_2021.pdf 3.252Mb application/pdf View/Open ou Pre-visualizar

This item appears in the following Collection(s)

Show simple item record

Search DSpace


Sobre o SBICafé

Browse

My Account