Search

Background The San Francisco Valley region from Brazil is known worldwide for its fruit production and exportation, especially grapes and wines. The grapes have high quality not only due to the excellent morphological characteristics, but also to the pleasant taste of their fruits. Such features are obtained because of the climatic conditions present in the region. In addition to the favorable climate for grape cultivation, harvesting at the right time interferes with fruit properties. Results This work aims to define grape maturation stage of Syrah and Cabernet Sauvignon cultivars with the aid of deep-learning models. The idea of working with these algorithms came from the fact that the techniques commonly used to find the ideal harvesting point are invasive, expensive, and take a long time to get their results. In this work, convolutional neural networks were used in an image classification system, in which grape images were acquired, preprocessed, and classified based on their maturation stage. Images were acquired with varying illuminants that were considered as parameters of the classification models, as well as the different post-harvesting weeks. The best models achieved maturation classification accuracy of 93.41% and 72.66% for Syrah and Cabernet Sauvignon respectively. Conclusions It was possible to correctly classify wine grapes using computational intelligent algorithms with high accuracy, regarding the harvesting time, corroborating chemometric results. © 2020 Society of Chemical Industry.

The use of deep learning models to identify lesions on cotton leaves on the basis of images of the crop in the field is proposed in this article. Cultivated in most of the world, cotton is one of the economically most important agricultural crops. Its cultivation in tropical regions has made it the target of a wide spectrum of agricultural pests and diseases, and efficient solutions are required. Moreover, the symptoms of the main pests and diseases cannot be differentiated in the initial stages, and the correct identification of a lesion can be difficult for the producer. To help resolve the problem, the present research provides a solution based on deep learning in the screening of cotton leaves which makes it possible to monitor the health of the cotton crop and make better decisions for its management. With the learning models GoogleNet and Resnet50 using convolutional neural networks, a precision of 86.6% and 89.2%, respectively, was obtained. Compared with traditional approaches for the processing of images such as support vector machines (SVM), Closest k-neighbors (KNN), artificial neural networks (ANN) and neuro-fuzzy (NFC), the convolutional neural networks proved to be up to 25% more precise, suggesting that this method can contribute to a more rapid and reliable inspection of the plants growing in the field.

The challenges of modern agriculture have led to the development of localized management tools which allow the rationalization of the use and application of pesticides, a reduction in production costs and the optimization of agricultural processes. This study was carried out to develop an algorithm capable of orienting weed control in the management of a corn crop, using digital image analysis to identify the level of weed infestation in the field. The seeds of six species of weed were sown in an experimental plot of corn, and daily images were captured for 40 days for the evaluation of the level of weed infestation (low, intermediate or high). The algorithm developed was able to target information about the plants and soil accurately and discriminate the residual information as referring to either the culture or weeds. The proposed algorithm has achieved 90% accuracy in identifying the level of infestation from images already evaluated by experts. The results can thus be used as part of weed control strategy, with the incorporation of the geographic coordinates of the image making possible the construction of a map of the level of weed infestation in the different areas where the crop is growing.

The determination of the period of harvest is essential in the vineyard. For that, attributes of quality such as Total Soluble Solids (TSS) and phenolic compounds are constantly monitored along the maturation. This work proposes a new non-destructive approach for prediction of TSS, total anthocyanins and yellow flavonoids using RGB images, called IRIS-GRAPE. It is inspired by the process of biometric recognition using the iris. In order to validate the proposed approach, a study comparing its performance with the traditional method was performed, using the average of RGB pixel values of the region of interest (ROI) as input variables for a multiple linear regression. The study used two performance evaluation metrics: the correlation coefficient ( r P ) and the mean square error (MSE). In order to compare the performance differences between the proposed approach, IRIS-GRAPE, and the traditional approach, hypothesis tests were done. The results show that the proposed approach has a superior performance than the traditional method with a confidence level of 95%.

