https://repositorio.ufu.br/handle/123456789/5142 Sat, 08 Aug 2026 16:42:00 GMT 2026-08-08T16:42:00Z https://repositorio.ufu.br:443/retrieve/9bc49516-3b2d-430b-b40d-367ebc2fccfc/logo-facom.png https://repositorio.ufu.br/handle/123456789/5142 https://repositorio.ufu.br/handle/123456789/49371 Title: Uma abordagem interpretável para a detecção de ransomware baseada no consenso de SHAP Abstract: This study investigates the detection of ransomware malware based on artifacts extracted from memory using machine learning techniques. The Canadian Institute for Cybersecurity Malware Memory Dataset 2022 (CIC-MalMem-2022) was used, containing behavioral information on benign processes and ransomware variants. Initially, data preprocessing was performed, including class balancing, the removal of irrelevant attributes, and the elimination of redundancies among highly correlated features. Subsequently, four supervised algorithms—Decision Tree, Random Forest, K-Nearest Neighbors (KNN), and AdaBoost—were evaluated through 10-fold stratified cross-validation, using metrics such as accuracy, precision, recall, F1-score, and confusion matrices. Subsequently, the explainability technique SHapley Additive exPlanations (SHAP) was applied to identify the importance of the features used by the models. Based on this analysis, a reduced set of attributes was generated through consensus among the models, enabling retraining and performance comparison. The results demonstrated that the reduced feature set maintained performance equivalent to that of the complete set, achieving an accuracy above 99.9% across all evaluated models. It is concluded that explainability-based feature selection can reduce data dimensionality without compromising detection capability, favoring lighter and more interpretable solutions for ransomware detection. Wed, 25 Mar 2026 00:00:00 GMT https://repositorio.ufu.br/handle/123456789/49371 2026-03-25T00:00:00Z https://repositorio.ufu.br/handle/123456789/49367 Title: Projeto de plataforma para gestão de programas de habitação de interesse social: Minha Casa, Minha Vida - Faixa 1 Abstract: This work presents the development and prototyping of a web platform aimed at managing social housing processes, with a specific focus on Faixa 1 of the Minha Casa, Minha Vida Program (PMCMV). The identified problem is the lack of integrated systems in municipalities, especially small and medium-sized ones, to standardize, track, and efficiently operate the stages of application, evaluation, and contracting of program beneficiaries, which compromises the transparency and effectiveness of housing initiatives. Thus, a modular digital solution is proposed, adaptable to current legislation and municipal realities, in order to significantly improve the management of these processes. The platform was modeled based on real workflows observed in municipal public administrations. In addition, two modules (Application and Evaluation) were implemented, and a third (Contracting) was modeled, meeting the defined functional and non-functional requirements. The results indicate the technical feasibility of the solution, with potential practical application in public administration, contributing to the transparency, traceability, and efficiency of PMCMV Faixa 1 processes. Thu, 25 Sep 2025 00:00:00 GMT https://repositorio.ufu.br/handle/123456789/49367 2025-09-25T00:00:00Z https://repositorio.ufu.br/handle/123456789/49355 Title: Segmentação geométrica de núcleos em Imagens microscópicas do desenvolvimento embrionário da Drosophila melanogaster Abstract: Drosophila melanogaster is a widely used model organism in developmental biology, and microscopy image analysis is an essential tool for quantifying cellular patterns. In this context, this work presents a computer vision-based approach for nuclear instance segmentation in microscopy images of embryos, focusing on high-density scenarios with touching structures. The proposed method uses a geometric pipeline that models contours in polar representation 𝑟(𝜃) and detects concavities from radial variations with respect to a reference derived from the convex hull. Based on these concavities, directional alignment rules, geometric consistency criteria, and fallback mechanisms are used to determine separation cuts between possible nuclear instances. To support the application and validation of the approach, an open-source Python software with a graphical user interface was developed, integrating visual parameter tuning, batch processing, inspection of intermediate steps, and automatic metric extraction. The quantitative evaluation was conducted on a subset of images containing wild-type and mutant samples, using manually annotated reference masks (ground truth) spatially normalized through B-Spline interpolation (BOOR, 2001). The results indicated promising performance in nuclear mass delineation, reaching a Dice coefficient of up to 85.6% in the baseline model. At the instance level, the method showed variable performance across samples, with F1-Score values of up to 77.0%, indicating that the approach is promising for nucleus individualization in part of the evaluated scenarios, although it still presents limitations in cases of higher morphological complexity. Parameter calibration also showed potential for reducing geometric segmentation errors. Fri, 08 May 2026 00:00:00 GMT https://repositorio.ufu.br/handle/123456789/49355 2026-05-08T00:00:00Z https://repositorio.ufu.br/handle/123456789/49252 Title: Avaliação de diferentes metodologias para o ensino de computação gráfica em nível superior Fri, 08 May 2026 00:00:00 GMT https://repositorio.ufu.br/handle/123456789/49252 2026-05-08T00:00:00Z