https://repositorio.ufu.br/handle/123456789/5473 2026-08-19T09:32:22Z 2026-08-19T09:32:22Z https://repositorio.ufu.br/handle/123456789/49389 2026-08-17T18:58:09Z 2026-02-25T00:00:00Z

Title: Modelos de inteligência artificial para predição de indicação e do risco de lesões em atletas de futebol feminino Abstract: Physical training plays a key role in enhancing athletes’ performance in the pursuit of high-level results; however, this context can trigger adverse effects that harm both these professionals and sports organizations. Sports injuries emerge from a complex network of factors, however, their occurrence is strongly associated with inadequate training load volumes. The aim of this work is to predict the indication and risk of injuries in professional female soccer athletes, where the injury indication is a binary value (0 or 1) and the risk is a value between 0 and 1. In this study, 11,612 daily records from athletes of two professional female soccer clubs in Norway were used, collected via the Player Monitoring System (pmSys) application during the 2020 and 2021 seasons. The database used includes variables related to training load, well-being, and injury occurrence. Training load variables were collected using the Rating of Perceived Exertion (RPE) scale, a tool that quantifies exercise intensity based on the athlete’s perception. In the dataset, injuries were recorded on the day they occurred, serving as the model’s output variable. Injury indication prediction models were developed using Decision Tree and Random Forest machine learning methods. The metrics used to evaluate model performance were sensitivity (success rate of positive predictions) and accuracy (success rate of all predictions). Random Forest outperformed Decision Tree, presenting a sensitivity rate of 64.52% and an accuracy rate of 98.71%. To predict injury risk, neuro-fuzzy methods were applied: the Dynamic Evolving Neural Fuzzy Inference System (DENFIS) and the Subtractive Clustering Method with Fuzzy C-Means (SBC/FCM). Each model employs four training and well-being–related input variables to generate a Fuzzy Rule-Based System (FRBS) aimed at predicting the athlete’s injury risk. In the test set, the DENFIS model presented a sensitivity rate of 75% and an accuracy rate of 85.38%, while the SBC/FCM model obtained a sensitivity of 75% and an accuracy of 91.70%. Using k-fold cross-validation with k=5, the DENFIS model achieved higher percentages across the folds in the sensitivity metric. In the injury risk models, to address the imbalance of the “injury” attribute, since its occurrence is generally of low frequency, the Synthetic Minority Over-sampling Technique (SMOTE) was applied to generate synthetic data for the minority class (injury). This study also developed a computational interface using R software that calculates the user’s injury risk based on physical training and well-being data, utilizing the model obtained by DENFIS.

2026-02-25T00:00:00Z https://repositorio.ufu.br/handle/123456789/48968 2026-07-23T06:22:58Z 2026-02-24T00:00:00Z

Title: Matemática financeira: despertando a consciência financeira em crianças e adolescentes Abstract: Financial Mathematics plays a fundamental role in students’ education, as its concepts are directly related to everyday situations involving consumption, planning, and financial decision-making. However, its approach in Basic Education still faces challenges, particularly with regard to the contextualization of content and the availability of pedagogical materials that support teachers’ classroom practices. In this context, this study aims to develop didactic games and teaching sequences for the instruction of Financial Mathematics at different stages of Basic Education, with a focus on supporting teaching practice. The research has a propositional nature and adopts a qualitative approach, centered on the development of educational products applicable to the school context. Three original didactic games were developed — Mercadinho da Matemática, Família emEquilíbrio, and Simulador de Investimentos — each accompanied by structured tea ching sequences designed to guide their use in the classroom. The application of two of these games in a school setting had a pedagogical and formative character, enabling the analysis of the contributions of the materials to the mobilization of Financial Mathematics concepts, decision-making processes, and student learning. The results indicate that the games and teaching sequences constitute viable and relevant pedagogical resources, contributing to the contextualization of Financial Mathematics teaching and to the support of teachers’ work in Basic Education.

2026-02-24T00:00:00Z https://repositorio.ufu.br/handle/123456789/48926 2026-07-21T06:27:49Z 2026-03-19T00:00:00Z

Title: Área máxima de um triângulo equilátero circunscrito a um triângulo qualquer Abstract: This work explores a classic optimization problem in Plane Euclidean Geometry: determining the equilateral triangle with the largest area that circumscribes any given triangle. The approach adopted relattes tools from Geometry and Differential Calculus, allowing the modeling of geometric quantities through real functions and the analysis of their maximum values using analytical techniques. A proof of this classic problem is presented, accompanied by a geometric construction using ruler and compass. As an applied development, a didactic sequence aimed at elementary and secondary education is proposed, as well as a report of its application in the classroom.

2026-03-19T00:00:00Z https://repositorio.ufu.br/handle/123456789/48916 2026-07-21T06:27:46Z 2026-02-26T00:00:00Z

Title: O teorema da fibração de Milnor para singularidades reais Abstract: The main objective of this work is to present and prove the classic Milnor Fibration Theorem for Real Singularities. To provide a foundation for understanding this result, we first establish the study of differentiable manifolds, including the case of manifolds with boundary. Next, we review essential concepts of algebraic topology, such as contractible spaces, homology, cohomology, CW complexes, and homotopy groups. We present a review of algebraic sets and, as a fundamental tool for the main proof, we demonstrate the Curve Selection Lemma. We introduce the notions of fiber bundles and fibrations, also discussing Ehresmann’s Fibration Theorem for both manifolds without boundary and manifolds with boundary. Finally, we prove the Milnor Fibration Theorem for the real case and analyze the topology of the resulting fibers.

2026-02-26T00:00:00Z