https://repositorio.ufu.br/handle/123456789/19618 2026-09-17T09:04:58Z 2026-09-17T09:04:58Z https://repositorio.ufu.br/handle/123456789/50259 2026-09-15T06:26:32Z 2026-08-06T00:00:00Z

Title: Modelagem preditiva da estabilidade de formulações cosméticas multicomponentes: um estudo comparativo de modelos de aprendizado de máquina Abstract: Physicochemical stability is a critical attribute in the development of multicomponent cosmetic formulations, and its assessment traditionally relies on time-consuming empirical tests. In this context, the present study aimed to compare the performance of tree-based machine learning models, such as Decision Tree, Random Forest and XGBoost, in the classification of shampoo formulation stability, using ingredient mass fractions as predictor variables. As a database, the experimental dataset of 812 formulations available in the literature was employed, from which stability was selected as the binary target variable (stable or unstable). The methodology involved data preparation and exploratory data analysis, followed by stratified splitting into train and test sets, cross-validation and hyperparameter optimization through grid search (GridSearchCV). The exploratory analysis revealed high sparsity, strong asymmetry and the absence of linear separability between classes, which justified the use of non-linear models. Performance was evaluated using F1-score, accuracy, precision and recall metrics, as well as error analysis through confusion matrices. A consistent progression in performance was observed with increasing model complexity: the Decision Tree, used as a reference, achieved an F1-score of 0.66 and accuracy of 68%, while the ensemble models, Random Forest and XGBoost, improved these metrics to an equivalent extent, reaching a test F1-score of 0.71 and accuracy of approximately 77%. Given the statistical equivalence between the two ensemble models on the test set, the mean cross-validation performance was adopted as the selection criterion, in which Random Forest achieved the best result (F1-score of 0.70), being selected as the final model. Feature importance analysis indicated thickeners and conditioning polymers as the most influential ingredients on stability, consistent with the combinatorial nature of the system. The results illustrate the potential of tree-based predictive models as a tool to support more agile and data-driven cosmetic formulation development.

2026-08-06T00:00:00Z https://repositorio.ufu.br/handle/123456789/50181 2026-09-10T06:21:21Z 2026-08-04T00:00:00Z

Title: Produção e aplicação do biocarvão para remoção de poluentes

2026-08-04T00:00:00Z https://repositorio.ufu.br/handle/123456789/50066 2026-09-04T06:31:19Z 2026-08-03T00:00:00Z

Title: Produção de biohidrogênio por fementação escura a partir do bagaço de cana de açúcar: análise comparativa dos principais métodos pré tratamentos e seus efeitos no rendimento do processo Abstract: The increasing global demand for energy and the need to reduce greenhouse gas emissions have intensified the search for renewable energy sources capable of meeting sustainability principles. In this context, biohydrogen has emerged as a promising energy alternative due to its potential to utilize agro-industrial residues while contributing to the reduction of dependence on fossil fuels. Among the available feedstocks, sugarcane bagasse has considerable potential because of its wide availability in Brazil and its high content of structural carbohydrates that can be converted into hydrogen through dark fermentation. However, the high recalcitrance of this lignocellulosic biomass, resulting from the presence of lignin, limits its biodegradation, making the application of pretreatment methods essential to increase the accessibility of cellulose and hemicellulose to fermentative microorganisms. The main pretreatment methods applied to lignocellulosic biomass include physical, chemical, physicochemical, and biological processes, whose effectiveness is directly associated with operational parameters such as pH, temperature, inoculum, and hydraulic retention time, all of which influence the performance of the fermentative process. The results demonstrated that alkaline and physicochemical pretreatments were more effective in promoting partial lignin removal and increasing cellulose fiber exposure, thereby enhancing the release of fermentable sugars. In the case study, the combined application of an alkaline solution and ultrasound promoted structural modifications confirmed by X-ray diffraction and Fourier-transform infrared spectroscopy, resulting in an approximately thirty-five percent increase in biohydrogen production and favoring the formation of acetic and butyric acids, metabolites associated with higher hydrogen yields. These findings demonstrate that the integration of efficient pretreatment strategies with appropriate control of operational conditions is a determining factor in maximizing the conversion of sugarcane bagasse into biohydrogen, reinforcing the potential of this biomass as a feedstock for sustainable energy production and the development of biorefineries.

2026-08-03T00:00:00Z https://repositorio.ufu.br/handle/123456789/50060 2026-09-04T06:31:10Z 2026-07-31T00:00:00Z

Title: Soluções sustentáveis na cosmética: a integração entre biocosméticos e técnicas de produção mais limpa Abstract: In recent years, the cosmetic sector has faced a growing demand for sustainable practices, driven both by environmental pressures and the demands of more conscious consumers. In this context, biocosmetics and green cosmetics emerge as more sustainable alternatives, combining natural, organic, and cruelty-free ingredients with production practices that have a lower environmental impact. This study aimed to analyze, through a literature review, the integration between Cleaner Production (CP) strategies and the development of biocosmetics, highlighting how this synergy can promote sustainable solutions for the beauty industry. The research covered the concepts and hierarchical levels of CP application within the cosmetic production chain, the characterization and differentiation of conventional, natural, organic, vegan, and biocosmetic products, and the analysis of well-established practices in the sector, illustrated by the cases of Natura, L'Oréal, and Grupo Boticário. The results indicate that the integration between CP and biocosmetics constitutes a complementary and technically viable strategy, capable of simultaneously reducing water and energy consumption, the generation of polluting effluents, and dependence on petrochemical inputs, while adding market value through alignment with ESG criteria. However, technical, economic, and regulatory challenges that still limit large-scale adoption were identified, such as the instability of natural formulations, certification costs, and the absence of a unified legal definition for the term biocosmetic. The results are expected to contribute to the dissemination of clean technologies, the strengthening of environmental responsibility in the cosmetic segment, and the formulation of guidelines for future sustainable innovations in the field.

2026-07-31T00:00:00Z