Anais da Academia Brasileira de Ciências
URI permanente para esta coleção${dspace.url}/handle/123456789/13096
Navegar
2 resultados
Resultados da Pesquisa
Item Relations between sensory quality and spectral indices in brazilian arabica coffees(Academia Brasileira de Ciências, 2025-03-17) SARMENTO, CARLA SIMONE A.G.; LEMOS, ODAIR L.; BOFFO, ELISANGELA F.; MATSUMOTO, SYLVANA N.; CASTRO, INGRID THALIA P. DE; ALVARENGA, YASMIN A.This article describes an investigation using spectral indices to characterize coffee production of Brazil, regarding beverage quality and possible correlations with the growing environment. The study evaluated 50 arabica coffee samples, 16 of which were natural process, and 34 were pulped coffes. These samples were originated from growing areas located in different altitude ranges and regions of the municipality, with similar planting spacing and predominance of Catuai cultivars. The samples were subjected to sensory analysis, which revealed that 58% of the samples were classified as specialty coffees: 3 natural, and 26 pulped coffes. Multiple correspondence analysis showed that average spectral indices, normalized difference vegetation index (NDVI), enhanced vegetation index (EVI), and photochemical reflectance index (PRI), derived from images of the multispectral instrument (MSI), were not associated with the quality parameters of the coffee beverage. In contrast, the plant senescence reflectance index (PSRI) proved to be the relevant factor in the quality of the drink. In summary, the analysis of the relationship between the indices demonstrated that the NDVI, which measures the vegetative vigor of plants, showed an inverse correlation with the PSRI. Additionally, the principal component analysis suggested that samples collected from drier areas differed significantly from other geographic regions.Item Classifiers based on artificial intelligence in the prediction of recently planted coffee cultivars using a Remotely Piloted Aircraft System(Academia Brasileira de Ciências, 2023-11-03) Bento, Nicole L.; Ferraz, Gabriel Araújo E.S.; Barata, Rafael Alexandre P.; Soares, Daniel V.; Teodoro, Sabrina A.; Estima, Pedro Henrique De O.The classification and prediction methods through artificial intelligence algorithms are applied in different sectors to assist and promote intelligent decision-making. In this sense, due to the great importance in the cultivation, consumption and export of coffee in Brazil and the technological application of the Remotely Piloted Aircraft System (RPAS) this study aimed to compare and select models based on different data classification techniques by different classification algorithms for the prediction of different coffee cultivars (Coffea arabica L.) recently planted. The attributes evaluated were height, crown diameter, total chlorophyll content, chlorophyll A and chlorophyll B, Foliar Area Index (LAI) and vegetation indexes NDVI, NDRE, MCARI1, GVI, and CI in six months. The data were prepared programming language Python using algorithms of Decision Trees, Random Forest, Support Vector Machine and Neural Networks. It was evaluated through cross-validation in all methods, the distribution by FreeViz, the hit rate, sensitivity, specificity, F1 score, and area under the ROC curve and percentage and predictive performance difference. All algorithms showed good hits and predictions for coffee cultivars (0.768% Decision Tree, 0.836% Random Forest, 0.886 Support Vector Machine and 0.899 Neural Networks) and the Neural Networks algorithm produced more accurate predictions than other tested algorithm models, with a higher percentage of hits for the classes considered.