https://repositorio.ufu.br/handle/123456789/18919 2026-04-05T01:14:42Z 2026-04-05T01:14:42Z https://repositorio.ufu.br/handle/123456789/48403 2026-02-26T06:26:07Z 2025-09-23T00:00:00Z

Title: Observatório de cibercrimes: prototipação e desenvolvimento do painel web interativo Abstract: The growth of crimes committed in the digital environment has pressured public au- thorities and academia to develop tools that make cybercrime data more accessible and interpretable. This work presents the development of an interactive web dashboard for analyzing judicial decisions classified as cybercrimes in the State of São Paulo. The sys- tem consumes a public API of legal cases, filters only records marked as cybercrimes, and performs data processing (date standardization, normalization of municipality names, and aggregations by year, subject, and district). The interface, built with Angular and ECharts, provides a choropleth map (heatmap) of São Paulo municipalities, bar charts by year, a pie chart by subject, a ranking of topics, and a searchable, paginated table of cases. Map ranges are calculated dynamically: when the maximum number of cases on the map is ≤ 4, integer steps (1, 2, 3, 4) are used, and in larger scenarios, breakpoints by percentiles (25%, 50%, and 75%) are applied, avoiding overlap and reinforcing readability. The dashboard is responsive, offers light/dark mode, and includes a state selector prepared for future datasets. Results show that the solution enables the exploration of temporal and spatial patterns with low response time, preserving privacy through aggregated pub- lic data. This work contributes a replicable pipeline for geovisualization of judicial data and a functional prototype, paving the way to extend coverage to other states and data sources.

2025-09-23T00:00:00Z https://repositorio.ufu.br/handle/123456789/48381 2026-02-25T06:19:14Z 2025-12-16T00:00:00Z

Title: Agente inteligente para qualificação de leads no setor automotivo utilizando machine learning Abstract: This Final Year Project details the development, implementation, and comparison of Machine Learning models for intelligent lead- potential customers who have demonstrated initial interest through digital channels- qualification at a luxury car dealership, facilitated by an Artificial Intelligence agent named “Betina”. Motivated by the need to optimize customer service amidst growing digital demand and the consequent overload of the sales team, the solution evolved from a Minimum Viable Product (MVP) on a no-code platform (Zaia) to a robust architecture integrating Make.com, ChatGPT-4o, and a custom ML API. The core of this study lies in the comparison of two predictive approaches trained on a dataset of 72 historical conversations: (1) a Random Forest classifier utilizing TF IDF and behavioral features, interpreted via a surrogate model; and (2) the fine-tuning of Transformer models (BERT and mBERT). The methodology encompassed advanced preprocessing, including speaker separation and data anonymization. While the fine-tuning of BERT demonstrated potential for high accuracy, computational constraints limited its viability in this context. Conversely, the Random Forest model proved to be a robust and interpretable solution, yielding actionable insights. The project validates the system’s effectiveness through empirical case analysis and the generation of strategic insights for the sales team regarding qualified leads, demonstrating the practical application and challenges of deploying AI and ML techniques to optimize business processes.

2025-12-16T00:00:00Z https://repositorio.ufu.br/handle/123456789/48321 2026-02-20T06:25:43Z 2025-09-22T00:00:00Z

Title: Plataformas digitais para a educação online: projeto e desenvolvimento do Observatório de Ensino de História e Geografia

2025-09-22T00:00:00Z https://repositorio.ufu.br/handle/123456789/48121 2026-01-31T06:23:49Z 2025-10-31T00:00:00Z

Title: Álgebra computacional com ênfase em Grupo Simétrico usando o GAP

2025-10-31T00:00:00Z