Periódicos
URI permanente desta comunidadehttps://thoth.dti.ufv.br/handle/123456789/3352
Navegar
2 resultados
Resultados da Pesquisa
Item Productivity and grain size of coffee grown in different weed management systems(Editora da Universidade Estadual de Maringá - EDUEM, 2022-08-15) Zaidan, Úrsula Ramos; Campos, Renata Cássia; Faria, Rodrigo Magalhães; Zaidan, Iasmine Ramos; Souza, Wendel Magno de; Santos, Ricardo Henrique Silva; Freitas, Francisco Cláudio Lopes deIntensive weed management is one of the most common practices in coffee cultivation areas. Consequently, some problems, such as soil degradation and the selection of herbicide resistant weed, have increased over time, but, if properly managed, weeds at coffee planting inter-rows can offer benefits of erosion control, nutrient recycling and crop sustainability. The aim of this study is to evaluate the effect of different weed management strategies on the productivity and coffee grain size, i.e., quality. The experiment is installed onto a resprouting Coffea arabica L. site, four years after it was established. Treatments are implanted at planting inter-row Urochloa ruziziensis, Pueraria phaseoloides, and spontaneous vegetation maintained by mowing, herbicides, and weeding. To measure dry matter accumulation, samples are taken with a 0.25 m2 square template at plots maintained by mowing and herbicide application. To evaluate the yield and granulometry, coffee fruits are harvested, processed and classified in a set of 14 sieves (grouped in flat or “moca” shapes). The methods of controlling herbicide and weeding show significance in relation to grain production, with the production of grains having a higher market value standing out, when compared with the other treatments. The accumulation of dry matter above soil, in treatments with herbicides and spontaneous vegetation positively influenced the early coffee productivity (2018), and with U. ruziziensis and spontaneous vegetation, positively influenced the productivity of late harvest (2019). The accumulation of dry matter on the soil tends to be positively linked to coffee productivity, especially in periods when there is a shortage of rain in the region under study; however, it cannot be stated that this influence relationship (causality) has a direct positive effect between dry matter mass production and productivity of future coffee plantations.Item Quality assessment of coffee beans through computer vision and machine learning algorithms(Editora UFLA, 2020) Santos, Fernando Ferreira Lima dos; Rosas, Jorge Tadeu Fim; Martins, Rodrigo Nogueira; Araújo, Guilherme de Moura; Viana, Lucas de Arruda; Gonçalves, Juliano de PaulaThe increasing market interest in coffee beverage, lead coffee growers around the world to adopt more efficient methods to select the best-quality coffee beans. Currently, coffee beans selection is carried out either manually, which is a costly and unreliable process, or using electronic sorting machines, which are often inefficient because some coffee beans defects, such as sour and immature beans, have similar spectral response patterns. In this sense, the present work aimed to analyze the importance of shape and color features for different machine learning techniques, such as Support Vector Machine (SVM), Deep Neural Network (DNN) and Random Forest (RF), to assess coffee beans’ defects. For this purpose, an algorithm written in Python language was used to extract shape and color features from coffee beans images. The dataset obtained was then used as input to the machine learning algorithms, developed using Python and R programing languages. The data reported in this study pointed to the importance of color descriptors for classifying coffee beans defects. Among the variables used, the components Gmean from RGB (Red, Green and Blue) color space and Vmean from HSV (Hue, Saturation and Value) color space were some of the most relevant features for the classification models. The results reported in this study indicate that all the classifier models presented similar performance. In addition, computer vision along with machine learning algorithms can be used to classify coffee beans with a very high accuracy (> 88%).