A potência de sinal é um importante parâmetro a ser considerado em um projeto de implantação de rede de sensores sem fio no meio agrícola. Este trabalho tem como objetivo coletar dados de qualidade de sinal transmitido entre uma estação base e um nó sensor situado no interior de uma casa de vegetação, localizada no campo experimental da Faculdade de Engenharia Agrícola - UNICAMP, com o auxílio de ferramentas computacionais. Após a implantação do nó sensor foram realizados experimentos com vista a se verificar alcance e qualidade do sinal de acordo com sua potência. Através desses ensaios foi possível concluir que uma potência de sinal com valor de -12,2 dBm é suficiente para manter a transmissão entre a estação base e nó sensor. Testes também foram realizados com uma potência de sinal de -9,2 dBm e mostraram que a rede possuía qualidade classificada "muito alta" porém, através do teste de duração da bateria, nota-se que existe economia de energia ao se utilizar a potência de sinal de -12,2 dBm. Foi avaliada a influência que o valor da potência de sinal tem sobre a qualidade do sinal de transmissão e recepção, o gasto de bateria e o alcance do sinal. The signal strength is an important parameter to be considered in a project to establish network of wireless sensors in an agricultural environment. This work aims to collect quality data signals transmitted between a base station and a sensor node located inside a greenhouse, which is an experimental field located in the College of Agricultural Engineering - UNICAMP, with the help of computational tools. After sensor node deployment, experiments were performed in order to check range and signal quality. Through these experiments, it was concluded that a radiofrequency power value of -12.2 dBm is sufficient to maintain transmissions between base station and the sensor. Tests were also performed to a radiofrequency power of -9.2 dBm, and showed that the network had quality rated as "very high". However, by testing the battery life, it is noted that there is an energy saving when the radiofrequency power of -12.2 dBm is used. It was shown that the value of the signal strength has an influence on the quality of signal transmission and reception, battery depletion and signal range.

Fruit and vegetable production has been growing significantly every year, in Brazil and worldwide. Therefore, the application of appropriate technologies requires constant improvement and technological investment, from harvest to commercialization. Particularly, packages are a significant part of post-harvest losses statistics for fresh fruit and vegetables; only 10 to 50% from the total yield are reported per year, depending on the country’s development, climate, cold chain employment, logistical aspects, and others. This study introduces the methodology of a packaging design project and discusses results of its application for design and optimization of mango (Mangifera indica L., ‘Tommy Atkins’) and banana (Musa cavendishii ‘Nanica’) packages, based on computer simulation and experimental validation. It was aimed to minimize material volume (reforestation wood - Pinnus ellioiti) by combining structural, thermal, ergonomic and geometric aspects, as effective areas and opening distribution. The Finite Element Method (FEM) was employed for optimization and structural dimensioning, allowing a material volume reduction of 83% for banana package and 67% for mango package. Due to the effective opening area distribution, the cooling time reduction of fruit, which were cooled by forced-air, was on average 50% as for packaging commercially utilized. The results of this study, as well as the methodology applied, may be employed for commercial purposes, such as for reforestation wood packages, provided these are watertight and non-reutilized, even for export markets. The methodology used combined computer and engineering tools, at an appropriate cost-benefit relationship among structural, geometric, thermal and ergonomic aspects.

The grapes dehydration to make wine, in controlled environment and with variance in temperature and humidity, began to be studied with greater emphasis recently for some grape varieties, due to the proven effects on the higher concentration of phenolic compounds and the positive change in aroma. This chapter focuses on process control in with particular emphasis in instrumentation, applied technologies and main quality results.

Agriculture plays a major role in the Brazilian economy so that actions such as reducing costs and improving the productive system are sought continuously. In the cultivation of sugarcane, the control of weeds is among the factors that increase the cost of production, since the weeds compete with the crop for water, nutrients and sunlight, and can compromise harvesting procedures. An automated system capable of distinguishing weed culture is a potential tool in the search for a more economical and sustainable agriculture. Such a system can be associated to equipment for spraying, or even for mapping the field infestation. In this paper, we propose a new approach for automatic classification of weeds and crop digital images. The aim is to assess whether a method based on the visual bag of words can properly discriminate six weeds and sugarcane, rate the classification and the time suitable for implementing real-time operations. In our experiments, we took into account only one descriptor for describing characteristics of the concerned plants. Analyses the results show that the method achieved 94 % hit rate, using a validation set of 149 test images. The processing time for each image is about 34 seconds, indicating the need the adjustment for consider its use in real-time operations. Nevertheless, the method proposed here constitutes an interesting alternative to the construction of functional maps of infestation which, eventually, can be considered in localized agricultural treatment.

