https://repositorio.ufu.br/handle/123456789/17903 Fri, 28 Aug 2026 13:40:19 GMT 2026-08-28T13:40:19Z https://repositorio.ufu.br/handle/123456789/49941 Title: Estudo de caso do uso de um sistema de gerenciamento de banco de dados para detecção de cyberbullying Abstract: The ease of access to social media has intensified episodes of cyberbullying among users, a practice that negatively affects victims’ lives. Given this problem, this work aims to evaluate the applicability of PGVector (an extension for creating VDBMSs) in processes for detecting messages potentially associated with cyberbullying, combining semantic similarity search with a supervised machine learning model. To this end, data from the X platform (formerly Twitter) were collected and submitted to a method structured in six steps: textual preprocessing, vector representation, sampling, storage in PostgreSQL with the PGVector extension, classification, and evaluation of results. In the classification step, three embedding generation models were compared — SBERT, BERT, and FastText —, each combined with the kNN algorithm executed directly in the VDBMS. The results showed that SBERT achieved the best performance (k = 9, f1-score of 0.77), outperforming BERT (k = 7, f1-score of 0.65) and FastText (k = 5, f1-score of 0.59), confirming that embeddings optimized for similarity comparison are more suitable for this type of task. It is concluded that PostgreSQL, through PGVector, is capable of acting as a complete similarity-based classification environment, validating its applicability for cyberbullying detection. Tue, 28 Jul 2026 00:00:00 GMT https://repositorio.ufu.br/handle/123456789/49941 2026-07-28T00:00:00Z https://repositorio.ufu.br/handle/123456789/49865 Title: Sistema agroclimático para previsão de safras para pequenos e médios agricultores Abstract: This work presents PredAgro, a web platform designed to support the agricultural planning of small and medium-sized producers, with a focus on climate risk analysis and productivity estimation. The proposal stems from the need to offer an accessible, explainable, and low-cost solution capable of integrating agrometeorological data, rural property records, and crop-specific agronomic rules. The solution was developed with a React front-end, Node.js back-end, and Firebase persistence, utilizing Firestore for storage and Firebase Authentication for user access. For the climate component, queries were integrated with Open-Meteo—a free, opensource platform for short-term weather forecasting and historical series. In the platform, short-term forecasting supports the field weather view, while agricultural planning uses historical climatology as the basis for the analyzed cycle. The system implements farm and plot registration, geographic mapping, planning by crop and period, risk assessment by category, and the generation of an estimated productivity range. The results demonstrate that the platform produces consistent analyses according to the provided climate scenario, indicating increased risk and reduced estimated productivity in adverse situations, such as drought or intense rainfall, and greater stability in conditions closer to ideal cultivation ranges (according to the specific crop). It is concluded that the proposal fulfills the objective of offering a functional basis for decision support in the agricultural context through an agroclimatic system based on agronomic rules, crop parameters, and historical climatology for planning. Short-term weather forecasting is used only for the field weather view, while the planning report relies entirely on historical climatology. Thu, 23 Jul 2026 00:00:00 GMT https://repositorio.ufu.br/handle/123456789/49865 2026-07-23T00:00:00Z https://repositorio.ufu.br/handle/123456789/49684 Title: Seleção de atributos para monitoração de Cloud-Networks: uma Análise do compromisso entre desempenho preditivo e complexidade computacional Fri, 27 Mar 2026 00:00:00 GMT https://repositorio.ufu.br/handle/123456789/49684 2026-03-27T00:00:00Z https://repositorio.ufu.br/handle/123456789/49648 Title: Relatório técnico profissional - gestão de projetos ágeis no mercado de trabalho Thu, 30 Apr 2026 00:00:00 GMT https://repositorio.ufu.br/handle/123456789/49648 2026-04-30T00:00:00Z