Principais Coleções do Repositório
Submissões Recentes
dissertação
Aplicação de métodos baseados em lógica fuzzy e de aprendizado de máquina para a previsão de preços de commodities
(Universidade Federal de Lavras, 2026-02-06) Souza, João Vitor Andrade Alves de; Pereira, Geraldo Magela da Cruz; Simão, Sérgio Domingos; Silva, Gabi Nunes; Oliveira, Anderson Castro Soares de
Corn and soybeans are two of the main agricultural commodities in Brazil, playing a strategic role in the Brazilian economy. Forecasting their prices is of utmost importance to support decision-making in the agro-industrial sector. This study aims to evaluate the use of Fuzzy Time Series (FTS) methods for forecasting the prices of these commodities, considering univariate and multivariate approaches. These models were applied and compared to Machine Learning (ML) algorithms, such as Random Forest, XGBoost, LightGBM, among others. The dataset used in the first article comprises daily corn price data for the period from 2007 to 2025, in the state of Minas Gerais, with three subsets, beginning in 2007, 2014, and 2021. The data used in the second article refer to the global price of soybeans, other commodities, and their derivatives, collected monthly from 1960 to 2025. After partitioning the data into training and test sets, the FTS models and machine learning algorithms were trained and evaluated on the test set. Performance evaluation metrics were used, such as Mean Absolute Percentage Error (MAPE), Mean Absolute Scaled Error (MASE), Mean Directional Accuracy (MDA), among other measures widely used in the evaluation of forecasting models. In the univariate case, the results indicate that the Probabilistic Weighted FTS (PWFTS) model presented the best performance, with lower forecasting errors and higher directional accuracy when trained with data beginning in 2014, and with a one-day forecasting horizon. In contrast, the high order FTS (HOFTS) and Weighted HOFTS (WHOFTS) models presented slightly lower performance than that observed for PWFTS. Nevertheless, HOFTS and WHOFTS maintained consistent performance, although with variations among the different training strategies used. For the multivariate case, the results indicated that the models based on fuzzy logic, especially the Weighted Multivariate FTS (WMVFTS) with 20% of test data and 60 partitions, obtained the best overall performance, presenting the lowest forecasting errors and high directional accuracy. It is concluded that Fuzzy Time Series methods constitute a good alternative for forecasting agricultural commodity prices, proving to be suitable both in univariate and multivariate contexts and at different time scales.
Artigo
Comparação de recursos pedagógicos em ações de educação alimentar e nutricional com crianças
(2022-11-21) Inácio, Monique Louise Cassimiro; Santos, Anabele Pires; Pereira, Rafaela Corrêa; Pereira, Michel Cardoso de Angelis
Food and Nutrition Education (FNE) has become an important strategy designed to promote better food choices and to prevent diseases. The aim of this study was to evaluate three pedagogical resources used in FNE interventions. Fifty-six children were invited to participate. They were divided into three groups. After applying exclusion criteria, the group division were A (n = 20), B (n = 12) and C (n = 13). The study consisted of: initial assessment (t = 0), interventions, second assessment (t = 1) and third assessment performed three weeks later (t = 2). To evaluate the interventions outcomes, it were used 24h food recall and questionnaire. Each group received an intervention based on different theory. The lecture represented the traditional pedagogy. Workshop for juice elaboration was developed through bases of Johaan Henrich Pestalozzi’s theory and the history book, contemplated bases of theoretical framework of Paulo Freire. The results showed, in general, all interventions got great outcomes in increasing the level of knowledge about food and nutrition, however the lecture and the development of a juice using the bases of the intuitive method proposed by Pestalozzi, respectively, showed lower levels of forgetfulness.
Artigo
Dhuoda (806-811? – 843?)