The aim of this study was to perform an experimental study to evaluate the proper operation distance between the nodes of a wireless sensor network available on the market for different agricultural crops (maize, physic nut, eucalyptus). The experimental data of the network performance offers to farmers and researchers information that might be useful to the sizing and project of the wireless sensor networks in similar situations to those studied. The evaluation showed that the separation of the nodes depends on the type of culture and it is a critical factor to ensure the feasibility of using WSN. In the configuration used, sending packets every 2 seconds, the battery life was about four days. Therefore, the autonomy may be increased with a longer interval of time between sending packets. Um estudo experimental, visando a avaliar a distância de operação adequada entre os nós de uma rede de sensores sem fio disponível no mercado, foi realizado para diferentes cultivos agrícolas (milho, pinhão-paraguaio e eucalipto), buscando oferecer aos agricultores e pesquisadores dados experimentais do desempenho da rede, que possa good yield are environmental factors, which include high temperatures and high humidity within the facilities, causing stress to the animal and consequent decreased production (SOUSA, 2005).am ser úteis para ser considerados no dimensionamento e no projeto de redes de sensores sem fio em situações semelhantes às estudadas. A avaliação mostrou que a distância de separação dos nós depende do tipo de cultura e é um fator crítico para garantir a viabilidade do uso da RSSF. Na configuração usada, com envio de pacotes a cada 2 segundos, a autonomia da bateria foi de cerca de quatro dias. Portanto, a autonomia pode ser aumentada com um intervalo maior de tempo entre o envio de pacotes.

Este trabalho propõe um método de projeto de embalagem para produtos hortícolas, buscando uma otimização integrada dos aspectos geométricos, estruturais e térmicos, ligados à facilitação do resfriamento e armazenamento refrigerado. Para o dimensionamento e otimização estrutural, foi utilizado o Método dos Elementos Finitos implementado pelo programa ANSYS, obtendo-se oito modelos virtuais de embalagens, com 10% e 14% de área efetiva de aberturas e geometria quadrada, retangular e circular. Para o desenvolvimento dos experimentos, que avaliaram a relação da área de aberturas com o tempo de sete-oitavos de resfriamento, foram construídos protótipos de tábuas de madeira (Pinnus elliotti) de reflorestamento. Nas embalagens, foram acondicionados aproximadamente 13 kg de banana variedade Nanica (Musa cavendishii, cultivar nanica), resfriada num túnel de ar forçado (vazão de ar de 0,32 m³ s-1, temperatura de 8,0±1,2ºC e umidade relativa de 84,5±2,6%). O tempo de resfriamento também foi comparado com aquele obtido quando a mesma quantidade de frutas foi resfriada em embalagens de papelão (2,5% de área efetiva de abertura) e madeira (18% de área efetiva de abertura). Os resultados demonstraram que, entre os protótipos propostos, não houve diferença significativa no tempo de resfriamento dos frutos acondicionados nas embalagens desenvolvidas, sendo o tempo médio de resfriamento de 40,71±2,81 min. Na comparação com as embalagens de papelão e madeira, houve diferenças significativas, sendo que as embalagens comerciais tiveram tempos de resfriamento de 1,25 e 2 vezes maiores. Concluiu-se que a simulação estrutural computacional, aliada a algoritmos de otimização, além de procedimentos experimentais ligados à cadeia do frio, são recursos promissores no auxílio de projetos para embalagens de transporte de produtos hortícolas. This study proposes a methodology for designing boxes for agricultural products based on computational simulation and experimental validation, seeking the integrated optimization of geometric, structural and thermal aspects associated with cooling and refrigerated storage. The Finite Element Method was used for structural dimensioning and optimization. It was implemented using the ANSYS program, obtaining eight virtual models with 10% and 14% of effective opening area with square, rectangular or circular geometry. In order to develop the experiments that evaluated the relation between effective opening area and seven-eighths cooling time, the prototypes were built using reforestation wood (Pinnus elliotti). Approximately 13 kg of bananas (Musa cavendishii cultivar nanica) were packed in the boxes and cooled in a forced-air tunnel (air flow of 0.32 m³ s-1, temperature of 8.0±1.2ºC and relative humidity of 84.5±2.6%). Cooling time was also compared with the one obtained when the same amount of bananas was cooled in the boxes used to transport and store bananas commercially (cardboard box with 2% of effective opening area and a wooden box called " torito" with 18% of effective opening area). The results showed no significant differences in cooling time of bananas packed in boxes with circular, square and rectangular opening, with average cooling time of 40.71±2.81 min. However, when compared with cardboard and torito boxes, there was a significant difference in cooling time of 1.25 to 2 times the time obtained with wooden boxes. In the structural optimization of the EC-60 box (twelve 60 mm in diameter side orifices and 10% of effective opening area); material volume was reduced in 67.3% in relation to the project initial conditions. In compression tests, the box rupture occurred at loads between 5.4 kN and 8.1 kN, values 3 to 4 times heavier than the imposed project condition (2.0 kN). The computational simulation with optimization algorithms associated with cooling time experiments are promising resources to help in the box design for transporting products.