Bananas (cv. Musa nana and Musa cavendishii) fresh and dried by hot air at 50 and 70°C and lyophilisation were analysed for phenolic contents and antioxidant activity. All samples were subject to six extractions (three with methanol followed by three with acetone/water solution). The experimental data served to train a neural network adequate to describe the experimental observations for both output variables studied: total phenols and antioxidant activity. The results show that both bananas are similar and air drying decreased total phenols and antioxidant activity for both temperatures, whereas lyophilisation decreased the phenolic content in a lesser extent. Neural network experiments showed that antioxidant activity and phenolic compounds can be predicted accurately from the input variables: banana variety, dryness state and type and order of extract. Drying state and extract order were found to have larger impact in the values of antioxidant activity and phenolic compounds.
RESUMO -Em razão de estudos e especulações envolvendo a questão da soja RR sob aplicação de glyphosate, são necessárias investigações que permitam esclarecer melhor essa situação. O presente trabalho teve por objetivo avaliar o desempenho agronômico e os teores de óleo e proteínas sob aplicação do herbicida glyphosate na cultura da soja transgênica. Para isso, foi desenvolvido um ensaio em delineamento em blocos casualizados, com quatro repetições, em que os tratamentos avaliados consistiram da pulverização foliar contendo glyphosate, em doses crescentes, aplicadas nos estádios V 6 e R 2 . As variáveis avaliadas foram: altura média das plantas, número de vagens por planta, massa de mil grãos e produtividade, assim como os teores de óleo e proteínas. Verificou-se que o glyphosate, especialmente quando usado em R 2 , pode comprometer o desempenho agronômico e os teores de proteínas.Palavras-chave: Glycine max, herbicida, produção.ABSTRACT -Previous studies and speculation involving the behavior of Roundup Ready soybean under glyphosate application requires further investigations to clarify this issue. This study aimed to evaluate the agronomic performance and oil and protein contents of transgenic soybean culture under glyphosate application. Thus, an assay was carried out in a completely randomized block design, with four replications. Treatments consisted of foliar sprays in increasing doses of glyphosate applied at stages V6 and R2. The variables evaluated were: plant height, number of pods per plant, thousand grain weight and yield, as well as oil and protein contents. It was verified that glyphosate, especially when used in R2, can compromise both the agronomic performance and protein contents.
The present work assessed the influence of different factors on some physical and chemical properties of nuts. The factors evaluated were the presence or absence of the inner skin, geographical origin, storage conditions (ambient temperature, in a stove at 30 and 50°C, in a chamber at 30 and 50°C and 90 % RH, refrigerated and freezing) and type of package (none, low density polyethylene and low density polyethylene). The fruits studied were almonds, hazelnuts and walnuts from different countries. The properties measured were moisture content, water activity, colour coordinates (L*, a* and b*) and texture parameters (hardness and friability). Experimental data were modelled using neural networks. The results showed that the almonds from Spain and Romania had a w greater than 0.6, and therefore, its stability was not guaranteed, contrarily to the other samples that presented values of a w lower than 0.6. The colour coordinate lightness varied from 40.60 to 49.30 in the fresh samples but decreased during storage, indicating darkening. In general, an increase in hardness and friability was observed with the different storage conditions. Neuron weight analysis has shown that the origin was a good predictor for moisture content and texture; whereas, the storage condition was a good predictor for a w and colour. In conclusion, it was possible to verify that the properties of nuts are very different depending on origin; they are better preserved at lower temperatures and the type of package used did not impact the properties studied.
Maintenance professionals and other technical staff regularly need to learn to identify new parts in car engines and other equipment. The present work proposes a model of a task assistant based on a deep learning neural network. A YOLOv5 network is used for recognizing some of the constituent parts of an automobile. A dataset of car engine images was created and eight car parts were marked in the images. Then, the neural network was trained to detect each part. The results show that YOLOv5s is able to successfully detect the parts in real time video streams, with high accuracy, thus being useful as an aid to train professionals learning to deal with new equipment using augmented reality. The architecture of an object recognition system using augmented reality glasses is also designed.
The accuracy of a predictive system is critical for predictive maintenance and to support the right decisions at the right times. Statistical models, such as ARIMA and SARIMA, are unable to describe the stochastic nature of the data. Neural networks, such as long short-term memory (LSTM) and the gated recurrent unit (GRU), are good predictors for univariate and multivariate data. The present paper describes a case study where the performances of long short-term memory and gated recurrent units are compared, based on different hyperparameters. In general, gated recurrent units exhibit better performance, based on a case study on pulp paper presses. The final result demonstrates that, to maximize the equipment availability, gated recurrent units, as demonstrated in the paper, are the best options.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.