(2022) Sousa, Meline Costa
Artigo
Vigilância alimentar e nutricional: estudo com pré-escolares e escolares participantes do Programa Bolsa Família
(2022-09-30) Santos, Rayane Oliveira; Bernardes, Milena Serenini; Alvarenga, Ana Pereira; Bernardes, Renan Serenini; Toloni, Maysa Helena de Aguiar
To describe the situation of food and nutritional [in]security of preschool and school children participating in the Bolsa Família Program. Methods:cross-sectional study with families of preschool and school age children. Questionnaires of socioeconomic characterization, food consumption and the Brazilian Food Insecurity Scale were applied. Anthropometric and food assessment was performed following the protocols of the Food and Nutrition Surveillance System. For the statistical analysis, a chi-square test was performed with a significance level of 5%. Results:144 families and 163 children were considered. The prevalence of food insecurity was 74.3%, and 29.4% of the children were overweight. There was a high consumption of ultra-processed foods, especially sugary drinks (80.4%). A statistically significant association was identified between the use of electronic devices and the consumption of sweets. Conclusion: to expand the positive effects of the Bolsa Família Program, intersectoral action is important with a view to strengthening food security programs and regulatory actions in food.Descriptors: Child nutrition; Eating; Food security;Public health administration.Objetivo: describir la situación de [in]seguridad alimentaria y nutricional de los preescolares y escolares participantes en el Programa Bolsa Família.Método: estudio transversal con familias de niños preescolares y escolares. Se aplicaron los cuestionarios de caracterización socioeconómica, de consumo de alimentos y la Escala Brasileña de Inseguridad Alimentaria. La evaluación antropométrica y alimentaria se realizó siguiendo los protocolos del Sistema de Vigilancia Alimentaria y Nutricional. Para el análisis estadístico, serealizó la prueba de chi-cuadrado con un nivel de significación del 5%.Resultados: Se consideraron 144 familias y 163 niños. La prevalencia de la inseguridad alimentaria fue del 74,3% y el 29,4% de los niños tenían sobrepeso. Se observó un elevado consumo de alimentos ultraprocesados, especialmente de bebidas azucaradas (80,4%). Se identificó una asociación estadísticamente significativa entre el uso de dispositivos electrónicos y el consumo de golosinas.Conclusión: para ampliar los efectos positivos delPrograma Bolsa Família es importante la actuación intersectorial con vistas al fortalecimiento de los programas de seguridad alimentaria y de las acciones reguladoras en la alimentación.Descriptores: Nutrición del niño;Ingestión de Alimentos; Seguridad alimentaria; Administración en salud pública.Autor Correspondente: Milena Serenini -miserenini@gmail.comto describe the situation of food and nutritional [in]security of preschool and school children participating in the Bolsa Família Program. Methods:cross-sectional study with families of preschool and school age children. Questionnaires of socioeconomic characterization, food consumption and the Brazilian Food Insecurity Scale were applied. Anthropometric and food assessment was performed following the protocols of the Food and Nutrition Surveillance System. For the statistical analysis, a chi-square test was performed with a significance level of 5%. Results:144 families and 163 children were considered. The prevalence of food insecurity was 74.3%, and 29.4% of the children were overweight. There was a high consumption of ultra-processed foods, especially sugary drinks (80.4%). A statistically significant association was identified between the use of electronic devices and the consumption of sweets. Conclusion: to expand the positive effects of the Bolsa Família Program, intersectoral action is important with a view to strengthening food security programs and regulatory actions in food.
Artigo
Kinetics and mineralization fraction of organic matter from sewage sludge mixed with soil under controlled laboratory conditions
(2022-12-27) Silva, Diogo André Pinheiro da; Matos, Mateus Pimentel; Marques, Marcus Vinícius Araújo; Matos, Antonio Teixeira de; Neves, Thiago de Alencar
The objective of this work was to evaluate the kinetics and mineralization fraction of organic matter from sewage sludge mixed with the soil under controlled laboratory conditions. For this, organic material samples accumulated in layers 0–5 cm, 5–10 cm and 10–15 cm in relation to the surface of a vertical flow constructed wetland system (VF-CW) used for treatment of septic tank sludge, in addition to samples of dewatered sludge from a septic tank and a UASB reactor and non-dewatered sludge from an anaerobic digester were mixed with material collected from the surface layer of a Red Yellow Argisol at rates equivalent to the applications, via organic residues, of 300 and 600 kg ha−1 year−1 of total nitrogen. It was found that the two-phase kinetic equation fit better to the mineralization data of labile and recalcitrant organic carbon. For the lowest nitrogen application rate in the mixtures, the mineralization fractions of the total organic carbon were higher than 73%, while at the highest dose there was a reduction in the mineralization of organic matter by 17% and 63%, respectively in samples collected in layer 10–15 cm from the VF-CW and in the septic tank sludge dewatered in the drying bed.